lit paper google

Locked-Image Tuning: Adding Language Understanding to Image Models

The ability to classify images into categories has been transformed by deep learning. It has also been significantly accelerated by transfer learning , whereby models are first pre-trained on large datasets, like ImageNet , to learn visual representations that are then transferred via fine-tuning to a new task with less data (e.g., classifying animals). Previous works such as BiT and ViT employed these methods to achieve state-of-the-art performance on a wide range of classification tasks, such as the VTAB benchmark .

However, fine-tuning has some downsides: though pre-training is done only once, fine-tuning is necessary on every new dataset for which task-specific data is needed. Multimodal contrastive learning is an alternative, recently popularized paradigm (e.g., CLIP , ALIGN ) that overcomes these issues by instead learning how to match free-form text with images. These models can then solve new tasks by reformulating them as image-text matching problems, without extra data (referred to as “zero-shot” learning). Contrastive learning is flexible and easy to adapt to new tasks, but has its own limitations, namely the need for a lot of paired image-text data and weaker performance than transfer learning approaches.

With those limitations in mind, we propose “ LiT: Zero-Shot Transfer with Locked-image Text Tuning ”, to appear at CVPR 2022 . LiT models learn to match text to an already pre-trained image encoder. This simple yet effective setup provides the best of both worlds: strong image representations from pre-training, plus flexible zero-shot transfer to new tasks via contrastive learning. LiT achieves state-of-the-art zero-shot classification accuracy, significantly closing the gap between the two styles of learning. We think the best way to understand is to try it yourself, so we’ve included a demo of LiT models at the end of this post.

Contrastive Learning on Image-Text Data

Contrastive learning models learn representations from “positive” and “negative” examples, such that representations for "positive" examples are similar to each other but different from "negative" examples.

Multimodal contrastive learning applies this to pairs of images and associated texts. An image encoder computes representations from images, and a text encoder does the same for texts. Each image representation is encouraged to be close to the representation of its associated text (“positive”), but distinct from the representation of other texts ("negatives") in the data, and vice versa. This has typically been done with randomly initialized models (“from scratch”), meaning the encoders have to simultaneously learn representations and how to match them.

This training can be done on noisy, loosely aligned pairs of image and text, which naturally occur on the web. This circumvents the need for manual labeling, and makes data scaling easy. Furthermore, the model learns much richer visual concepts — it’s not constrained to what’s defined in the classification label space. Instead of classifying an image as “coffee”, it can understand whether it’s "a small espresso in a white mug” or “a large latte in a red flask”.

Once trained, a model that aligns image and text can be used in many ways . For zero-shot classification, we compare image representations to text representations of the class names. For example, a “wombat vs jaguar” classifier can be built by computing the representations of the texts “ jaguar ” and “ wombat ”, and classifying an image as a jaguar if its representation better matches the former. This approach scales to thousands of classes and makes it very easy to solve classification tasks without the extra data necessary for fine-tuning. Another application of contrastive models is image search (a.k.a. image-text retrieval), by finding the image whose representation best matches that of a given text, or vice versa.

The Best of Both Worlds with Locked-image Tuning

As mentioned earlier, transfer learning achieves state-of-the-art accuracy, but requires per-task labels, datasets, and training. On the other hand, contrastive models are flexible, scalable, and easily adaptable to new tasks, but fall short in performance. To compare, at the time of writing, the state of the art on ImageNet classification using transfer learning is 90.94% , but the best contrastive zero-shot models achieve 76.4% .

LiT tuning bridges this gap: we contrastively train a text model to compute representations well aligned with the powerful ones available from a pre-trained image encoder. Importantly, for this to work well, the image encoder should be “locked“, that is: it should not be updated during training. This may be unintuitive since one usually expects the additional information from further training to increase performance, but we find that locking the image encoder consistently leads to better results.

This can be considered an alternative to the classic fine-tuning stage, where the image encoder is separately adapted to every new classification task; instead we have one stage of LiT-tuning, after which the model can classify any data. LiT-tuned models achieve 84.5% zero-shot accuracy on ImageNet classification, showing significant improvements over previous methods that train models from scratch, and halving the performance gap between fine-tuning and contrastive learning.

An impressive benefit of contrastive models is increased robustness — they retain high accuracy on datasets that typically fool fine-tuned models, such as ObjectNet and ImageNet-C . Similarly, LiT-tuned models have high performance across various challenging versions of ImageNet, for example achieving a state-of-the-art 81.1% accuracy on ObjectNet.

LiT-tuning has other advantages. While prior contrastive works require large amounts of data and train for a very long time, the LiT approach is much less data hungry. LiT models trained on 24M publicly available image-text pairs rival the zero-shot classification performance of prior models trained on 400M image-text pairs of private data. The locked image encoder also leads to faster training with a smaller memory footprint. On larger datasets, image representations can be pre-computed; not running the image model during training further improves efficiency and also unlocks much larger batch sizes, which increases the number of “negatives” the model sees and is key to high-performance contrastive learning. The method works well with varied forms of image pre-training (e.g., including self-supervised learning), and with many publicly available image models. We hope that these benefits make LiT a great testbed for researchers.

We present Locked-image Tuning (LiT), which contrastively trains a text encoder to match image representations from a powerful pre-trained image encoder. This simple method is data and compute efficient, and substantially improves zero-shot classification performance compared to existing contrastive learning approaches.

Want to try it yourself?

We have prepared a small interactive demo to try some LiT-tuned models. We also provide a Colab with more advanced use cases and larger models, which are a great way to get started.

Acknowledgments

We would like to thank Xiaohua Zhai, Xiao Wang, Daniel Keysers, Alexander Kolesnikov, and Lucas Beyer who have co-authored the LiT paper and been involved in all aspects of its development, as well as the Brain team in Zürich. We also would like to thank Tom Small for creating the animations used in this blogpost.

The Learning Interpretability Tool (LIT) is for researchers and practitioners looking to understand NLP model behavior through a visual, interactive, and extensible tool.

Use LIT to ask and answer questions like:

• What kind of examples does my model perform poorly on?
• Why did my model make this prediction? Can it attribute it to adversarial behavior, or undesirable priors from the training set?
• Does my model behave consistently if I change things like textual style, verb tense, or pronoun gender?

LIT contains many built-in capabilities but is also customizable, with the ability to add custom interpretability techniques, metrics calculations, counterfactual generators, visualizations, and more.

In addition to language, LIT also includes preliminary support for models operating on tabular and image data. For a similar tool built to explore general-purpose machine learning models, check out the What-If Tool .

LIT can be run as a standalone server, or inside of python notebook environments such as Colab, Jupyter, and Google Cloud Vertex AI Notebooks.

Built-in capabilities

Salience maps

Attention visualization

Metrics calculations

Counterfactual generation

Model and datapoint comparison

Embedding visualization

And more...

Supported task types

Classification

Text generation / seq2seq

Masked language models

Span labeling

Multi-headed models

Image and tabular data

Framework agnostic

TensorFlow 1.x

TensorFlow 2.x

Notebook compatibility

Custom inference code

Remote Procedure Calls

What's the latest

Version 1.0

Documentation

Demo Paper at EMNLP ‘20

LiT: Zero-Shot Transfer with Locked-image Tuning

This page is an interactive demo of the Google AI blog post LiT: adding language understanding to image models – please refer to that page for a detailed explanation of how a LiT model works. If you're interested in how this demo makes a JAX model run on device in your browser, check out our other blog post JAX on the Web with TensorFlow.js .

Below you can choose an image from a selection and then write free-form text prompts that are matched to the image. Once you hit return on your keyboard or press the "compute" button, a text encoder implemented in TensorFlow.js will compute embeddings for the provided text on your local device, and the similarity of these text embeddings to the image embedding will be displayed.

The prompts can be used to classify an image into multiple categories, listing each category individually with a prompt "an image of a X". But you can also probe the model interactively with more detailed prompts, comparing the different results when small details change in the text.

Please use this demo responsibly. The models will always compare the image to the prompts you provide, and it is therefore trivial to construct situations where the model picks from a bunch of bad options.

Note: The models available in this interactive demo are not those from the paper . We had to train much smaller text towers and tokenizers to avoid overloading your browser. Please see our GitHub repository for the models from the paper pre-trained on public datasets. Multilingual models coming soon.

Google open-sources LIT, a toolset for evaluating natural language models

• Share on Facebook
• Share on LinkedIn

Join us in Atlanta on April 10th and explore the landscape of security workforce. We will explore the vision, benefits, and use cases of AI for security teams. Request an invite here.

Google-affiliated researchers today released the Language Interpretability Tool (LIT) , an open source, framework-agnostic platform and API for visualizing, understanding, and auditing natural language processing models. It focuses on questions about AI model behavior, like why models made certain predictions and why they’re performing poorly with input corpora. LIT incorporates aggregate analysis into a browser-based interface that’s designed to enable explorations of text generation behavior.

Advances in modeling have led to unprecedented performance on natural language processing tasks, but questions remain about models’ tendencies to behave according to biases and heuristics. There’s no silver bullet for analysis — data scientists must often employ several techniques to build a comprehensive understanding of model behavior.

That’s where LIT comes in. The tool set is architected so that users can hop between visualizations and analysis to test hypotheses and validate those hypotheses over a data set. New data points can be added on the fly and their effect on the model visualized immediately, while side-by-side comparison allows for two models or two data points to be visualized simultaneously. And LIT calculates and displays metrics for entire data sets to spotlight patterns in model performance, including the current selection, manually generated subsets, and automatically generated subsets.

LIT supports a wide range of natural language processing tasks like classification, language modeling, and structured prediction. It’s extensible and can be reconfigured for novel workflows, and the components are self-contained, portable, and simple to implement, its creators claim. LIT works with any model that can run from Python, the Google researchers say, including TensorFlow, PyTorch, and remote models on a server. And it has a low barrier to entry, with only a small amount of code needed to add models and data.

The AI Impact Tour – Atlanta

To demonstrate LIT’s robustness, the researchers conducted a series of case studies in sentiment analysis, gender debiasing, and model debugging. They show how the tool set can expose bias in a coreference model trained on the open source OntoNotes data set, for example revealing where certain occupations are associated with a high proportion of male workers. “In LIT’s metrics table, we can slice a selection by pronoun type and by the true referent,” the Google developers behind LIT wrote in a technical paper . “On the set of male-dominated occupations, we see the model performs well when the ground-truth agrees with the stereotype — e.g. when the answer is the occupation term, male pronouns are correctly resolved 83% of the time, compared to female pronouns only 37.5% of the time.”

The team cautions that LIT doesn’t scale well to large corpora and that it’s not “directly” useful for training-time model monitoring. But they say that in the near future, the tool set will gain features like counterfactual generation plugins, additional metrics and visualizations for sequence and structured output types, and a greater ability to customize the UI for different applications.

Stay in the know! Get the latest news in your inbox daily

By subscribing, you agree to VentureBeat's Terms of Service.

Thanks for subscribing. Check out more VB newsletters here .

An error occured.

• Português – Brasil

Deploying Learning Interpretability Tool (LIT) Demo on Google Cloud Platform

1. overview.

This lab provides the instructions to deploy a LIT demo quickly. The objective is to familiarize you with the LIT tool to explore the model behavior. You will conduct a sentimental analysis and use the Counterfactual LIT feature to find the importance of specific words. The demo includes a dataset to carry out the analysis. The lab provides steps to deploy LIT in the Google Cloud Platform, analyze the data, and delete the deployed services.

What is the Learning Interpretability Tool (LIT)?

🔥LIT is a visual, interactive ML model-understanding tool that supports text, image, and tabular data. It can be run as a standalone server, or inside of notebook environments such as Colab, Jupyter, and Google Cloud Vertex AI notebooks.

LIT is built to answer questions such as:

• What kind of examples does my model perform poorly on?
• Why did my model make this prediction? Can this prediction be attributed to adversarial behavior, or to undesirable priors in the training set?
• Does my model behave consistently if I change things like textual style, verb tense, or pronoun gender?

The tool is available in LIT Github Repo . A paper for it also is available in the ArXiv .

What you will do

You will create a docker image available from the LIT Git Repo, push it to a registry, and deploy to Cloud Run. You will then explore the LIT tool. You have used the Cloud Run service to deploy the container but you can deploy the image to Google Kubernetes Engine.

You will use Google Cloud Shell and Google Cloud Workbench as launch pads to run the commands. You will use the latter specifically to build, push, and deploy the container image. Vertex AI Workbench instances are Jupyter notebook-based development environments for the entire data science workflow. You can interact with Vertex AI and other Google Cloud services from within a Vertex AI Workbench instance's Jupyter notebook.

You will use Google Artifactory Registry that enables you to centrally store artifacts and build dependencies as part of an integrated Google Cloud experience. You will upload the docker image to the Artifactory registry. You can learn more about the it at Google Cloud Artifactory Registry documentation.

You will use Google Cloud Cloud Run , a managed Knative service, to deploy the docker image. It is a managed compute platform that lets you run containers directly on top of Google's scalable infrastructure.

You could also deploy the image in Google Cloud Kubernetes Engine , a managed Kubernetes container orchestration service. You can use it to deploy and operate containerized applications at scale using Google's infrastructure.

The demo uses the Stanford Sentiment Treebank dataset.

"The Stanford Sentiment Treebank is the first corpus with fully labeled parse trees that allows for a complete analysis of the compositional effects of sentiment in language. The corpus is based on the dataset introduced by Pang and Lee (2005) and consists of 11,855 single sentences extracted from movie reviews. It was parsed with the Stanford parser (Klein and Manning, 2003) and includes a total of 215,154 unique phrases from those parse trees, each annotated by 3 human judges." Reference paper

Before you begin

For this reference guide, you need a Google Cloud project . You can create a new one, or select a project you already created.

• Select or create a Google Cloud project .
• Make sure that billing is enabled for your project .

2. Launch Google Cloud Console and a Cloud Shell

You will launch a Google Cloud Console and use the Google Cloud Shell in this step.

2-a: Launch a Google Cloud Console

Launch a browser and go to Google Cloud Console .

The Google Cloud Console is a powerful, secure web admin interface that lets you manage your Google Cloud resources quickly. It's a DevOps tool on the go.

2-b: Launch a Google Cloud Shell

Launch a Google Cloud Shell. See the picture below for reference.

You should see something like this:

You will be using the command prompt in the next steps.

Cloud Shell is an online development and operations environment accessible anywhere with your browser. You can manage your resources with its online terminal preloaded with utilities such as the gcloud command-line tool, kubectl, and more. You can also develop, build, debug, and deploy your cloud-based apps using the online Cloud Shell Editor. Cloud Shell provides a developer ready, online environment with a preinstalled favorite tool set and 5GB of persistent storage space.

2-c: Set Google Cloud Project

Set the Google Cloud project and the location where you will create the Google Cloud services. You will use the information to create a Google Cloud Workbench and an Artifactory Registry. You will use the former to build, and push a container. You will use the latter to store the container image.

You must set the only mandatory PROJECT_ID variable. You can modify the other variables, but the default values are sufficient to run the lab. Set the correct Google Cloud Project. This is used by the gcloud command.

3. Create a Google Cloud Artifact Registry

You will store the container image of the LIT demo in the registry.

4. Create a Google Cloud Workbench

You will create a Workbench instance. You will use the Workbench Terminal to build, and push a container image of the LIT demo.

4-a: Set a few variables

Set shell variables that are used to create a Workbench instance.

4-b: Create a Google Cloud Workbench

Create a Workbench instance. You will use this instance to build, push, and deploy the container image with LIT demo.

Click on the web url, $WB_URL, to launch the Workbench in a web browser.

You have used the --format flag to gather specific value from the gcloud response. You can do a lot more. You can read about format, filters, etc. in the following blog post: Filter, format, and transform data with gcloud, Google Cloud's command line interface .

5. Launch a Terminal in the Workbench (WB)

Launch a Terminal from the Workbench (WB) web page. See the picture below for reference.

You will be working on the terminal in the next few Steps.

6. Git clone LIT repo

You will use the Workbench terminal to build, and push a container image of the LIT demo.

6-a: Set variables in the WB Terminal

Set the Google Cloud project and the location where you will create the Google Cloud services.

6-b: Authenticate with Google Cloud

Set up the proper Google Cloud security context. The email you will sign with is the context we need to continue the lab.

There are various ways to sign in to the gcloud. You can learn them in our doucumentation page .

6-c: Set Google Cloud project

Set the correct Google Cloud Project. This is used by the gcloud command.

Create a LIT directory for your work

Clone the lit git repo, 7. build a container image and push it to the artifact registry.

In the Workbench terminal, run the commands below. You can optionally set a few shell variables for which we already set the default values.

8. Create a Cloud Run with the above docker image

Deploy the demo LIT container that you created above to a Cloud Run service. In the Workbench terminal, run the below commands.

After creating the service i.e. executing the gcloud run above, you can watch the logs in the Google Cloud Console.

Navigation: Top Bar in the Google Cloud Console → Cloud Run (in the search bar) → select the demo1 application → select the LOGS. You can also check the METRICS, etc.

In the Google Cloud Console use the Search and type ‘Cloud Run'. See the picture below for reference.

Select the ‘demo1' service that you just created. See the picture below for your reference.

9. Gather the LIT Service deployed URL

Either gather the url using the following command or click the ‘URL' in the Google Cloud Console Cloud Run service.

See the picture below for your reference.

Use the command below to gather the LIT service url:

The LIT demo takes a while to render the web page; after all, it loads a large image and downloads the model it uses. You can watch the Cloud Run LOGS for these activities.

10. Browse the URL and play with the LIT demo

The LIT demo looks like the screenshot below:

You will be checking the Sentimental Analysis on the Stanford Sentiment Treebank dataset. Follow the below steps

• Use the search function in the LIT's data table to find the 56 data points containing the word ‘not'.

• Check the BERT model accuracy in the Metrics Table. The BERT model's accuracy is high.

• Select individual data points and look for explanations. Search for the word ‘depression'.

• Select "It's not the ultimate depression-era gangster movie." Check the Salience Map. Salience maps suggest that "not" and "ultimate" are important to the prediction.

There are many LIT features that you can try. You can find our short Youtube video or the LIT ArXiv explaining the LIT features.

11. Congratulations

Well done on completing the codelab! Time to chill!

To clean up the lab, delete all the Google Cloud Services created for the lab. Use Google Cloud Shell to run the following commands.

If the Google Cloud Connection is lost because of inactivity, then reset the variables. Follow 2-c and 4-1 to set the shell variables and to set the Google Cloud Project.

Further reading

Continue learning the LIT tool features with the below materials:

• LIT open source code base: Git repo
• LIT paper: ArXiv
• LIT feature video demo: Youtube

This work is licensed under a Creative Commons Attribution 2.0 Generic License.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates.

Literature Review: Google Scholar

• Sample Searches
• Examples of Published Literature Reviews
• Researching Your Topic
• Subject Searching
• Google Scholar
• Track Your Work
• Citation Managers This link opens in a new window
• Citation Guides This link opens in a new window
• Tips on Writing Your Literature Review This link opens in a new window
• Research Help

Ask a Librarian

Chat with a Librarian

Lisle: (630) 829-6057 Mesa: (480) 878-7514 Toll Free: (877) 575-6050 Email: [email protected]

Book a Research Consultation Library Hours

Google Scholar Library Links

To see links to BenU Library subscription content in your Google Scholar search results:

• Go to Google Scholar > Settings > Library Links
• Search " Benedictine "
• Check the boxes
• Click Save and you're done!
• Google Scholar Library Links Tutorial This tutorial will guide you step-by-step through the quick setup process.

Finding Academic Literature

• 8 Winning hacks to use Google Scholar for your research paper

• << Previous: Subject Searching
• Next: Track Your Work >>
• Last Updated: Feb 27, 2023 2:09 PM
• URL: https://researchguides.ben.edu/lit-review

Kindlon Hall 5700 College Rd. Lisle, IL 60532 (630) 829-6050

Gillett Hall 225 E. Main St. Mesa, AZ 85201 (480) 878-7514

Stand on the shoulders of giants

Google Scholar provides a simple way to broadly search for scholarly literature. From one place, you can search across many disciplines and sources: articles, theses, books, abstracts and court opinions, from academic publishers, professional societies, online repositories, universities and other web sites. Google Scholar helps you find relevant work across the world of scholarly research.

How are documents ranked?

Google Scholar aims to rank documents the way researchers do, weighing the full text of each document, where it was published, who it was written by, as well as how often and how recently it has been cited in other scholarly literature.

Features of Google Scholar

• Search all scholarly literature from one convenient place
• Explore related works, citations, authors, and publications
• Locate the complete document through your library or on the web
• Keep up with recent developments in any area of research
• Check who's citing your publications, create a public author profile

Disclaimer: Legal opinions in Google Scholar are provided for informational purposes only and should not be relied on as a substitute for legal advice from a licensed lawyer. Google does not warrant that the information is complete or accurate.

• Privacy & Terms

Help | Advanced Search

Computer Science > Computation and Language

Title: long-form factuality in large language models.

Abstract: Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user's preferred response length (recall). Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators - on a set of ~16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality. LongFact, SAFE, and all experimental code are available at this https URL .

Submission history

Access paper:.

• Other Formats

References & Citations

• Google Scholar
• Semantic Scholar

BibTeX formatted citation

Bibliographic and Citation Tools

Code, data and media associated with this article, recommenders and search tools.

• Institution

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Using google scholar to conduct a literature search

Affiliation.

• 1 North Somerset Healthcare Library, Weston General Hospital, Weston Area Health NHS Trust, Weston Super Mare. [email protected]
• PMID: 20701052
• DOI: 10.7748/ns2010.07.24.45.40.c7906

This article provides information about conducting a literature search on the Google Scholar website. The article briefly describes how to narrow or expand a search and how to find non-journal literature. Although Google Scholar is not without limitations, it offers a practical starting point for a literature search.

• Education, Continuing
• Information Storage and Retrieval*

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, generate accurate citations for free.

• Knowledge Base

Methodology

• How to Write a Literature Review | Guide, Examples, & Templates

How to Write a Literature Review | Guide, Examples, & Templates

Published on January 2, 2023 by Shona McCombes . Revised on September 11, 2023.

What is a literature review? A literature review is a survey of scholarly sources on a specific topic. It provides an overview of current knowledge, allowing you to identify relevant theories, methods, and gaps in the existing research that you can later apply to your paper, thesis, or dissertation topic .

There are five key steps to writing a literature review:

• Search for relevant literature
• Evaluate sources
• Identify themes, debates, and gaps
• Outline the structure
• Write your literature review

A good literature review doesn’t just summarize sources—it analyzes, synthesizes , and critically evaluates to give a clear picture of the state of knowledge on the subject.

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

What is the purpose of a literature review, examples of literature reviews, step 1 – search for relevant literature, step 2 – evaluate and select sources, step 3 – identify themes, debates, and gaps, step 4 – outline your literature review’s structure, step 5 – write your literature review, free lecture slides, other interesting articles, frequently asked questions, introduction.

• Quick Run-through
• Step 1 & 2

When you write a thesis , dissertation , or research paper , you will likely have to conduct a literature review to situate your research within existing knowledge. The literature review gives you a chance to:

• Demonstrate your familiarity with the topic and its scholarly context
• Develop a theoretical framework and methodology for your research
• Position your work in relation to other researchers and theorists
• Show how your research addresses a gap or contributes to a debate
• Evaluate the current state of research and demonstrate your knowledge of the scholarly debates around your topic.

Writing literature reviews is a particularly important skill if you want to apply for graduate school or pursue a career in research. We’ve written a step-by-step guide that you can follow below.

Here's why students love Scribbr's proofreading services

Discover proofreading & editing

Writing literature reviews can be quite challenging! A good starting point could be to look at some examples, depending on what kind of literature review you’d like to write.

• Example literature review #1: “Why Do People Migrate? A Review of the Theoretical Literature” ( Theoretical literature review about the development of economic migration theory from the 1950s to today.)
• Example literature review #2: “Literature review as a research methodology: An overview and guidelines” ( Methodological literature review about interdisciplinary knowledge acquisition and production.)
• Example literature review #3: “The Use of Technology in English Language Learning: A Literature Review” ( Thematic literature review about the effects of technology on language acquisition.)
• Example literature review #4: “Learners’ Listening Comprehension Difficulties in English Language Learning: A Literature Review” ( Chronological literature review about how the concept of listening skills has changed over time.)

You can also check out our templates with literature review examples and sample outlines at the links below.

Download Word doc Download Google doc

Before you begin searching for literature, you need a clearly defined topic .

If you are writing the literature review section of a dissertation or research paper, you will search for literature related to your research problem and questions .

Make a list of keywords

Start by creating a list of keywords related to your research question. Include each of the key concepts or variables you’re interested in, and list any synonyms and related terms. You can add to this list as you discover new keywords in the process of your literature search.

• Social media, Facebook, Instagram, Twitter, Snapchat, TikTok
• Body image, self-perception, self-esteem, mental health
• Generation Z, teenagers, adolescents, youth

Search for relevant sources

Use your keywords to begin searching for sources. Some useful databases to search for journals and articles include:

• Your university’s library catalogue
• Google Scholar
• Project Muse (humanities and social sciences)
• Medline (life sciences and biomedicine)
• EconLit (economics)
• Inspec (physics, engineering and computer science)

You can also use boolean operators to help narrow down your search.

Make sure to read the abstract to find out whether an article is relevant to your question. When you find a useful book or article, you can check the bibliography to find other relevant sources.

You likely won’t be able to read absolutely everything that has been written on your topic, so it will be necessary to evaluate which sources are most relevant to your research question.

For each publication, ask yourself:

• What question or problem is the author addressing?
• What are the key concepts and how are they defined?
• What are the key theories, models, and methods?
• Does the research use established frameworks or take an innovative approach?
• What are the results and conclusions of the study?
• How does the publication relate to other literature in the field? Does it confirm, add to, or challenge established knowledge?
• What are the strengths and weaknesses of the research?

Make sure the sources you use are credible , and make sure you read any landmark studies and major theories in your field of research.

You can use our template to summarize and evaluate sources you’re thinking about using. Click on either button below to download.

Take notes and cite your sources

As you read, you should also begin the writing process. Take notes that you can later incorporate into the text of your literature review.

It is important to keep track of your sources with citations to avoid plagiarism . It can be helpful to make an annotated bibliography , where you compile full citation information and write a paragraph of summary and analysis for each source. This helps you remember what you read and saves time later in the process.

Receive feedback on language, structure, and formatting

Professional editors proofread and edit your paper by focusing on:

• Academic style
• Vague sentences
• Style consistency

See an example

To begin organizing your literature review’s argument and structure, be sure you understand the connections and relationships between the sources you’ve read. Based on your reading and notes, you can look for:

• Trends and patterns (in theory, method or results): do certain approaches become more or less popular over time?
• Themes: what questions or concepts recur across the literature?
• Debates, conflicts and contradictions: where do sources disagree?
• Pivotal publications: are there any influential theories or studies that changed the direction of the field?
• Gaps: what is missing from the literature? Are there weaknesses that need to be addressed?

This step will help you work out the structure of your literature review and (if applicable) show how your own research will contribute to existing knowledge.

• Most research has focused on young women.
• There is an increasing interest in the visual aspects of social media.
• But there is still a lack of robust research on highly visual platforms like Instagram and Snapchat—this is a gap that you could address in your own research.

There are various approaches to organizing the body of a literature review. Depending on the length of your literature review, you can combine several of these strategies (for example, your overall structure might be thematic, but each theme is discussed chronologically).

Chronological

The simplest approach is to trace the development of the topic over time. However, if you choose this strategy, be careful to avoid simply listing and summarizing sources in order.

Try to analyze patterns, turning points and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred.

If you have found some recurring central themes, you can organize your literature review into subsections that address different aspects of the topic.

For example, if you are reviewing literature about inequalities in migrant health outcomes, key themes might include healthcare policy, language barriers, cultural attitudes, legal status, and economic access.

Methodological

If you draw your sources from different disciplines or fields that use a variety of research methods , you might want to compare the results and conclusions that emerge from different approaches. For example:

• Look at what results have emerged in qualitative versus quantitative research
• Discuss how the topic has been approached by empirical versus theoretical scholarship
• Divide the literature into sociological, historical, and cultural sources

Theoretical

A literature review is often the foundation for a theoretical framework . You can use it to discuss various theories, models, and definitions of key concepts.

You might argue for the relevance of a specific theoretical approach, or combine various theoretical concepts to create a framework for your research.

Like any other academic text , your literature review should have an introduction , a main body, and a conclusion . What you include in each depends on the objective of your literature review.

The introduction should clearly establish the focus and purpose of the literature review.

Depending on the length of your literature review, you might want to divide the body into subsections. You can use a subheading for each theme, time period, or methodological approach.

As you write, you can follow these tips:

• Summarize and synthesize: give an overview of the main points of each source and combine them into a coherent whole
• Analyze and interpret: don’t just paraphrase other researchers — add your own interpretations where possible, discussing the significance of findings in relation to the literature as a whole
• Critically evaluate: mention the strengths and weaknesses of your sources
• Write in well-structured paragraphs: use transition words and topic sentences to draw connections, comparisons and contrasts

In the conclusion, you should summarize the key findings you have taken from the literature and emphasize their significance.

When you’ve finished writing and revising your literature review, don’t forget to proofread thoroughly before submitting. Not a language expert? Check out Scribbr’s professional proofreading services !

This article has been adapted into lecture slides that you can use to teach your students about writing a literature review.

Scribbr slides are free to use, customize, and distribute for educational purposes.

Open Google Slides Download PowerPoint

If you want to know more about the research process , methodology , research bias , or statistics , make sure to check out some of our other articles with explanations and examples.

• Sampling methods
• Simple random sampling
• Stratified sampling
• Cluster sampling
• Likert scales
• Reproducibility

 Statistics

• Null hypothesis
• Statistical power
• Probability distribution
• Effect size
• Poisson distribution

Research bias

• Optimism bias
• Cognitive bias
• Implicit bias
• Hawthorne effect
• Anchoring bias
• Explicit bias

A literature review is a survey of scholarly sources (such as books, journal articles, and theses) related to a specific topic or research question .

It is often written as part of a thesis, dissertation , or research paper , in order to situate your work in relation to existing knowledge.

There are several reasons to conduct a literature review at the beginning of a research project:

• To familiarize yourself with the current state of knowledge on your topic
• To ensure that you’re not just repeating what others have already done
• To identify gaps in knowledge and unresolved problems that your research can address
• To develop your theoretical framework and methodology
• To provide an overview of the key findings and debates on the topic

Writing the literature review shows your reader how your work relates to existing research and what new insights it will contribute.

The literature review usually comes near the beginning of your thesis or dissertation . After the introduction , it grounds your research in a scholarly field and leads directly to your theoretical framework or methodology .

A literature review is a survey of credible sources on a topic, often used in dissertations , theses, and research papers . Literature reviews give an overview of knowledge on a subject, helping you identify relevant theories and methods, as well as gaps in existing research. Literature reviews are set up similarly to other  academic texts , with an introduction , a main body, and a conclusion .

An  annotated bibliography is a list of  source references that has a short description (called an annotation ) for each of the sources. It is often assigned as part of the research process for a  paper .  

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

McCombes, S. (2023, September 11). How to Write a Literature Review | Guide, Examples, & Templates. Scribbr. Retrieved April 2, 2024, from https://www.scribbr.com/dissertation/literature-review/

Is this article helpful?

Shona McCombes

Other students also liked, what is a theoretical framework | guide to organizing, what is a research methodology | steps & tips, how to write a research proposal | examples & templates, what is your plagiarism score.

A free, AI-powered research tool for scientific literature

• Carl H June
• Hedge Funds

New & Improved API for Developers

Introducing semantic reader in beta.

Stay Connected With Semantic Scholar Sign Up What Is Semantic Scholar? Semantic Scholar is a free, AI-powered research tool for scientific literature, based at the Allen Institute for AI.

• +91-0000000000
• [email protected]
• Research Gate

Koshal Research Support

—Information | Knowledge | Wisdom—

How To Conduct A Literature Review Using Google Scholar Step By Step Guide

A free academic search engine known as Google Scholar (GS) is sometimes referred to as the academic counterpart of Google. Instead of searching all of the online content that has been indexed, it searches publisher repositories, academic databases, or scholarly websites.

Typically, a smaller portion of the pool gets searched by Google in this manner. Even though everything is done automatically, the majority of search results come from trustworthy academic sources. In contrast to highly moderated subscription-based academic databases like Scopus and Web of Science, Google is also less selective about what it includes in search results, therefore it is important to determine the authority of the sources linked through Google Scholar on your own.

When conducting thorough searches, such as systematic reviews, Google Scholar (and Web of Science ) shouldn’t be used as a stand-alone resource for locating evidence and finding: Title searches rather than full-text searches in Google Scholar get much more results for ancient literature.

When you are going to complete a literature review , it’s essential to collect research information from many domains and eras, and google scholar is helpful in that regard.

Now, there are a few different reasons why I prefer using Google Scholar while conducting a literature review study.

The first is that Google does a reasonably good job of discovering all of the relevant work that is available online and indexing journals, conference papers, and research databases.

The second is that Google provides us with a few useful tools that we may use to browse the literature and find new information as we search.

• Tools for Automatic Referencing
• Free Online Citation Generator Tools

In order to show you how to use Google Scholar, allow me to give you an example. Consider that our literature review is looking for information on social eye observation in robotics.

Step By Step Guide of using Google Scholar for Literature search

Step 1: Type “ Google Schola r” into the search bar and click and find the google scholar dashboard

Note: The first thing to keep in mind is that you may type “google scholar” in the search field and use the same Google tactics as you would when conducting a regular Google search.

Step 2: Now you can search any topic of your interest on the search bar of google scholar For example, you can Search Fish farming by typing the word in the search bar and clicking the enter button.

Note: Add the word(s) in question to the search tab and press Enter to look for the exact phrase. And it’s clear that Google provides us with a lengthy list of results with the same outcomes. Additionally, it provides us with the paper’s title, the authors who wrote it (although it can be difficult to see on other platforms), where it was published, and the year (see above screenshot) So feel free to click on any of these sites immediately and find the articles details.

Despite these details, Google Scholar Dashboard will also indicate on the right-hand side of this page whether the article is directly available as a PDF (see above screenshot). If so, it will also let you know which website is hosting the PDF. This is due to the fact that PDFs aren’t always hosted by the journal or conference that published the work; instead, writers may upload the PDFs on their own personal pages, for instance.

If you want to find older works that may have been published a little while ago as well as more recent publications that really show the recent R&D in the field of the subject selected.

Step 3: Google scholar allows us to search for articles based on their publication date and years and if you wish to restrict our search, you can search articles starting in the year (as shown below ) 2022, we will only see paper those that have been released in the selected years and this aids in limiting the scope to the most recent work.

As shown above, we are obtaining all 2022 academic research papers (shown in the above screenshot) that have been published in that particular field, complete with source information If you wish to look for research within specific timeframes, you may also build a custom range of your search.

Now, if you read the references in a certain paper, you can locate pertinent articles that were released earlier than that paper. But google scholar offers us a convenient way to locate publications citation and cite scores (see inside the red circle in below screenshot)

Note: If you are enjoying a specific research article and also wanted to see whether there was any additional research that was interested in it and had cited the publication. To view a list of publications that have mentioned the article we are most interested in, click the “cited by” (as shown in the red circle of below screenshot) link and see results and use these papers for your literature review.

Step 4: Google Scholar also offers the ability to automatically generate references, and you can easily obtain several citation types or styles by simply checking the cite button and finding the results as displayed below screenshot.

As mentioned above, you can find references for citations in several citation formats. To use them, just copy and paste the references into your written document’s references area.

• Citation Writing Pattern
• How to Increase Your Citation

You can see that you may acquire the citations in a variety of different standardized formats by clicking the cite link that is located beneath each article as shown in the picture above.

In fact, if you read down to the bottom, you may also find the citation in BibTeX style (see in the red circle below screenshot) a text format that you can copy and paste directly into your bib file, which is particularly useful for students studying computer science field.

You can also use one more useful feature of Google Scholar is the ability to conduct a fresh Google search inside the articles that are quoting the article we’re most interested in by selecting “search within citing articles” from the drop-down menu. And by doing so, you can significantly hone in on your area of interest.

Step 5: Google scholar dashboard also provides us with the beneficial feature of occasionally being able to click on individual author names to access that author’s research profile.

As an illustration, by clicking on my name (Koshal Kumar) here, you can find a Google Scholar profile which I set up with a picture of myself and my affiliation and citation I received till date (see below red circle) and Google automatically indexes all of the articles online that are published by me.

In this way, you can find the literature you want, and google scholar is also automatically ordered by how frequently they have been cited, but you can manually sort by recency by clicking the year or by author name and titles of the paper. Additionally, it might occasionally be helpful to research recent works by a particular author while building your literature review, and finally, Google provides us with a convenient way to cite, allowing us to determine how to cite specific articles.

I do recommend checking the citation over, because oftentimes Google automatically generates it, and there may be some weirdness or errors in the way it has handled the title or the journal-title. So that was a whirlwind tour of how to use Google Scholar to do a literature review.

This is all about this article, and we sincerely hope that these steps and advice of using google scholar in the literature review will be useful to you as you are going to search for literature review online in your journey of research and you are familiar with the online literature review process. KressUp is an online learning platform that occasionally publishes new articles; stay connected to more updates

Please share and subscribe to our website so that it can help as many people as possible. You can also write to us at [email protected] for a free consultation if you’re looking for further E-content or research support.

If you find this article useful, don’t forget to share it!

Related Articles:

• What is A literature Review and Types of Literature Review
• How to write A literature Review paper II Literature Review Paper structure
• 4 Easy Steps To Writing A Literature Review Paper
• Important Purpose of Literature Review in Research

One thought on “How To Conduct A Literature Review Using Google Scholar Step By Step Guide”

• Pingback: What Are Citation Metrics And Why Are They Important | Koshal Research Support

Leave a Reply Cancel reply

You must be logged in to post a comment.

LITERATURE REVIEW SOFTWARE FOR BETTER RESEARCH

“This tool really helped me to create good bibtex references for my research papers”

Ali Mohammed-Djafari

Director of Research at LSS-CNRS, France

“Any researcher could use it! The paper recommendations are great for anyone and everyone”

Swansea University, Wales

“As a student just venturing into the world of lit reviews, this is a tool that is outstanding and helping me find deeper results for my work.”

Franklin Jeffers

South Oregon University, USA

“One of the 3 most promising tools that (1) do not solely rely on keywords, (2) does nice visualizations, (3) is easy to use”

Singapore Management University

“Incredibly useful tool to get to know more literature, and to gain insight in existing research”

KU Leuven, Belgium

“Seeing my literature list as a network enhances my thinking process!”

Katholieke Universiteit Leuven, Belgium

“I can’t live without you anymore! I also recommend you to my students.”

Professor at The Chinese University of Hong Kong

“This has helped me so much in researching the literature. Currently, I am beginning to investigate new fields and this has helped me hugely”

Aran Warren

Canterbury University, NZ

“It's nice to get a quick overview of related literature. Really easy to use, and it helps getting on top of the often complicated structures of referencing”

Christoph Ludwig

Technische Universität Dresden, Germany

“Litmaps is extremely helpful with my research. It helps me organize each one of my projects and see how they relate to each other, as well as to keep up to date on publications done in my field”

Daniel Fuller

Clarkson University, USA

“Litmaps is a game changer for finding novel literature... it has been invaluable for my productivity.... I also got my PhD student to use it and they also found it invaluable, finding several gaps they missed”

Varun Venkatesh

Austin Health, Australia

Watch CBS News

How did April Fools' Day start and what are some famous pranks?

By Aliza Chasan

April 1, 2024 / 6:00 AM EDT / CBS News

Historians aren't pulling your leg when they say no one is quite sure about the origins of April Fools' Day. 

April 1, the annual day of shenanigans, pranks, tricks and hoaxes, falls on Monday this year. While historians are unsure of the exact source of the tradition, they do know the custom goes back centuries, at least back to Renaissance Europe and possibly back to Roman times. Here's a look at what the experts say.

Theories, both real and false, tie April Fools' Day to Roman times 

Some believe April Fools' Day dates back to Hilaria festivals celebrated during classical Roman times. The festival was held on March 25 which, in Roman terms, was called the "eighth of the Calends of April," according to the Library of Congress. 

One theory tying the source of April Fools' Day to Roman times is a hoax. In 1983, an Associated Press reporter reached out to Joseph Boskin, a historian at Boston University, to discuss the origins of April Fools' Day. Boskin spun a tall tale to the reporter, assuming it would be fact-checked and revealed as fake. 

It wasn't. 

According to the story Boskin made up, a group of jesters convinced Emperor Constantine to make one of them king for a day. The appointed jester, named Kugel, declared it would be a day of levity. 

"I got an immediate phone call from an editor there, who was furious, saying that I had ruined the career of a young reporter," Boskin said in a Boston University post. "He said I told a lie. 'A lie?' I asked, 'I was telling an April Fools' Day story.'"

Middle Ages 

Some historians believe France is responsible for the humorous tradition, tying it to a calendar change in 1582, according to the History Channel . That year, France implemented the Gregorian calendar, shifting the start of the New Year from the spring equinox, which usually falls around April 1, to January 1. 

After the change, people who wrongly celebrated the new year in late March and early April were called "April fools."

The first clear reference to April Fools' Day is a 1561 Flemish poem by Eduard De Dene, which tells the story of a servant being sent on "fool's errands" because it's April 1, according to the Library of Congress. 

What are some famous April Fools' Day pranks?

In 1957, the BBC ran a broadcast on the Italian spaghetti harvest  that pretended the pasta was being harvested from trees. 

The BBC also ran an April Fools' report on flying penguins in 2008.

In Los Angeles, airline passengers were greeted with a banner saying "Welcome to Chicago" after landing on April 1, 1992, CBS Sunday Morning previously reported.

Taco Bell in 1996 advertised that it had bought the Liberty Bell and renamed it the "Taco Liberty Bell," according to the company.

As part of a 1997 April Fools' Day joke, Alex Trebek, host of "Jeopardy," swapped places with "Wheel of Fortune" host Pat Sajak, according to jeopardy.com .

On April 1, 2015, streaming giant Netflix shared faux public service announcements to remind viewers to "Binge Responsibly."

• April Fools' Day

Aliza Chasan is a digital producer at 60 Minutes and CBSNews.com. She has previously written for outlets including PIX11 News, The New York Daily News, Inside Edition and DNAinfo. Aliza covers trending news, often focusing on crime and politics.

More from CBS News

How Americans in the solar eclipse's path of totality plan to celebrate the celestial event on April 8, 2024

Why you should open a CD this April

Climber falls 1,200 feet to death in Mount St. Helens crater

Botswana threatens to send 20,000 elephants to "roam free" in Germany