Transforming Science with Large Language Models

Welcome to the Transforming Science with Large Language Models repository! This repository is a collection of the most influential papers, AI models, and tools to empower researchers and academics worldwide to conduct their research more efficiently and effectively.

👥 Authors

Steffen Eger, Yong Cao, Jennifer D'Souza, Andreas Geiger, Christian Greisinger, Stephanie Gross, Yufang Hou, Brigitte Krenn, Anne Lauscher, Yizhi Li, Chenghua Lin, Nafise Sadat Moosavi, Wei Zhao, and Tristan Miller

📢 Updates

• 2024-01: Our conference paper, AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ has been accepted at
• 2024-09: Our conference paper, DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ has been accepted at as a Spotlight Paper
• 2025-01: Our conference paper, ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation? has been accepted at
• 2025-02: Our survey paper, Transforming Science with Large Language Models, is now available on

👀 Introduction

Science is undergoing a transformation with AI-driven tools assisting researchers at every stage of the research cycle.

Our survey provides a comprehensive overview of LLMs role in scientific workflows, structured around five key areas: search and summarization, experimentation, unimodal and multimodal content generation, and peer review.

For a detailed introduction, please refer to our survey paper.

📌 Table of Contents

• 🔍 Literature Search, Summarization, and Comparison
  • AI-Enhanced Search
  • Graph-Based
  • Paper Chat
  • Recommender
  • Search Engines
  • Benchmarks
• 💡 AI-Driven Scientific Discovery: Ideation, Hypothesis Generation, and Experimentation
  • Idea Generation
  • Hypothesis Generation
  • Automated Experimentation
• 📝 Text-based Content Generation
  • Title
  • Abstract
  • Related Work
  • Citation
  • Long Text
  • Proof-Reading and Paraphrasing
  • Press Release
• 🎨 Multimodal Content Generation and Understanding
  • Scientific Figure Understanding
  • Scientific Figure Generation
  • Scientific Table Understanding
  • Scientific Table Generation
  • Scientific Slides and Poster Generation
• ✅ Peer Review
  • Analysis of Peer Reviews
  • Paper Feedback and Automatic Reviewing
  • Scientific Rigor
  • Scientific Claim Verification
  • Meta Review Generation
• 🚀 End-to-End

🔍 Literature Search, Summarization, and Comparison

AI-Enhanced Search

Platform	Search	Reco-mmen-dations	Collec-tions	Citation Analysis	Trending Analysis	Author Profiles	Visual-ization Tools	Paper Chat	Idea Gener-ation	Paper Writing	Summa-rization	Paper Review	Data-sets	Code Reposi-tories	LLM Inte-gration	Web API	Personal-ization	Free
Elicit	✔️	❌	❌	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	✔️❌
OpenSholar	✔️	❌	✔️	❌	❌	❌	❌	✔️	❌	❌	✔️	❌	❌	❌	✔️	❌	❌	✔️
Undermind	✔️	❌	✔️	❌	❌	❌	❌	✔️	❌	❌	✔️	❌	❌	❌	✔️	❌	✔️	❌
Perplexity	✔️	❌	❌	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	✔️❌
Consensus	✔️	❌	✔️	❌	❌	❌	❌	✔️	❌	❌	✔️	❌	❌	❌	✔️	✔️	❌	✔️❌
SciSpace	✔️	❌	✔️	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	✔️❌
scienceQA	✔️	❌	✔️	✔️	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	✔️❌
PaperQA2	❌	❌	❌	❌	❌	❌	❌	✔️	❌	❌	❌	❌	❌	✔️	✔️	❌	❌	✔️
Paperguide	✔️	❌	✔️	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	✔️❌
HyperWrite	✔️	❌	❌	❌	❌	❌	❌	✔️	✔️	✔️	✔️	✔️	❌	❌	✔️	❌	❌	❌
ResearchKick	✔️	❌	❌	❌	❌	❌	❌	✔️	✔️	✔️	✔️	✔️	❌	❌	✔️	❌	✔️	❌

Graph-Based

Platform	Search	Reco-mmen-dations	Collec-tions	Citation Analysis	Trending Analysis	Author Profiles	Visual-ization Tools	Paper Chat	Idea Gener-ation	Paper Writing	Summa-rization	Paper Review	Data-sets	Code Reposi-tories	LLM Inte-gration	Web API	Personal-ization	Free
Connected Papers	✔️	❌	✔️	❌	❌	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️❌
ScholarGPS	✔️	❌	❌	✔️	✔️	✔️	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️
CiteSpace	❌	❌	❌	❌	✔️	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️❌
Sci2	❌	❌	❌	❌	❌	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️
NLP KG	✔️	❌	✔️	✔️	❌	✔️	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️
ORKG ASK	✔️	❌	✔️	❌	❌	❌	❌	❌	❌	❌	✔️	❌	❌	❌	✔️	❌	❌	✔️

Paper Chat

Platform	Search	Reco-mmen-dations	Collec-tions	Citation Analysis	Trending Analysis	Author Profiles	Visual-ization Tools	Paper Chat	Idea Gener-ation	Paper Writing	Summa-rization	Paper Review	Data-sets	Code Reposi-tories	LLM Inte-gration	Web API	Personal-ization	Free
ChatGPT	✔️	❌	❌	❌	❌	❌	❌	✔️	✔️	✔️	✔️	✔️	❌	❌	✔️	✔️	❌	✔️❌
Claude	✔️	❌	❌	❌	❌	❌	❌	✔️	✔️	✔️	✔️	✔️	❌	❌	✔️	✔️	❌	✔️❌
Deepseek	✔️	❌	❌	❌	❌	❌	❌	✔️	✔️	✔️	✔️	✔️	❌	❌	✔️	✔️	❌	✔️
Research	❌	❌	✔️	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	✔️❌
NotebookLM	❌	❌	❌	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	✔️	✔️❌
EnagoRead	✔️	❌	✔️	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	✔️	✔️❌
DocAnalyzer.AI	❌	❌	✔️	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	✔️	✔️	❌
CoralAI	❌	❌	✔️	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	✔️❌
ExplainPaper	❌	❌	❌	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	✔️❌
ChatPDF	✔️	❌	✔️	❌	❌	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	❌	❌	❌

Recommender

Platform	Search	Reco-mmen-dations	Collec-tions	Citation Analysis	Trending Analysis	Author Profiles	Visual-ization Tools	Paper Chat	Idea Gener-ation	Paper Writing	Summa-rization	Paper Review	Data-sets	Code Reposi-tories	LLM Inte-gration	Web API	Personal-ization	Free
Arxiv Sanity	✔️	✔️	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	✔️
Scholar Inbox	✔️	✔️	✔️	❌	✔️	❌	✔️	❌	❌	❌	❌	❌	❌	❌	✔️	❌	✔️	✔️
ResearchTrend.ai	✔️	❌	❌	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️❌
TrendingPapers	✔️	✔️	❌	❌	✔️	❌	❌	❌	❌	❌	✔️	❌	❌	❌	✔️	❌	✔️	✔️
Bytez	✔️	❌	❌	❌	✔️	❌	❌	✔️	✔️	❌	✔️	✔️	❌	❌	✔️	✔️	❌	✔️❌
Notesum.ai	✔️	✔️	✔️	❌	❌	❌	❌	❌	❌	❌	✔️	❌	❌	❌	✔️	❌	✔️	✔️❌
Research Rabbit	✔️	❌	✔️	❌	❌	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️

Search Engines

Platform	Search	Reco-mmen-dations	Collec-tions	Citation Analysis	Trending Analysis	Author Profiles	Visual-ization Tools	Paper Chat	Idea Gener-ation	Paper Writing	Summa-rization	Paper Review	Data-sets	Code Reposi-tories	LLM Inte-gration	Web API	Personal-ization	Free
Google Sholar	✔️	✔️	✔️	✔️	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	✔️
Semantic Sholar	✔️	✔️	✔️	✔️	✔️	✔️	❌	✔️	❌	❌	✔️	❌	❌	❌	✔️	✔️	✔️	✔️
Baidu Sholar	✔️	✔️	✔️	✔️	✔️	✔️	❌	❌	❌	❌	❌	❌	❌	❌	✔️	❌	✔️	✔️❌
BASE	✔️	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	❌	✔️
Internet Archive Sholar	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	❌	✔️
Scilit	✔️	❌	✔️	✔️	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️
The Lens	✔️	❌	✔️	❌	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	❌	✔️❌
Science.gov	✔️	❌	❌	❌	❌	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️
Academia.eu	✔️	❌	✔️	❌	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️❌
OpenAlex	✔️	❌	❌	❌	❌	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	❌	✔️❌
AceMap	✔️	❌	❌	✔️	✔️	✔️	✔️	❌	❌	❌	❌	✔️	❌	❌	❌	❌	❌	✔️
PubTator3	✔️	❌	✔️	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	❌	✔️

Benchmarks

Platform	Search	Reco-mmen-dations	Collec-tions	Citation Analysis	Trending Analysis	Author Profiles	Visual-ization Tools	Paper Chat	Idea Gener-ation	Paper Writing	Summa-rization	Paper Review	Data-sets	Code Reposi-tories	LLM Inte-gration	Web API	Personal-ization	Free
Papers with Code	✔️	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	✔️	❌	❌	❌	✔️
ScienceAgentBench	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✔️	❌	✔️	✔️	✔️	❌	❌	✔️
ORKG Benchmarks	❌	❌	❌	❌	✔️	❌	✔️	❌	❌	❌	❌	❌	✔️	❌	❌	❌	❌	✔️
Huggingface	✔️	❌	✔️	❌	✔️	❌	❌	❌	❌	❌	❌	❌	✔️	✔️	❌	❌	❌	✔️❌

💡 AI-Driven Scientific Discovery: Ideation, Hypothesis Generation, and Experimentation

Idea Generation

• The IDEA Challenge 2022 dataset [Dataset]
• SPACE-IDEAS: A Dataset for Salient Information Detection in Space Innovation [Paper]
• Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas [Paper]
• Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents [Paper]
• Scideator: Human-LLM Scientific Idea Generation Grounded in Research-Paper Facet Recombination [Paper]
• Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System [Paper]

Hypothesis Generation

• Large Language Models are Zero Shot Hypothesis Proposers [Paper]
• Hypothesis Generation with Large Language Models [Paper]
• Exploring Scientific Hypothesis Generation with Mamba [Paper]
• Large Language Models for Automated Open-domain Scientific Hypotheses Discovery [Paper]
• Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation [Paper]
• Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models [Paper]
• Towards an AI co-scientist [Paper]
• MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses [Paper]
• Literature Meets Data: A Synergistic Approach to Hypothesis Generation [Paper]

Automated Experimentation

• AutoML-GPT: Large Language Model for AutoML [Paper]
• MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation [Paper]
• SWE-bench: Can Language Models Resolve Real-world Github Issues? [Paper]
• MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks [Paper]
• Automatic benchmarking of large multimodal models via iterative experiment programming [Paper]
• Agent-as-a-Judge: Evaluate Agents with Agents [Paper]
• ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery [Paper]
• AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML [Paper]
• Tree Search for Language Model Agents [Paper]
• SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning [Paper]
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents [Paper]
• AI agents in chemical research: GVIM - an intelligent research assistant system [Paper]
• SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? [Paper]
• AIDE: AI-Driven Exploration in the Space of Code [Paper]
• MLGym: A New Framework and Benchmark for Advancing AI Research Agents [Paper]
• DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration [Paper]

📝 Text-based Content Generation

Title

• PaperRobot: Incremental Draft Generation of Scientific Ideas [Paper]
• Automatic Title Generation for Text with Pre-trained Transformer Language Model [Paper]
• Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End [Paper]

Abstract

• PaperRobot: Incremental Draft Generation of Scientific Ideas [Paper]
• Comparing scientific abstracts generated by ChatGPT to real abstracts with detectors and blinded human reviewers [Paper]
• How trustworthy is ChatGPT? The case of bibliometric analyses [Paper]
• Can ChatGPT assist authors with abstract writing in medical journals? Evaluating the quality of scientific abstracts generated by ChatGPT and original abstracts [Paper]

Related Work

• Towards Automated Related Work Summarization [Paper]
• Neural Related Work Summarization with a Joint Context-driven Attention Mechanism [Paper]
• ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks [Paper]
• PaperRobot: Incremental Draft Generation of Scientific Ideas [Paper]
• Automatic related work section generation: experiments in scientific document abstracting [Paper]
• Automatic Generation of Related Work Sections in Scientific Papers: An Optimization Approach [Paper]
• CORWA: A Citation-Oriented Related Work Annotation Dataset [Paper]
• Automatic generation of related work through summarizing citations [Paper]
• CiteBench: A Benchmark for Scientific Citation Text Generation [Paper]
• ToC-RWG: Explore the Combination of Topic Model and Citation Information for Automatic Related Work Generation [Paper]

Citation

• Fabrication and errors in the bibliographic citations generated by ChatGPT [Paper]
• Cited Text Spans for Scientific Citation Text Generation [Paper]
• Systematic Task Exploration with LLMs: A Study in Citation Text Generation [Paper]
• Citation: A Key to Building Responsible and Accountable Large Language Models [Paper]
• Citation-Enhanced Generation for LLM-based Chatbots [Paper]
• Related Work and Citation Text Generation: A Survey [Paper]

Long Text

• LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs [Paper]
• LongReward: Improving Long-context Large Language Models with AI Feedback [Paper]
• LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm [Paper]

Proof-Reading and Paraphrasing

• Can artificial intelligence help for scientific writing? [Paper]
• Good Practices for Scientific Article Writing with ChatGPT and Other Artificial Intelligence Language Models [Paper]
• The role of ChatGPT in scientific communication: writing better scientific review articles [Paper]
• Using ChatGPT for language editing in scientifc articles [Paper]
• The Ability of ChatGPT in Paraphrasing Texts and Reducing Plagiarism: A Descriptive Analysis [Paper]

Press Release

• Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen [Paper]
• Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature [Paper]
• ‘Don’t Get Too Technical with Me’: A Discourse Structure-Based Framework for Automatic Science Journalism [Paper]

🎨 Multimodal Content Generation and Understanding

Scientific Figure Understanding

• A Diagram is Worth a Dozen Images [Paper]
• A simple neural network module for relational reasoning [Paper]
• FigureQA: An Annotated Figure Dataset for Visual Reasoning [Paper]
• ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning [Paper]
• ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries [Paper]
• Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models [Paper]
• SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval [Paper]
• SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers [Paper]
• CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs [Paper]
• ChartAdapter: Large Vision-Language Model for Chart Summarization [Paper]

Scientific Figure Generation

• Data2Vis: Automatic Generation of Data Visualizations Using Sequence-to-Sequence Recurrent Neural Networks [Paper]
• ADVISor: Automatic Visualization Answer for Natural-Language Question on Tabular Data [Paper]
• Sevi: Speech-to-Visualization through Neural Machine Translation [Paper]
• Chat2VIS: Generating Data Visualizations via Natural Language Using ChatGPT, Codex and GPT-3 Large Language Models [Paper]
• AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ [Paper]
• SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement [Paper]
• Plots Made Quickly: An Efficient Approach for Generating Visualizations from Natural Language Queries [Paper]
• DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning [Paper]
• DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ [Paper]
• ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation [Paper]
• ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation? [Paper]

Scientific Table Understanding

• ToTTo: A Controlled Table-To-Text Generation Dataset [Paper]
• SciGen: a Dataset for Reasoning-Aware Text Generation from Scientific Tables [Paper]
• Towards Table-to-Text Generation with Numerical Reasoning [Paper]
• SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation [Paper]
• Structure-Aware Pre-Training for Table-to-Text Generation [Paper]
• Table-To-Text generation and pre-training with TabT5 [Paper]
• Few-shot Table-to-text Generation with Prefix-Controlled Generator [Paper]
• Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning [Paper]
• SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text Generation [Paper]
• LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control [Paper]
• Arithmetic-Based Pretraining Improving Numeracy of Pretrained Language Models [Paper]
• Structure-aware Table-to-Text Generation with Prefix-tuning [Paper]
• Table-to-Text Using Pre-trained Large Language Model and LoRA [Paper]
• Unifying Structured Data as Graph for Data-to-Text Pre-Training [Paper]
• Integrating Table Representations into Large Language Models for Improved Scholarly Document Comprehension [Paper]

Scientific Table Generation

• gTBLS: Generating Tables from Text by Conditional Question Answering [Paper]
• ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models [Paper]
• OpenTE: Open-Structure Table Extraction From Text [Paper]
• Is This a Bad Table? A Closer Look at the Evaluation of Table Generation from Text [Paper]
• LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement [Paper]

Scientific Slides and Poster Generation

• SlidesGen: Automatic Generation of Presentation Slides for a Technical Paper Using Summarization [Paper]
• PPSGen: learning to generate presentation slides for academic papers [Paper]
• Learning to Generate Posters of Scientific Papers [Paper]
• Phrase-Based Presentation Slides Generation for Academic Papers [Paper]
• D2S: Document-to-Slide Generation Via Query-Based Text Summarization [Paper]
• Towards Topic-Aware Slide Generation For Academic Papers With Unsupervised Mutual Learning [Paper]
• DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents [Paper]
• PosterBot: A System for Generating Posters of Scientific Papers with Neural Models [Paper]
• Presentations by the Humans and For the Humans: Harnessing LLMs for Generating Persona-Aware Slides from Documents [Paper]
• Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach [Paper]
• Presentations are not always linear! GNN meets LLM for Text Document-to-Presentation Transformation with Attribution [Paper]

✅ Peer Review

Analysis of Peer Reviews

• Argument Mining for Understanding Peer Reviews [Paper]
• Aspect-based Sentiment Analysis of Scientific Reviews [Paper]
• APE: Argument Pair Extraction from Peer Review and Rebuttal via Multi-task Learning [Paper]
• Argument Mining Driven Analysis of Peer-Reviews [Paper]
• HedgePeer: A Dataset for Uncertainty Detection in Peer Reviews [Paper]
• PolitePEER: does peer review hurt? A dataset to gauge politeness intensity in the peer reviews [Paper]
• Automatic Analysis of Substantiation in Scientific Peer Reviews [Paper]
• Exploring Jiu-Jitsu Argumentation for Writing Peer Review Rebuttals [Paper]

Paper Feedback and Automatic Reviewing

• DeepSentiPeer: Harnessing Sentiment in Review Texts to Recommend Peer Review Decisions [Paper]
• Exploring the Potential of GPT-2 for Generating Fake Reviews of Research Papers [Paper]
• Multi-task Peer-Review Score Prediction [Paper]
• ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis [Paper]
• PEERAssist: Leveraging on Paper-Review Interactions to Predict Peer Review Decisions [Paper]
• Can We Automate Scientific Reviewing? [Paper]
• ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing [Paper]
• GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study [Paper]
• Can large language models provide useful feedback on research papers? A large-scale empirical analysis [Paper]
• MARG: Multi-Agent Review Generation for Scientific Papers [Paper]

Scientific Rigour

• Online software spots genetic errors in cancer papers [Paper]
• SciScore [Tool]
• Assessing Scientific Research Papers with Knowledge Graphs [Paper]
• On the Rigour of Scientific Writing: Criteria, Analysis, and Insights [Paper]

Scientific Claim Verification

• SciFact-Open: Towards open-domain scientific claim verification [Paper]
• Scientific Fact-Checking: A Survey of Resources and Approaches [Paper]
• The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who [Paper]
• Missci: Reconstructing Fallacies in Misrepresented Science [Paper]
• Overview of the Context24 Shared Task on Contextualizing Scientific Claims [Paper]
• How We Refute Claims: Automatic Fact-Checking through Flaw Identification and Explanation [Paper]
• Claim Verification in the Age of Large Language Models: A Survey [Paper]
• Grounding Fallacies Misrepresenting Scientific Publications in Evidence [Paper]

Meta Review Generation

• Uncertainty-aware machine support for paper reviewing on the interspeech 2019 submission corpus [Paper]
• A Deep Neural Architecture for Decision-Aware Meta-Review Generation [Paper]
• Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation [Paper]
• Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation [Paper]
• LLMs as Meta-Reviewers' Assistants: A Case Study [Paper]

🚀 End-to-End

• Scientific discovery in the age of artificial intelligence [Paper]
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery [Paper]

Citation

@article{eger2025transforming,
  title={Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation},
  author={Eger, Steffen and Cao, Yong and D'Souza, Jennifer and Geiger, Andreas and Greisinger, Christian and Gross, Stephanie and Hou, Yufang and Krenn, Brigitte and Lauscher, Anne and Li, Yizhi and others},
  journal={arXiv preprint arXiv:2502.05151},
  year={2025}
}