# Can ChatGPT be used to generate scientific hypotheses?

arXiv: https://arxiv.org/abs/2304.12208 · HTML: https://mlsanity.com/paper/2304.12208/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 58 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## Builds on (most cited first, 3 of 3)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level](https://mlsanity.com/paper/2112.15594/) (2021)
- [The Dawn of Quantum Natural Language Processing](https://mlsanity.com/paper/2110.06510/) (2021)

## Built on by (most cited first, 21 of 21)

- [Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions](https://mlsanity.com/paper/2406.05688/) (2024)
- [Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation](https://mlsanity.com/paper/2502.05151/) (2025)
- [Large Language Models for Scientific Synthesis, Inference and Explanation](https://mlsanity.com/paper/2310.07984/) (2023)
- [Probing the Creativity of Large Language Models: Can models produce divergent semantic association?](https://mlsanity.com/paper/2310.11158/) (2023)
- [AI for social science and social science of AI: A Survey](https://mlsanity.com/paper/2401.11839/) (2024)
- [When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research](https://mlsanity.com/paper/2505.11855/) (2025)
- [Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review](https://mlsanity.com/paper/2401.01519/) (2024)
- [SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models](https://mlsanity.com/paper/2503.13503/) (2025)
- [Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models](https://mlsanity.com/paper/2505.14599/) (2025)
- [MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design](https://mlsanity.com/paper/2412.16270/) (2024)
- [GPT vs Human for Scientific Reviews: A Dual Source Review on Applications of ChatGPT in Science](https://mlsanity.com/paper/2312.03769/) (2023)
- [CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback](https://mlsanity.com/paper/2411.09073/) (2024)
- [Toward Full Autonomous Laboratory Instrumentation Control with Large Language Models](https://mlsanity.com/paper/2604.03286/) (2026)
- [1.5 million materials narratives generated by chatbots](https://mlsanity.com/paper/2308.13687/) (2023)
- [EvidenceBench: A Benchmark for Extracting Evidence from Biomedical Papers](https://mlsanity.com/paper/2504.18736/) (2025)
- [Speculative Exploration on the Concept of Artificial Agents Conducting Autonomous Research](https://mlsanity.com/paper/2312.03497/) (2023)
- [Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices](https://mlsanity.com/paper/2501.00224/) (2024)
- [Epitome: Pioneering an Experimental Platform for AI-Social Science Integration](https://mlsanity.com/paper/2507.01061/) (2025)
- [Zero-shot reasoning for simulating scholarly peer-review](https://mlsanity.com/paper/2510.02027/) (2025)
- [Biomedical Hypothesis Explainability with Graph-Based Context Retrieval](https://mlsanity.com/paper/2511.05498/) (2025)
- [Designing Computational Tools for Exploring Causal Relationships in Qualitative Data](https://mlsanity.com/paper/2602.06506/) (2026)

## Abstract (arXiv)

We investigate whether large language models can perform the creative hypothesis generation that human researchers regularly do. While the error rate is high, generative AI seems to be able to effectively structure vast amounts of scientific knowledge and provide interesting and testable hypotheses. The future scientific enterprise may include synergistic efforts with a swarm of "hypothesis machines", challenged by automated experimentation and adversarial peer reviews.