mlsanityData to 7 Oct 2026

Can ChatGPT be used to generate scientific hypotheses?

arXiv 2304.12208 ↗First posted 30 Mar 2023cs.CLcited by 21

Not on the map. Why?

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.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 3 of its 58 references that are in the map. First posted on arXiv 30 Mar 2023.

Builds on

3 of 58 references.

References · 3

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
  3. 2021The Dawn of Quantum Natural Language Processingcited by 60

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 6; 2025: 8; 2026: 2.

21 papers.

Sort:

By area:

  1. 2024Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactionscited by 43
  2. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 41
  3. 2023Large Language Models for Scientific Synthesis, Inference and Explanationcited by 38
  4. 2023Probing the Creativity of Large Language Models: Can models produce divergent semantic association?cited by 31
  5. 2024AI for social science and social science of AI: A Surveycited by 29
  6. 2025When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Researchcited by 25
  7. 2024Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Reviewcited by 17
  8. 2025SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Modelscited by 15
  9. 2024MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Designcited by 8
  10. 2025Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Modelscited by 7
  11. 2023GPT vs Human for Scientific Reviews: A Dual Source Review on Applications of ChatGPT in Sciencecited by 5
  12. 2024CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedbackcited by 5
9 more
  1. 2026Toward Full Autonomous Laboratory Instrumentation Control with Large Language Modelscited by 5
  2. 20231.5 million materials narratives generated by chatbotscited by 3
  3. 2025EvidenceBench: A Benchmark for Extracting Evidence from Biomedical Paperscited by 2
  4. 2023Speculative Exploration on the Concept of Artificial Agents Conducting Autonomous Researchcited by 1
  5. 2024Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devicescited by 1
  6. 2025Epitome: Pioneering an Experimental Platform for AI-Social Science Integrationcited by 0
  7. 2025Zero-shot reasoning for simulating scholarly peer-reviewcited by 0
  8. 2025Biomedical Hypothesis Explainability with Graph-Based Context Retrievalcited by 0
  9. 2026Designing Computational Tools for Exploring Causal Relationships in Qualitative Datacited by 0