MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

• URL: http://arxiv.org/abs/2410.07076v5
• Date: Sun, 18 May 2025 13:23:30 GMT
• Title: MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses
• Authors: Zonglin Yang, Wanhao Liu, Ben Gao, Tong Xie, Yuqiang Li, Wanli Ouyang, Soujanya Poria, Erik Cambria, Dongzhan Zhou,
• Abstract summary: It remains unclear whether large language models (LLMs) can autonomously generate novel and valid hypotheses in chemistry.<n>We develop a benchmark of 51 high-impact chemistry papers published and online after January 2024, each manually annotated by PhD chemists with background, inspirations, and hypothesis.<n>We assume that LLMs may already encode latent scientific knowledge associations not yet recognized by humans.
• Score: 72.39144388083712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific discovery plays a pivotal role in advancing human society, and recent progress in large language models (LLMs) suggests their potential to accelerate this process. However, it remains unclear whether LLMs can autonomously generate novel and valid hypotheses in chemistry. In this work, we investigate whether LLMs can discover high-quality chemistry hypotheses given only a research background-comprising a question and/or a survey-without restriction on the domain of the question. We begin with the observation that hypothesis discovery is a seemingly intractable task. To address this, we propose a formal mathematical decomposition grounded in a fundamental assumption: that most chemistry hypotheses can be composed from a research background and a set of inspirations. This decomposition leads to three practical subtasks-retrieving inspirations, composing hypotheses with inspirations, and ranking hypotheses - which together constitute a sufficient set of subtasks for the overall scientific discovery task. We further develop an agentic LLM framework, MOOSE-Chem, that is a direct implementation of this mathematical decomposition. To evaluate this framework, we construct a benchmark of 51 high-impact chemistry papers published and online after January 2024, each manually annotated by PhD chemists with background, inspirations, and hypothesis. The framework is able to rediscover many hypotheses with high similarity to the groundtruth, successfully capturing the core innovations-while ensuring no data contamination since it uses an LLM with knowledge cutoff date prior to 2024. Finally, based on LLM's surprisingly high accuracy on inspiration retrieval, a task with inherently out-of-distribution nature, we propose a bold assumption: that LLMs may already encode latent scientific knowledge associations not yet recognized by humans.

Related papers

• MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search [93.64235254640967]
  Large language models (LLMs) have shown promise in automating scientific hypothesis generation.<n>We define the novel task of fine-grained scientific hypothesis discovery.<n>We propose a hierarchical search method that incrementally proposes and integrates details into the hypothesis.
  arXiv  Detail & Related papers  (2025-05-25T16:13:46Z)
• Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models [18.850296587858946]
  We introduce TruthHypo, a benchmark for assessing the capabilities of large language models in generating truthful hypotheses.<n>KnowHD is a knowledge-based hallucination detector to evaluate how well hypotheses are grounded in existing knowledge.
  arXiv  Detail & Related papers  (2025-05-20T16:49:40Z)
• ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition [67.26124739345332]
  Large language models (LLMs) have demonstrated potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined. We introduce the first large-scale benchmark for evaluating LLMs with a near-sufficient set of sub-tasks of scientific discovery. We develop an automated framework that extracts critical components - research questions, background surveys, inspirations, and hypotheses - from scientific papers.
  arXiv  Detail & Related papers  (2025-03-27T08:09:15Z)
• LLM4SR: A Survey on Large Language Models for Scientific Research [15.533076347375207]
  Large Language Models (LLMs) offer unprecedented support across various stages of the research cycle. This paper presents the first systematic survey dedicated to exploring how LLMs are revolutionizing the scientific research process.
  arXiv  Detail & Related papers  (2025-01-08T06:44:02Z)
• From Generalist to Specialist: A Survey of Large Language Models for Chemistry [14.317448405387195]
  Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP) The predominant pretraining of LLMs on extensive web-based texts remains insufficient for advanced scientific discovery, particularly in chemistry. Although several studies have reviewed Pretrained Language Models (PLMs) in chemistry, there is a conspicuous absence of a systematic survey specifically focused on chemistry-oriented LLMs.
  arXiv  Detail & Related papers  (2024-12-28T03:40:25Z)
• Simulating Tabular Datasets through LLMs to Rapidly Explore Hypotheses about Real-World Entities [9.235910374587734]
  This paper explores the potential to quickly prototype hypotheses through applying LLMs to estimate properties of concrete entities. The hope is to allow sifting through hypotheses more quickly through collaboration between human and machine.
  arXiv  Detail & Related papers  (2024-11-27T05:48:44Z)
• Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models [20.648157071328807]
  Large language models (LLMs) can identify novel research directions by analyzing existing knowledge. LLMs are prone to generating hallucinations'', outputs that are plausible-sounding but factually incorrect. We propose KG-CoI, a system that enhances LLM hypothesis generation by integrating external, structured knowledge from knowledge graphs.
  arXiv  Detail & Related papers  (2024-11-04T18:50:00Z)
• ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models [62.37850540570268]
  Existing benchmarks in this domain fail to adequately meet the specific requirements of chemical research professionals. ChemEval identifies 4 crucial progressive levels in chemistry, assessing 12 dimensions of LLMs across 42 distinct chemical tasks. Results show that while general LLMs excel in literature understanding and instruction following, they fall short in tasks demanding advanced chemical knowledge.
  arXiv  Detail & Related papers  (2024-09-21T02:50:43Z)
• A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery [68.48094108571432]
  Large language models (LLMs) have revolutionized the way text and other modalities of data are handled. We aim to provide a more holistic view of the research landscape by unveiling cross-field and cross-modal connections between scientific LLMs.
  arXiv  Detail & Related papers  (2024-06-16T08:03:24Z)
• LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery [141.39722070734737]
  We propose to enhance the knowledge-driven, abstract reasoning abilities of Large Language Models with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework. We conduct experiments to demonstrate our framework's efficacy in law discovery and molecular design.
  arXiv  Detail & Related papers  (2024-05-16T03:04:10Z)
• Mapping the Increasing Use of LLMs in Scientific Papers [99.67983375899719]
  We conduct the first systematic, large-scale analysis across 950,965 papers published between January 2020 and February 2024 on the arXiv, bioRxiv, and Nature portfolio journals. Our findings reveal a steady increase in LLM usage, with the largest and fastest growth observed in Computer Science papers.
  arXiv  Detail & Related papers  (2024-04-01T17:45:15Z)
• A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules? [27.976789491185354]
  We study the question of whether large language models (LLMs) are actually useful to accelerate principled Bayesian optimization in the molecular space. Our experiments with real-world chemistry problems show that LLMs can be useful for BO over molecules, but only if they have been pretrained or finetuned with domain-specific data.
  arXiv  Detail & Related papers  (2024-02-07T16:32:58Z)
• Scientific Large Language Models: A Survey on Biological & Chemical Domains [47.97810890521825]
  Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension. The application of LLMs extends beyond conventional linguistic boundaries, encompassing specialized linguistic systems developed within various scientific disciplines. As a burgeoning area in the community of AI for Science, scientific LLMs warrant comprehensive exploration.
  arXiv  Detail & Related papers  (2024-01-26T05:33:34Z)
• Structured Chemistry Reasoning with Large Language Models [70.13959639460015]
  Large Language Models (LLMs) excel in diverse areas, yet struggle with complex scientific reasoning, especially in chemistry. We introduce StructChem, a simple yet effective prompting strategy that offers the desired guidance and substantially boosts the LLMs' chemical reasoning capability. Tests across four chemistry areas -- quantum chemistry, mechanics, physical chemistry, and kinetics -- StructChem substantially enhances GPT-4's performance, with up to 30% peak improvement.
  arXiv  Detail & Related papers  (2023-11-16T08:20:36Z)
• Large Language Models are Zero Shot Hypothesis Proposers [17.612235393984744]
  Large Language Models (LLMs) hold a wealth of global and interdisciplinary knowledge that promises to break down information barriers. We construct a dataset consist of background knowledge and hypothesis pairs from biomedical literature. We evaluate the hypothesis generation capabilities of various top-tier instructed models in zero-shot, few-shot, and fine-tuning settings.
  arXiv  Detail & Related papers  (2023-11-10T10:03:49Z)
• Large Language Models for Automated Open-domain Scientific Hypotheses Discovery [50.40483334131271]
  This work proposes the first dataset for social science academic hypotheses discovery. Unlike previous settings, the new dataset requires (1) using open-domain data (raw web corpus) as observations; and (2) proposing hypotheses even new to humanity. A multi- module framework is developed for the task, including three different feedback mechanisms to boost performance.
  arXiv  Detail & Related papers  (2023-09-06T05:19:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.