arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.07076cs.CLcs.AIcs.LG
收藏

MOOSE-Chem:用于重新发现未见化学科学假设的大型语言模型

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

Nanyang Technological University(南洋理工大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Science and Technology of China(中国科学技术大学);Wuhan University(武汉大学);University of New South Wales(新南威尔士大学);GreenDynamics;Singapore University of Technology and Design(新加坡科技设计大学)

Zonglin Yang, Wanhao Liu, Ben Gao, Tong Xie, Yuqiang Li, Wanli Ouyang, Soujanya Poria, Erik Cambria, Dongzhan Zhou

AI总结:

本研究提出MOOSE-Chem框架,通过将化学假设发现分解为检索灵感、组合假设和排序三个子任务,使LLM能仅凭研究背景重新发现高相似度的新假设,并暗示LLM可能编码了未被人类识别的科学知识关联。

摘要:

科学发现在推动人类社会进步中发挥着关键作用,而大型语言模型(LLM)的最新进展表明其具有加速这一过程的潜力。然而,目前尚不清楚LLM能否自主生成化学领域新颖且有效的假设。在本工作中,我们研究了在仅给定研究背景(包括问题和/或综述)且不限制问题领域的情况下,LLM能否发现高质量的化学假设。我们首先观察到,假设发现看似是一个难以处理的任务。为解决这一问题,我们基于一个基本假设提出了正式的数学分解:大多数化学假设可以由研究背景和一组灵感组合而成。该分解引出三个实际子任务——检索灵感、用灵感组合假设以及排序假设——这些子任务共同构成了整个科学发现任务的充分子任务集。我们进一步开发了一个代理式LLM框架MOOSE-Chem,它是该数学分解的直接实现。为评估该框架,我们构建了一个包含51篇于2024年1月之后发表或在线的高影响力化学论文的基准,每篇论文均由化学博士手动标注了背景、灵感和假设。该框架能够重新发现许多与真实结果高度相似的假设,成功捕捉核心创新,同时由于使用知识截止日期早于2024年的LLM,确保了无数据污染。最后,基于LLM在灵感检索(一项本质上具有分布外性质的任务)上令人惊讶的高准确性,我们提出了一个大胆的假设:LLM可能已经编码了人类尚未认识到的潜在科学知识关联。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑