arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.16282cs.CLcs.AI
收藏

大规模生成文献驱动的科学理论

Generating Literature-Driven Scientific Theories at Scale

Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Arizona(亚利桑那大学);University of Washington(华盛顿大学)

Peter Jansen, Peter Clark, Doug Downey, Daniel S. Weld

AI总结:

研究通过大规模文献数据生成科学理论,比较文献基础与参数知识生成对理论质量和预测能力的影响。

摘要:

当代自动科学发现主要聚焦于生成科学实验的代理,而从事更高层次科学活动如理论构建的系统仍被忽视。本文提出从大规模科学文献中合成包含定性和定量定律的理论问题。我们研究大规模理论生成,利用13.7k源论文合成2.9k理论,考察文献基础与参数知识、准确性导向与创新性导向生成目标对理论属性的影响。实验表明,与使用参数化LLM内存生成相比,我们的文献支持方法生成的理论在匹配现有证据和预测后续论文结果方面显著更好。

英文摘要:

Contemporary automated scientific discovery has focused on agents for generating scientific experiments, while systems that perform higher-level scientific activities such as theory building remain underexplored. In this work, we formulate the problem of synthesizing theories consisting of qualitative and quantitative laws from large corpora of scientific literature. We study theory generation at scale, using 13.7k source papers to synthesize 2.9k theories, examining how generation using literature-grounding versus parametric knowledge, and accuracy-focused versus novelty-focused generation objectives change theory properties. Our experiments show that, compared to using parametric LLM memory for generation, our literature-supported method creates theories that are significantly better at both matching existing evidence and at predicting future results from 4.6k subsequently-written papers

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。

↑