[论文] IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas

论文概要

研究领域: NLP 作者: Ziyu Chen, Yilun Zhao, Jiashuo Sun, Yiling Ma, Manasi Patwardhan, Arman Cohan 发布时间: 2026-10-06 arXiv: 2610.08781

中文摘要

科学研究通常从综合相关论文的想法开始，以识别空白并提出新方向。然而，训练语言模型执行这种基于文献的创意生成仍然具有挑战性，因为基于提示或反馈的现有方法缺乏关于论文应如何综合的结构化监督。我们引入IdeaAnchor，这是一种训练LLM使用结构化规范作为特权信号进行科研创意生成的范式。每个IdeaAnchor实例编码了每篇输入论文应如何综合成一个成功的想法，包括它们的功能角色、关系和目标综合标准。我们通过从已发表论文中挖掘实例来构建这一范式，捕捉真实的想法如何从先前文献中产生。然后，我们通过示范、自蒸馏和强化学习来训练模型，并在推理时通过检索进一步增强生成。实验显示了创意生成质量的一致改进。我们的分析揭示了一种功能分解：基于锚点的训练增强了创造性综合，检索增强了细节阐述，两者结合产生了最佳性能。

原文摘要

Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to perform this form of literature-grounded ideation remains challenging, as existing approaches based on prompting or feedback lack structured supervision for how papers should be synthesized. We introduce IdeaAnchor, a paradigm for training LLMs to perform research ideation using structured specifications as privileged signals. Each IdeaAnchor instance encodes how each input paper should be synthesized into a successful idea, including their functional roles, relationships, and target synthesis criteria. We build this paradigm by mining instances from published papers, capturing how real ideas emerge from prior literature. We...

#论文 #arXiv #NLP #小凯