arXiv:2512.19240cs.CLcs.AI2025-12被引 1

让大模型精准推理化学反应,不训练也能达到顶尖水平。

ChemATP: A Training-Free Chemical Reasoning Framework for Large Language Models

  • 构建原子级文本知识库,动态检索化学先验知识
  • 在多个化学任务上超越无训练基线,媲美训练模型
  • 适合需要快速更新知识的化学推理场景

大语言模型虽具强大泛化推理能力,但在分子科学领域因标准字符串表示缺乏显式化学先验而表现不佳。现有方法面临根本性困境:基于训练的方法将先验注入参数,导致知识更新缓慢且损害通用推理能力;而现有无训练方法依赖表面提示,无法提供原子级别的精细先验。为此,我们提出ChemATP框架,首次实现化学知识与推理引擎的解耦。通过构建首个原子级文本知识库,使冻结的LLM能动态检索并显式推理该信息,既保持可解释性与可适应性,又保留模型内在通用智能。实验表明,ChemATP显著优于无训练基线,并媲美最先进的训练型模型,证明显式先验注入是隐式参数更新的有力替代方案。

原文摘要 · Abstract (English)

Large Language Models (LLMs) exhibit strong general reasoning but struggle in molecular science due to the lack of explicit chemical priors in standard string representations. Current solutions face a fundamental dilemma. Training-based methods inject priors into parameters, but this static coupling hinders rapid knowledge updates and often compromises the model's general reasoning capabilities. Conversely, existing training-free methods avoid these issues but rely on surface-level prompting, failing to provide the fine-grained atom-level priors essential for precise chemical reasoning. To address this issue, we introduce ChemATP, a framework that decouples chemical knowledge from the reasoning engine. By constructing the first atom-level textual knowledge base, ChemATP enables frozen LLMs to explicitly retrieve and reason over this information dynamically. This architecture ensures interpretability and adaptability while preserving the LLM's intrinsic general intelligence. Experiments show that ChemATP significantly outperforms training-free baselines and rivals state-of-the-art training-based models, demonstrating that explicit prior injection is a competitive alternative to implicit parameter updates.

化学推理大模型知识检索

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。