警惕大模型虚构机制，科学发现需优先识别真实结构
Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery
- 提出机制学习应聚焦数据支撑下的真实结构，而非依赖复杂模型生成流畅假说
- 指出在高维数据中，多种不相容机制可能产生相同观测结果，导致解释不可靠
- 强调大模型易将多类解释合并为单一叙事，误导科学发现，适合科研人员警惕
现代机器学习与人工智能模型，尤其是大型语言模型（LLMs），越来越多地被用于从观测数据中生成科学假设和机制解释。本文认为，在现代机器学习擅长的高维代理域中，机制学习本质上是欠定的：许多不相容的机制可能在数据支持范围内产生几乎相同的观测关系，因此预测成功与解释连贯性不足以证明机制发现。这种欠定性在大型语言模型中尤为危险，它们倾向于将大量解释等价类压缩成单一流畅叙述。本文提出‘机制化机器学习’的具体标准，并主张这些规范是确保以大模型为中心的工作流真正支持科学而非仅模拟科学所必需的。
原文摘要 · Abstract (English)
Modern Machine Learning (ML) and Artificial Intelligence (AI) models, especially large language models (LLMs), are increasingly used to generate scientific hypotheses and mechanistic explanations from observational data. This position paper argues that in the high-dimensional proxy regimes where modern ML excels, mechanistic learning is generically underdetermined: many incompatible mechanisms induce essentially the same observational relationships on the support of the data, so predictive success and coherent explanations are insufficient evidence of mechanism discovery. This underdetermination becomes uniquely hazardous with large language models (LLMs), which tend to collapse large equivalence classes of explanations into a single fluent narrative. This paper proposes concrete standards for ``mechanistic ML,'' and argues these norms are necessary if LLM-centered workflows are to support science rather than merely simulate it.
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。