用概率模型模拟人对常识的差异，提升大模型推理准确性
Abductive Reasoning with Probabilistic Commonsense
- 通过采样个体常识信念，构建概率化推理框架
- 在多个基准上超越链式思考和传统神经符号方法
- 适合需要考虑人类认知多样性的场景
近期提升大语言模型推理能力的研究多采用神经符号框架集成形式逻辑求解器。核心挑战在于形式求解器缺乏常识世界知识，难以做出人类认为理所当然的推理步骤。已有方法利用大模型补全缺失的常识假设，但隐含了对常识事实存在普遍共识的假设。事实上，常识信念因人而异。本文提出一种概率化归因常识推理框架，显式建模这种个体差异，旨在判断多数人是否会认为某陈述为真。我们引入概率归因常识（PACS）算法，利用大模型与形式求解器采样个体不同的常识信念作为观察，聚合这些样本以得出结论。实证表明，PACS在多个基准上优于链式思考、先前神经符号方法及基于搜索的策略。
原文摘要 · Abstract (English)
Recent efforts to improve the reasoning abilities of Large Language Models (LLMs) have focused on integrating formal logic solvers within neurosymbolic frameworks. A key challenge is that formal solvers lack commonsense world knowledge, preventing them from making reasoning steps that humans find obvious. Prior methods address this by using LLMs to supply missing commonsense assumptions, but these approaches implicitly assume universal agreement on such commonsense facts. In reality, commonsense beliefs vary across individuals. We propose a probabilistic framework for abductive commonsense reasoning that explicitly models this variation, aiming to determine whether most people would judge a statement as true or false. We introduce Probabilistic Abductive CommonSense (PACS), a novel algorithm that uses an LLM and a formal solver to sample proofs as observations of individuals' distinct commonsense beliefs, and aggregates conclusions across these samples. Empirically, PACS outperforms chain-of-thought reasoning, prior neurosymbolic methods, and search-based approaches across multiple benchmarks.
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。