通过约束推理链提升大模型心智理论能力
Constrained Reasoning Chains for Enhancing Theory-of-Mind in Large Language Models
- 构建显式推理链，分步推导心智维度关系
- 在多个数据集上显著超越现有方法
- 适用于叙事与对话等多样化场景
大语言模型的心智理论（ToM）能力有限。现有大多数方法采用零样本提示，但在复杂推理任务中表现不佳，且难以处理非叙述性语境。本文提出一种零样本提示方法——受限心智推理链（CCoToM），利用领域知识和心智维度间的因果关系来改进这一问题。CCoToM首先引导模型推断相关心智维度（如信念），再基于已生成的维度及对应因果关系推断目标维度。此外，该方法自适应地施加提示约束，引入归纳偏置，增强各心智维度间的一致性。除了叙述性文本，CCoToM还可处理对话等非叙述性语境。大量实验表明，其在所有使用的模型和数据集上均显著优于当前最优方法。我们还进行了深入分析以揭示其内在机制。代码已公开。
原文摘要 · Abstract (English)
Theory-of-Mind (ToM) ability possessed by Large Language Models (LLMs) has been shown to be limited. Most existing methods for improving ToM in LLMs adopt zero-shot prompting, and they face challenges including poor performance in complex ToM reasoning tasks and an inability to handle non-narrative contexts. We propose a zero-shot prompting method named Constrained Chain-of-ToM (CCoToM) that leverages domain knowledge and the causal relations between ToM dimensions to address these limitations. Specifically, CCoToM guides LLMs to construct explicit reasoning chains by first prompting LLMs to infer related ToM dimensions (e.g., belief). Afterward, CCoToM prompts LLMs to infer the queried ToM dimension based on the generated related ToM dimensions and corresponding causal relations. Additionally, CCoToM adaptively imposes constraints on prompts to introduce inductive biases and improve consistency between ToM dimensions. Besides narratives, CCoToM can also handle non-narrative contexts like conversations. Extensive experiments show that CCoToM consistently outperforms previous state-of-the-art methods by large margins across all LLMs and datasets used. We also conduct in-depth analyses to gain deeper insights into CCoToM. We have made our code publicly available.
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。