让大模型推理更可信，自动筛选有效思考链。
ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Model
- 用主题感知生成+因果对齐，优化思维链质量。
- 在多个基准上提升推理准确率，减少错误链占比。
- 适合需要高可信决策的AI应用，如医疗、金融。
在大规模人工智能时代，大语言模型（LLMs）在自然语言处理方面取得显著进展，但常缺乏透明性且输出不可靠，引发对其可解释性的担忧。为应对这一问题，思维链（CoT）提示方法将推理过程结构化为逐步推导。然而，并非所有推理链都有效，错误可能导致不可靠结论。我们提出ECCoT——一个端到端认知思维链验证框架，用于评估与优化LLM中的推理链。ECCoT结合马尔可夫随机场嵌入主题模型（MRF-ETM）实现主题驱动的思维链生成，以及因果句向量（CSBert）实现因果推理对齐。通过结构化排序统计过滤无效链条，ECCoT提升了可解释性，降低了偏见，增强了基于LLM决策的可信度。主要贡献包括：提出ECCoT框架、MRF-ETM用于主题引导的思维链生成、以及CSBert用于因果推理增强。代码已开源：https://github.com/erwinmsmith/ECCoT.git。
原文摘要 · Abstract (English)
In the era of large-scale artificial intelligence, Large Language Models (LLMs) have made significant strides in natural language processing. However, they often lack transparency and generate unreliable outputs, raising concerns about their interpretability. To address this, the Chain of Thought (CoT) prompting method structures reasoning into step-by-step deductions. Yet, not all reasoning chains are valid, and errors can lead to unreliable conclusions. We propose ECCoT, an End-to-End Cognitive Chain of Thought Validation Framework, to evaluate and refine reasoning chains in LLMs. ECCoT integrates the Markov Random Field-Embedded Topic Model (MRF-ETM) for topic-aware CoT generation and Causal Sentence-BERT (CSBert) for causal reasoning alignment. By filtering ineffective chains using structured ordering statistics, ECCoT improves interpretability, reduces biases, and enhances the trustworthiness of LLM-based decision-making. Key contributions include the introduction of ECCoT, MRF-ETM for topic-driven CoT generation, and CSBert for causal reasoning enhancement. Code is released at: https://github.com/erwinmsmith/ECCoT.git.
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。