ECCoT：通过大型语言模型中的思维链增强有效认知的框架
ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Model
AI总结：
本文提出端到端认知思维链验证框架ECCoT，集成MRF-ETM生成主题感知CoT并用CSBert进行因果推理对齐，通过过滤无效推理链提升LLM的可解释性与可信度。
摘要：
在大规模人工智能时代，大型语言模型（LLMs）在自然语言处理方面取得了显著进展。然而，它们通常缺乏透明度并生成不可靠的输出，引发了对其可解释性的担忧。为此，思维链（CoT）提示方法将推理结构化为逐步演绎。然而，并非所有推理链都是有效的，错误可能导致不可靠的结论。我们提出了ECCoT，一个端到端认知思维链验证框架，以评估和改进LLMs中的推理链。ECCoT集成了马尔可夫随机场嵌入式主题模型（MRF-ETM）用于主题感知的CoT生成，以及因果句子BERT（CSBert）用于因果推理对齐。通过利用结构化排序统计过滤无效链，ECCoT提高了可解释性，减少了偏差，并增强了基于LLM的决策的可信度。主要贡献包括引入ECCoT、用于主题驱动CoT生成的MRF-ETM，以及用于因果推理增强的CSBert。代码发布于：https://github.com/erwinmsmith/ECCoT.git。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
