Scholarlink

Large language Models (LLMs) often encounter hallucination issues in knowledge-intensive tasks like question answering (QA). Existing methods attempt to mitigate this by retrieving relevant external knowledge to guide the LLM’s reasoning process. However, knowledge retrieved by semantic similarity-based knowledge retriever is often fragmented and unable to provide structured and coherent reasoning clues that align with the question’s semantic structure. Furthermore, for complex, multi-hop questions involving multiple-topic entities, knowledge retriever frequently introduce irrelevant information or overlook critical knowledge, leading to lower retrieval accuracy for the golden answer and ultimately misguiding the reasoning of LLMs. To address these challenges, we propose a novel model, CoT-F, which introduces responsible, explicit, knowledge-based Chain-of-Thought Families to enhance LLM reasoning. CoT-F identifies high-confidence candidate answers by starting from each topic entity and systematically organizing intermediary triples into structured reasoning paths. Extensive experiments demonstrate that our model significantly improves the reasoning capabilities of LLMs in knowledge-intensive tasks, particularly for complex questions, without requiring additional fine-tuning of the LLM.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CoT-F: Leveraging Chain-of-Thought Families in Large Language Models for Complex Question Answering

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Feng Zhao,
  • Xianggan Liu,
  • Long Wang,
  • Ruilin Zhao,
  • Yu Yang,
  • Guandong Xu

摘要

Large language Models (LLMs) often encounter hallucination issues in knowledge-intensive tasks like question answering (QA). Existing methods attempt to mitigate this by retrieving relevant external knowledge to guide the LLM’s reasoning process. However, knowledge retrieved by semantic similarity-based knowledge retriever is often fragmented and unable to provide structured and coherent reasoning clues that align with the question’s semantic structure. Furthermore, for complex, multi-hop questions involving multiple-topic entities, knowledge retriever frequently introduce irrelevant information or overlook critical knowledge, leading to lower retrieval accuracy for the golden answer and ultimately misguiding the reasoning of LLMs. To address these challenges, we propose a novel model, CoT-F, which introduces responsible, explicit, knowledge-based Chain-of-Thought Families to enhance LLM reasoning. CoT-F identifies high-confidence candidate answers by starting from each topic entity and systematically organizing intermediary triples into structured reasoning paths. Extensive experiments demonstrate that our model significantly improves the reasoning capabilities of LLMs in knowledge-intensive tasks, particularly for complex questions, without requiring additional fine-tuning of the LLM.