通过排序思维链提升检索增强生成的知识提炼效果
RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts
- 用排序思维链筛选相关文档，引导模型生成更精准的推理摘要
- 训练时让模型直接复现最优思维链，显著减少无关信息干扰
- 支持自反思机制，适合需要高精度知识推理的应用场景
检索增强生成（RAG）通过引入外部知识提升大语言模型（LLM）性能，但模型在利用检索文档时仍易受无关或噪声信息误导。为此，我们提出RankCoT，一种基于查询与全部检索文档的排序思维链（RankCoT）知识精炼方法。训练阶段，模型根据查询和每篇文档生成多个思维链候选；随后微调模型直接复现由所有检索文档综合判断出的最佳思维链，促使模型在生成思维链摘要时主动过滤无关文档。此外，RankCoT引入自反思机制进一步优化思维链输出，生成更高质量训练数据。实验表明，RankCoT在多项指标上优于现有知识精炼模型，能生成更短但更有效的提炼结果，从而提升答案准确性。代码与数据已公开于https://github.com/NEUIR/RankCoT。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) enhances the performance of Large Language Models (LLMs) by incorporating external knowledge. However, LLMs still encounter challenges in effectively utilizing the knowledge from retrieved documents, often being misled by irrelevant or noisy information. To address this issue, we introduce RankCoT, a knowledge refinement method that incorporates reranking signals in generating CoT-based summarization for knowledge refinement based on given query and all retrieval documents. During training, RankCoT prompts the LLM to generate Chain-of-Thought (CoT) candidates based on the query and individual documents. It then fine-tunes the LLM to directly reproduce the best CoT from these candidate outputs based on all retrieved documents, which requires LLM to filter out irrelevant documents during generating CoT-style summarization. Additionally, RankCoT incorporates a self-reflection mechanism that further refines the CoT outputs, resulting in higher-quality training data. Our experiments demonstrate the effectiveness of RankCoT, showing its superior performance over other knowledge refinement models. Further analysis reveals that RankCoT can provide shorter but effective refinement results, enabling the generator to produce more accurate answers. All code and data are available at https://github.com/NEUIR/RankCoT.
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。