无需基于分类的错误归类即可改进检索增强生成
Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization
AI总结：
本文提出RePAIR方法，通过直接将错误的RAG输出映射到错误缓解行动计划，无需依赖细粒度错误分类和显式批评者监督，从而提升检索增强生成的性能。
摘要：
检索增强生成（RAG）通过将生成过程 grounding 在外部知识来提高大语言模型（LLM）输出的事实准确性。最近的代理 RAG 系统扩展了这一范式，通过关键代理评估模型响应并迭代优化输出。然而，大多数先前工作隐式假设可靠的批评反馈，专注于规划策略，而对误差纠正过程本身的鲁棒性关注有限，这可能受到对齐错误类别和无效或错误纠正的影响。本文假设 RAG 性能可以在没有显式错误分类的情况下得到改进。我们提出 RePAIR，一种响应-行动学习范式，通过直接将错误的 RAG 输出映射到错误缓解行动计划，而无需依赖细粒度错误分类和显式批评者监督。在多个基准测试中，RePAIR 一致地提高了代理 RAG 的性能。
英文摘要：
Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language model (LLM) outputs by grounding generation in external knowledge. Recent agentic RAG systems extend this paradigm with critical agents to evaluate model responses and iteratively refine outputs. However, most prior work implicitly assumes reliable critic feedback and focuses on planning strategies, while paying limited attention to the robustness of the error-correction process itself, which can be impacted by misaligned error categories and ineffective or incorrect corrections. Here, we hypothesize that RAG performance can be improved without explicit error categorization. We propose RePAIR, a response-action learning paradigm that directly maps flawed RAG outputs to error-mitigating action plans without relying on fine-grained error taxonomies and explicit critic supervision. Across multiple benchmarks, RePAIR consistently improves agentic RAG performance.
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。
