对齐抽取与生成以实现鲁棒的检索增强生成
Aligning Extraction and Generation for Robust Retrieval-Augmented Generation
AI总结：
针对检索增强生成（RAG）易受检索噪声影响导致幻觉的问题，提出Ext2Gen先抽取再生成框架，通过联合证据选择与生成、偏好对齐优化提升鲁棒性，无需独立压缩模块，性能优于现有方法且能结合检索改进技术。
摘要：
检索增强生成（RAG）利用外部知识增强大语言模型（LLMs），但生成过程仍易受检索诱导噪声和相关片段不确定位置的影响，常导致幻觉问题。我们提出Ext2Gen，一个先抽取再生成的框架，通过联合证据选择和答案生成来强化LLMs，动态识别与查询相关的内容同时抑制噪声，从而无需任何独立的生成前压缩模块。通过精心构建的成对反馈进行偏好对齐优化后，即使在噪声或不精确检索条件下，Ext2Gen也能生成准确且忠实的答案。实验表明，它显著增强了生成主干的鲁棒性，且比依赖独立压缩模型的方法（如Recomp、CompAct、EXIT）获得更大的性能提升。它还能从查询重写等改进的检索技术中获益，强调生成侧增强可解决仅靠检索无法克服的局限性。
英文摘要：
Retrieval-augmented generation (RAG) enhances LLMs with external knowledge, yet generation remains vulnerable to retrieval-induced noise and uncertain placement of relevant chunks, often causing hallucinations. We present Ext2Gen, an extract-then-generate framework that strengthens LLMs via joint evidence selection and answer generation, dynamically identifying query-relevant content while suppressing noise, thereby removing the need for any independent pre-generation compression module. Optimized through preference alignment with well-curated pairwise feedback, Ext2Gen produces accurate and faithful answers even under noisy or imprecise retrieval. Experiments demonstrate that it substantially enhances the robustness of the generation backbone and yields greater performance gains than methods relying on independent compression models, e.g., Recomp, CompAct, EXIT). It further benefits from improved retrieval techniques such as query rewriting, underscoring that generation-side enhancements address limitations that retrieval alone cannot overcome.
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。
