SEER：用于检索增强生成的自对齐证据提取
SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation
AI总结：
针对检索增强生成中证据提取的泛化性差、语义缺失和长度偏斜问题，提出基于模型的自对齐证据提取学习框架SEER，将基础模型优化为证据提取器，大幅提升RAG性能并将证据长度缩减9.25倍。
摘要：
检索增强生成（RAG）领域的近期研究探索了从检索段落中提取证据，以降低计算成本并提升最终RAG性能，但这仍具挑战。现有方法严重依赖基于启发式的增强，面临几个问题：(1) 由于手工上下文过滤导致泛化性差；(2) 由于基于规则的上下文分块导致语义缺失；(3) 由于逐句过滤学习导致长度偏斜。为解决这些问题，我们提出一种基于模型的证据提取学习框架SEER，通过自对齐学习将基础模型优化为具备理想特性的证据提取器。大量实验表明，我们的方法大幅提升了最终RAG性能，增强了提取证据的忠实度、有用性和简洁性，并将证据长度缩减了9.25倍。
英文摘要：
Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily rely on heuristic-based augmentation, encountering several issues: (1) Poor generalization due to hand-crafted context filtering; (2) Semantics deficiency due to rule-based context chunking; (3) Skewed length due to sentence-wise filter learning. To address these issues, we propose a model-based evidence extraction learning framework, SEER, optimizing a vanilla model as an evidence extractor with desired properties through self-aligned learning. Extensive experiments show that our method largely improves the final RAG performance, enhances the faithfulness, helpfulness, and conciseness of the extracted evidence, and reduces the evidence length by 9.25 times. The code will be available at https://github.com/HITsz-TMG/SEER.
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。
