面向复杂领域增强检索增强生成的上下文自适应合成与压缩
Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains
AI总结：
本文提出CASC框架，通过微调小型LLM驱动的CAS模块对检索上下文进行关键信息提取、冲突消解和结构化合成，以缓解复杂领域RAG中的信息过载问题，并在SciDocs-QA数据集上验证其优于强基线。
摘要：
大型语言模型（LLMs）在语言任务中表现出色，但容易产生幻觉和知识过时。检索增强生成（RAG）通过将LLMs基于外部知识来缓解这些问题。然而，在涉及多篇、冗长或相互冲突文档的复杂领域中，传统RAG面临信息过载和低效合成的问题，导致答案不准确且不可信。为解决这一问题，我们提出CASC（Context-Adaptive Synthesis and Compression，上下文自适应合成与压缩），这是一个智能处理检索上下文的新框架。CASC引入了一个上下文分析与合成器（CAS）模块，该模块由一个经过微调的较小LLM驱动，执行关键信息提取、跨文档一致性检查与冲突消解，以及面向问题的结构化合成。这一过程将原始、分散的信息转化为高度浓缩、结构化且语义丰富的上下文，显著降低了最终Reader LLM的token数量和认知负荷。我们在SciDocs-QA上评估CASC，这是一个新的具有挑战性的多文档问答数据集，专为具有固有冗余和冲突的复杂科学领域设计。我们的大量实验表明，CASC持续优于强基线方法。
英文摘要：
Large Language Models (LLMs) excel in language tasks but are prone to hallucinations and outdated knowledge. Retrieval-Augmented Generation (RAG) mitigates these by grounding LLMs in external knowledge. However, in complex domains involving multiple, lengthy, or conflicting documents, traditional RAG suffers from information overload and inefficient synthesis, leading to inaccurate and untrustworthy answers. To address this, we propose CASC (Context-Adaptive Synthesis and Compression), a novel framework that intelligently processes retrieved contexts. CASC introduces a Context Analyzer & Synthesizer (CAS) module, powered by a fine-tuned smaller LLM, which performs key information extraction, cross-document consistency checking and conflict resolution, and question-oriented structured synthesis. This process transforms raw, scattered information into a highly condensed, structured, and semantically rich context, significantly reducing the token count and cognitive load for the final Reader LLM. We evaluate CASC on SciDocs-QA, a new challenging multi-document question answering dataset designed for complex scientific domains with inherent redundancies and conflicts. Our extensive experiments demonstrate that CASC consistently outperforms strong baselines.
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。
