SARA通过文本与语义向量融合，提升大模型问答的准确性和效率。
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
- 用文本片段和压缩向量双层表示上下文，兼顾细节与概括。
- 在9个数据集上平均提升答案相关性17.71、正确性13.72、语义相似度15.53。
- 适合需要高效利用上下文、追求高准确率的RAG应用。
检索增强生成（RAG）虽扩展了大语言模型的外部知识，但面临有效上下文长度受限和检索文档冗余的问题。纯压缩方法虽减少输入规模，却常丢失影响事实准确性的细粒度信息。我们提出SARA，一个统一的RAG框架，在严格上下文预算下平衡局部精确性与全局知识覆盖。SARA结合自然语言文本片段与语义压缩向量，共同提升上下文效率与答案正确性。其上下文表示分为两个互补层面：1）保留关键实体与数值的细粒度自然语言片段；2）紧凑可解释的向量，用于总结高层语义。一个迭代证据选择模块利用压缩向量动态重排上下文。在9个数据集和5个开源LLM（涵盖Mistral、Llama、Gemma三类模型）上，SARA持续提升答案相关性（+17.71）、正确性（+13.72）和语义相似度（+15.53），证明融合文本与压缩表示对鲁棒、高效的RAG至关重要。
原文摘要 · Abstract (English)
Retrieval-augmented Generation (RAG) extends large language models (LLMs) with external knowledge but faces key challenges: restricted effective context length and redundancy in retrieved documents. Pure compression-based approaches reduce input size but often discard fine-grained details essential for factual accuracy. We propose SARA, a unified RAG framework that balances local precision and global knowledge coverage under tight context budgets. SARA combines natural-language text snippets with semantic compression vectors to jointly enhance context efficiency and answer correctness. It represents contexts at two complementary levels: 1) fine-grained natural-language spans that preserve critical entities and numerical values, and 2) compact, interpretable vectors that summarize high-level semantics. An iterative evidence-selection module employs the compression vectors for dynamic reranking of contexts. Across 9 datasets and 5 open-source LLMs spanning 3 model families (Mistral, Llama, and Gemma), SARA consistently improves answer relevance (+17.71), answer correctness (+13.72), and semantic similarity (+15.53), demonstrating the importance of integrating textual and compressed representations for robust, context-efficient RAG.
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。