基于证据性压缩，让大模型更准地从长文档中找答案。
ECoRAG: Evidentiality-guided Compression for Long Context RAG
- 根据内容是否提供有效证据，筛选并压缩检索到的文本。
- 在多个问答任务上超越现有压缩方法，且减少延迟和令牌消耗。
- 适合需要高精度与低资源开销的长文档问答场景。
大型语言模型（LLMs）通过检索增强生成（RAG）利用外部文档，在开放域问答（ODQA）中表现优异。为降低RAG开销，需对长上下文进行压缩。然而，已有压缩方法未关注过滤非证据性信息，限制了性能。为此，我们提出证据性引导的RAG框架——ECoRAG。ECoRAG通过基于证据性的压缩，确保答案生成有正确依据；若压缩后证据不足，则继续检索直至满足。实验表明，ECoRAG在ODQA任务上优于现有压缩方法，同时显著降低延迟和令牌使用量，实现高效与高精度兼顾。代码已开源：https://github.com/ldilab/ECoRAG。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown remarkable performance in Open-Domain Question Answering (ODQA) by leveraging external documents through Retrieval-Augmented Generation (RAG). To reduce RAG overhead, from longer context, context compression is necessary. However, prior compression methods do not focus on filtering out non-evidential information, which limit the performance in LLM-based RAG. We thus propose Evidentiality-guided RAG, or ECoRAG framework. ECoRAG improves LLM performance by compressing retrieved documents based on evidentiality, ensuring whether answer generation is supported by the correct evidence. As an additional step, ECoRAG reflects whether the compressed content provides sufficient evidence, and if not, retrieves more until sufficient. Experiments show that ECoRAG improves LLM performance on ODQA tasks, outperforming existing compression methods. Furthermore, ECoRAG is highly cost-efficient, as it not only reduces latency but also minimizes token usage by retaining only the necessary information to generate the correct answer. Code is available at https://github.com/ldilab/ECoRAG.
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。