ECoRAG：基于证据指导的长上下文RAG压缩

摘要

大型语言模型（LLMs）在开放域问答（ODQA）任务中展现了卓越的性能，这得益于其通过检索增强生成（RAG）机制利用外部文档的能力。为了降低RAG在处理较长上下文时的开销，进行上下文压缩成为必要。然而，现有的压缩方法未能有效过滤非证据性信息，这限制了LLM在基于RAG的应用中的表现。为此，我们提出了证据导向的RAG框架，即ECoRAG。ECoRAG通过依据证据性对检索到的文档进行压缩，确保答案生成得到正确证据的支持，从而提升LLM的性能。作为额外步骤，ECoRAG还会评估压缩后的内容是否提供了足够的证据，若不足，则继续检索直至满足条件。实验表明，ECoRAG在ODQA任务上显著提升了LLM的表现，超越了现有的压缩方法。此外，ECoRAG具有极高的成本效益，不仅减少了延迟，还通过仅保留生成正确答案所需的信息，最小化了token的使用量。代码已发布于https://github.com/ldilab/ECoRAG。

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.

ECoRAG：基于证据指导的长上下文RAG压缩

ECoRAG: Evidentiality-guided Compression for Long Context RAG

摘要

Support