arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.05524cs.CLcs.DB
收藏

上下文驱动的索引修剪:从数据质量视角提升 RALM 的精确性

Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs

National University of Defense Technology(国防科技大学)

Kexin Ma, Ruochun Jin, Xi Wang, Huan Chen, Jing Ren, Yuhua Tang

AI总结:

本文提出上下文驱动的索引修剪框架 CDIT,利用上下文匹配依赖作为数据质量规则,借助大语言模型识别并剔除不一致检索结果并修正索引,从而联合提升 RALM 的数据质量与检索精度。

摘要:

检索增强大语言模型(RALMs)在提升生成回答的准确性方面已取得显著进展。然而,现有研究常常忽视检索结果中的数据质量问题,这些问题通常由现有基于向量距离的检索方法不准确所导致。我们提出从数据质量视角,通过上下文驱动的索引修剪(CDIT)框架来提升 RALM 回答的精确性,其中采用上下文匹配依赖(CMDs)作为逻辑数据质量规则,以捕获并约束检索上下文之间的一致性。基于大语言模型(LLMs)的语义理解能力,CDIT 能够有效识别并丢弃与查询上下文不一致的检索结果,并进一步修改数据库中的索引,从而提高回答质量。实验在具有挑战性的问答任务上进行了验证。同时,CDIT 的灵活性通过其与多种语言模型和索引方法的兼容性得到证实,这为共同增强 RALM 的数据质量和检索精度提供了一种有前景的方法。

英文摘要:

Retrieval-Augmented Large Language Models (RALMs) have made significant strides in enhancing the accuracy of generated responses.However, existing research often overlooks the data quality issues within retrieval results, often caused by inaccurate existing vector-distance-based retrieval methods.We propose to boost the precision of RALMs' answers from a data quality perspective through the Context-Driven Index Trimming (CDIT) framework, where Context Matching Dependencies (CMDs) are employed as logical data quality rules to capture and regulate the consistency between retrieved contexts.Based on the semantic comprehension capabilities of Large Language Models (LLMs), CDIT can effectively identify and discard retrieval results that are inconsistent with the query context and further modify indexes in the database, thereby improving answer quality.Experiments demonstrate on challenging question-answering tasks.Also, the flexibility of CDIT is verified through its compatibility with various language models and indexing methods, which offers a promising approach to bolster RALMs' data quality and retrieval precision jointly.

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。

↑