Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs
This addresses retrieval precision and data quality for RALMs, offering a flexible approach that is compatible with various models and indexing methods, though it appears incremental as it builds on existing retrieval and LLM capabilities.
The paper tackles the problem of data quality issues in retrieval-augmented large language models (RALMs) caused by inaccurate retrieval methods, proposing the Context-Driven Index Trimming (CDIT) framework to improve answer precision by identifying and discarding inconsistent retrieval results, with experiments showing enhanced performance on challenging question-answering tasks.
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.