2024
Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs
EMNLP 2024finding
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. W…