Measuring What RAG Reranking Hides: A Behavioral Framework and the Fragility of Correctness Metrics
- 3 November 2026
- book chapter
- Published by Springer Nature
- p. 202-217
Abstract
No abstract availableKeywords
This publication has 14 references indexed in Scilit:
- Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation2025
- GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis2025
- Lost in the Middle: How Language Models Use Long ContextsTransactions of the Association for Computational Linguistics, 2024
- RAGAs: Automated Evaluation of Retrieval Augmented Generation2024
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents2023
- FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation2023
- ♫ MuSiQue: Multihop Questions via Single-hop Question CompositionTransactions of the Association for Computational Linguistics, 2022
- Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps2020
- Exploiting query reformulations for web search result diversification2010
- The use of MMR, diversity-based reranking for reordering documents and producing summaries1998