Research
Rag Performance Prediction for Question Answering
arXiv:2604.07985v1 Announce Type: new Abstract: We address the task of predicting the gain of using RAG (retrieval augmented generation) for question answering with respect to not using it. We study t
arXiv:2604.07985v1 Announce Type: new Abstract: We address the task of predicting the gain of using RAG (retrieval augmented generation) for question answering with respect to not using it. We study the performance of a few pre-retrieval and post-retrieval predictors originally devised for ad hoc retrieval. We also study a few post-generation predictors, one of which is novel to this study and posts the best prediction quality. Our results show that the most effective prediction approach is a novel supervised predictor that explicitly models the semantic relationships among the question, retrieved passages, and the generated answer.
Related
- Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
- ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation
- An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations
- Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
Source: arXiv cs.CL | 2026-04-10