LLM-confidence reranker: A training-free approach for enhancing retrieval-augmented generation systems

By Zhi-Peng Song, Xiang-Yu Kong, Xinrui Bao, Yi-Zhi Zhou, Jiu-Long Jiao, Si-Tong Liu, Yu-Hang Zhou, Heng Qi. 2026

Subfields: Retrieval-Augmented Generation, Information Retrieval & Search

Citations in the corpus

• A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering (2026, unknown): “Recent approaches have also explored LLM-based re-ranking strategies to improve the quality of retrieved evidence [31].”