How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 5693-5709
Abstract
Abdelrahman Abdallah, Bhawna Piryani, Jamshid Mozafari, Mohammed Ali, Adam Jatowt. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions2026
- Retrieval-Augmented Generation for AI-Generated Content: A SurveyData Science and Engineering, 2026
- RerankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback2025
- Evaluation of Retrieval-Augmented Generation: A Survey2025
- FIRST: Faster Improved Listwise Reranking with Single Token Decoding2024
- ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval2024
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents2023
- LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion2023
- Improving Passage Retrieval with Zero-Shot Question Generation2022
- Document Ranking with a Pretrained Sequence-to-Sequence Model2020