Accelerating Listwise Reranking: Reproducing and Enhancing FIRST
Open Access
- 13 July 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3165-3172
Abstract
No abstract availableFunding Information
- Natural Sciences and Engineering Research Council of Canada (RGPIN-2021-02490)
- Microsoft via the Accelerating Foundation Models Research program and an Institute of Information & Communica- tions Technology Planning & Evaluation (IITP) grant funded by the Korean Government (MSIT) (No. RS-2024-00457882, National AI Research Lab Proje
This publication has 9 references indexed in Scilit:
- A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models2024
- Fine-Tuning LLaMA for Multi-Stage Text Retrieval2024
- FIRST: Faster Improved Listwise Reranking with Single Token Decoding2024
- Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels2024
- Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting2024
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents2023
- Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training2023
- From Distillation to Hard Negative Sampling2022
- The Probabilistic Relevance Framework: BM25 and BeyondFoundations and Trends® in Information Retrieval, 2009