Ranked List Truncation for Large Language Model-based Re-Ranking
Author:
Affiliation:
1. University of Amsterdam, Amsterdam, Netherlands
2. University of Waterloo, Waterloo, Canada
3. Leiden University, Leiden, Netherlands
4. University of Amsterdam, Amstedam, Netherlands
Funder
Dutch Research Council (NWO)
European UnionðÄôs Horizon Europe research and innovation program
Dutch Research Council (NWO), DPG Media, RTL, and the Dutch Ministry of Economic Affairs and Climate Policy (EZK)
Netherlands Organisation for Scientific Research
China Scholarship Council (CSC)
Publisher
ACM
Link
https://dl.acm.org/doi/pdf/10.1145/3626772.3657864
Reference67 articles.
1. Zahra Abbasiantaeb, Chuan Meng, David Rau, Antonis Krasakis, Hossein A Rahmani, and Mohammad Aliannejadi. 2023. LLM-based Retrieval and Generation Pipelines for TREC Interactive Knowledge Assistance Track (iKAT) 2023. In TREC.
2. Negar Arabzadeh, Chuan Meng, Mohammad Aliannejadi, and Ebrahim Bagheri. 2024. Query Performance Prediction: From Fundamentals to Advanced Techniques. In ECIR. Springer, 381--388.
3. Avi Arampatzis Jaap Kamps and Stephen Robertson. 2009. Where to Stop Reading a Ranked List? Threshold Optimization using Truncated Score Distributions. In SIGIR. 524--531.
4. Nima Asadi and Jimmy Lin. 2013. Effectiveness/Efficiency Tradeoffs for Candidate Generation in Multi-Stage Retrieval Architectures. In SIGIR. 997--1000.
5. Arian Askari, Roxana Petcu, Chuan Meng, Mohammad Aliannejadi, Amin Abolghasemi, Evangelos Kanoulas, and Suzan Verberne. 2024. Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs. arXiv preprint arXiv:2402.11633 (2024).
Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Query Performance Prediction for Conversational Search and Beyond;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3