Ranked List Truncation for Large Language Model-based Re-Ranking

International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 141–151

Abstract

We study ranked list truncation (RLT) from a novel retrieve-then-re-rank perspective, where we optimize re-ranking by truncating the retrieved list (i.e., trim re-ranking candidates). RLT is crucial for re-ranking as it can improve re-ranking efficiency by sending variable-length candidate lists to a re-ranker on a per-query basis. It also has the potential to improve re-ranking effectiveness. Despite its importance, there is limited research into applying RLT methods to this new perspective. To address this research gap, we reproduce existing RLT methods in the context of re-ranking, especially newly emerged large language model (LLM)-based re-ranking. In particular, we examine to what extent established findings on RLT for retrieval are generalizable to the "retrieve-then-re-rank" setup from three perspectives: (i) assessing RLT methods in the context of LLM-based re-ranking with lexical first-stage retrieval, (ii) investigating the impact of different types of first-stage retrievers on RLT methods, and (iii) investigating the impact of different types of re-rankers on RLT methods. We perform experiments on the TREC 2019 and 2020 deep learning tracks, investigating 8 RLT methods for pipelines involving 3 retrievers and 2 re-rankers. We reach new insights into RLT methods in the context of re-ranking.

Authors 5

1. Chuan Meng

   University of Waterloo · University of Amsterdam

   Affiliation as printed

   University of Amsterdam, Amsterdam, Netherlands

   , The

   University of Amsterdam Amsterdam, The Netherlands

   University of Waterloo Waterloo, Canada

   of , The

2. Negar Arabzadeh

   University of Waterloo · University of Amsterdam

   Affiliation as printed

   University of Waterloo, Waterloo, Canada

   , The

   University of Amsterdam Amsterdam, The Netherlands

   of , The

3. Arian Askari Aachen

   Leiden University · University of Waterloo · University of Amsterdam

   Affiliation as printed

   Leiden University, Leiden, Netherlands

   , The

   University of Amsterdam Amsterdam, The Netherlands

   University of Waterloo Waterloo, Canada

   of , The

4. Mohammad Aliannejadi

   University of Waterloo · University of Amsterdam

   Affiliation as printed

   University of Amsterdam, Amstedam, Netherlands

   , The

   University of Amsterdam Amsterdam, The Netherlands

   University of Waterloo Waterloo, Canada

   of , The

5. Maarten de Rijke

   University of Waterloo · University of Amsterdam

   Affiliation as printed

   University of Amsterdam, Amsterdam, Netherlands

   , The

   University of Amsterdam Amsterdam, The Netherlands

   University of Waterloo Waterloo, Canada

   of , The