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

TL;DR

This paper explores ranked list truncation (RLT) in large language model-based re-ranking, analyzing its effectiveness and generalizability across different retrieval and re-ranking setups to improve efficiency and effectiveness.

Contribution

It reproduces and evaluates existing RLT methods within the context of LLM-based re-ranking, providing new insights into their applicability and impact across various retrieval and re-ranking configurations.

Findings

RLT methods can improve re-ranking efficiency and effectiveness.

The impact of retriever and re-ranker types on RLT effectiveness varies.

Established RLT findings are partially generalizable to LLM-based re-ranking.

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.