paper-with-me

홈 › Papers

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

2024-04-28 · Chuan Meng, Negar Arabzadeh, Arian Askari, Mohammad Aliannejadi, Maarten de Rijke

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.

📄 PDF Abstract BibTeX arXiv:2404.18185

Code (1)

chuanmeng/rlt4reranking 공식 구현 jax

Tasks

Language ModelingLanguage ModellingLarge Language ModelRe-RankingRetrieval

Similar Papers 제목 키워드 기반

List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation

2024-02-05 · Shicheng Xu, Liang Pang, Jun Xu, HuaWei Shen 외

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List…

Information RetrievalLearning-To-RankMisinformationReranking+2

Choppy: Cut Transformer For Ranked List Truncation

2020-04-26 · Dara Bahri, Yi Tay, Che Zheng, Donald Metzler 외

Work in information retrieval has traditionally focused on ranking and relevance: given a query, return some number of results ordered by relevance to the user. However, the problem of determining how many results to ret…

Information RetrievalRetrieval

Surprise: Result List Truncation via Extreme Value Theory

2020-10-19 · Dara Bahri, Che Zheng, Yi Tay, Donald Metzler 외

Work in information retrieval has largely been centered around ranking and relevance: given a query, return some number of results ordered by relevance to the user. The problem of result list truncation, or where to trun…

Information RetrievalRetrievalTwo-sample testing

An Empirical Analysis of the Effect of Ballot Truncation on Ranked-Choice Electoral Outcomes

2023-06-09 · Mallory Dickerson, Erin Martin, David McCune

In ranked-choice elections voters cast preference ballots which provide a voter's ranking of the candidates. The method of ranked-choice voting (RCV) chooses a winner by using voter preferences to simulate a series of ru…

Statistical Models of Top-$k$ Partial Orders

2024-06-22 · Amel Awadelkarim, Johan Ugander

In many contexts involving ranked preferences, agents submit partial orders over available alternatives. Statistical models often treat these as marginal in the space of total orders, but this approach overlooks informat…