On Listwise Reranking for Corpus Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoon, Soyoung, Kim, Jongho, Kwon, Daeyong, Anand, Avishek, Hwang, Seung-won
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914211582443520
author Yoon, Soyoung
Kim, Jongho
Kwon, Daeyong
Anand, Avishek
Hwang, Seung-won
author_facet Yoon, Soyoung
Kim, Jongho
Kwon, Daeyong
Anand, Avishek
Hwang, Seung-won
contents Reranker improves retrieval performance by capturing document interactions. At one extreme, graph-aware adaptive retrieval (GAR) represents an information-rich regime, requiring a pre-computed document similarity graph in reranking. However, as such graphs are often unavailable, or incur quadratic memory costs even when available, graph-free rerankers leverage large language model (LLM) calls to achieve competitive performance. We introduce L2G, a novel framework that implicitly induces document graphs from listwise reranker logs. By converting reranker signals into a graph structure, L2G enables scalable graph-based retrieval without the overhead of explicit graph computation. Results on the TREC-DL and BEIR subset show that L2G matches the effectiveness of oracle-based graph methods, while incurring zero additional LLM calls.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00887
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On Listwise Reranking for Corpus Feedback
Yoon, Soyoung
Kim, Jongho
Kwon, Daeyong
Anand, Avishek
Hwang, Seung-won
Information Retrieval
Reranker improves retrieval performance by capturing document interactions. At one extreme, graph-aware adaptive retrieval (GAR) represents an information-rich regime, requiring a pre-computed document similarity graph in reranking. However, as such graphs are often unavailable, or incur quadratic memory costs even when available, graph-free rerankers leverage large language model (LLM) calls to achieve competitive performance. We introduce L2G, a novel framework that implicitly induces document graphs from listwise reranker logs. By converting reranker signals into a graph structure, L2G enables scalable graph-based retrieval without the overhead of explicit graph computation. Results on the TREC-DL and BEIR subset show that L2G matches the effectiveness of oracle-based graph methods, while incurring zero additional LLM calls.
title On Listwise Reranking for Corpus Feedback
topic Information Retrieval
url https://arxiv.org/abs/2510.00887