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.
@article{arxiv.2510.00887,
title = {On Listwise Reranking for Corpus Feedback},
author = {Soyoung Yoon and Jongho Kim and Daeyong Kwon and Avishek Anand and Seung-won Hwang},
journal= {arXiv preprint arXiv:2510.00887},
year = {2025}
}