{"ID":2862093,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.00887","arxiv_id":"2510.00887","title":"On Listwise Reranking for Corpus Feedback","abstract":"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.","short_abstract":"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 whe...","url_abs":"https://arxiv.org/abs/2510.00887","url_pdf":"https://arxiv.org/pdf/2510.00887v2","authors":"[\"Soyoung Yoon\",\"Jongho Kim\",\"Daeyong Kwon\",\"Avishek Anand\",\"Seung-won Hwang\"]","published":"2025-10-01T13:34:02Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}