Generate to Accelerate: Improved Reranking via LLM-Generated Pivot Documents

[2604.09492] Generate to Accelerate: Improved Reranking via LLM-Generated Pivot Documents Skip to main content Search Submit Donate Log in Computer Science > Information Retrieval arXiv:2604.09492 (cs) [Submitted on 10 Apr 2026 ( v1 ), last revised 27 Aug 2026 (this version, v3)] Title: Generate to Accelerate: Improved Reranking via LLM-Generated Pivot Documents Authors: Nilanjan Sinhababu , Soumedhik Bharati , Debasis Ganguly , Pabitra Mitra View PDF HTML (experimental) Abstract: Common approaches to reduce the computational overhead of reranking models include identifying a candidate set of documents for reranking or constructing comparison graphs to minimize redundant comparisons. For pointwise rankers, determining a candidate set typically involves estimating a query-dependent cutoff based on the scores of the top-ranked documents. In contrast, comparison graphs for listwise approaches are often derived using heuristics, such as propagating local comparisons within sliding windows in a bottom-up fashion or reducing comparisons via pivot-based strategies in a top-down manner. In this work, we argue that restricting these processes to existing documents in the collection is unnecessary. Instead, we propose leveraging the generative capabilities of large language models to synthesize a pseudo-relevant document for a given query. We then adapt existing reranking approaches and also propose a novel parallel reranking approach to leverage this LLM-generated document as a pivot. Our experiments demonstrate that using LLM-generated pivots for ranked list truncation reduces the number of pointwise ranker inferences by up to 66\%. In both in-domain and out-of-domain settings, we observe speedups of up to $2.95\times$ in listwise reranking, while maintaining comparable or improved retrieval effectiveness. Subjects: Information Retrieval (cs.IR) Cite as: arXiv:2604.09492 [cs.IR] (or arXiv:2604.09492v3 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2604.09492 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Nilanjan Sinhababu [ view email ] [v1] Fri, 10 Apr 2026 16:59:54 UTC (897 KB) [v2] Thu, 28 May 2026 08:58:53 UTC (2,236 KB) [v3] Thu, 27 Aug 2026 09:00:06 UTC (1,928 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.IR < prev | next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Generate to Accelerate: Improved Reranking via LLM-Generated Pivot Documents#674360
• Instability of LLM text embeddings for unsupervised dimension reduction of tabular data.#446130
• When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design#610039
• When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design#608977
• HNPP: Higher-order network-based personalized PageRank for detecting critical phase in complex biological systems.#380967