Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval

• URL: http://arxiv.org/abs/2509.07163v1
• Date: Mon, 08 Sep 2025 19:24:09 GMT
• Title: Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval
• Authors: Haike Xu, Tong Chen,
• Abstract summary: We introduce Reranker-Guided-Search (RGS), a novel approach to retrieve documents according to reranker preferences.<n>Our method uses a greedy search on proximity graphs generated by approximate nearest neighbor algorithms.<n> Experimental results demonstrate substantial performance improvements across multiple benchmarks.
• Score: 8.57583804155738
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The widely used retrieve-and-rerank pipeline faces two critical limitations: they are constrained by the initial retrieval quality of the top-k documents, and the growing computational demands of LLM-based rerankers restrict the number of documents that can be effectively processed. We introduce Reranker-Guided-Search (RGS), a novel approach that bypasses these limitations by directly retrieving documents according to reranker preferences rather than following the traditional sequential reranking method. Our method uses a greedy search on proximity graphs generated by approximate nearest neighbor algorithms, strategically prioritizing promising documents for reranking based on document similarity. Experimental results demonstrate substantial performance improvements across multiple benchmarks: 3.5 points on BRIGHT, 2.9 on FollowIR, and 5.1 on M-BEIR, all within a constrained reranker budget of 100 documents. Our analysis suggests that, given a fixed pair of embedding and reranker models, strategically selecting documents to rerank can significantly improve retrieval accuracy under limited reranker budget.

Related papers

• Adaptive Retrieval for Reasoning-Intensive Retrieval [60.30588731127791]
  Bridge documents are those that contribute to the reasoning process but are not directly relevant to the initial query.<n>Existing reasoning-based reranker pipelines attempt to surface these documents in ranking, they suffer from bounded recall.<n>We propose a framework that bridges this gap by repurposing reasoning plans as dense feedback signals for adaptive retrieval.
  arXiv  Detail & Related papers  (2026-01-08T05:46:50Z)
• Query Decomposition for RAG: Balancing Exploration-Exploitation [83.79639293409802]
  RAG systems address complex user requests by decomposing them into subqueries, retrieving potentially relevant documents for each, and then aggregating them to generate an answer.<n>We formulate query decomposition and document retrieval in an exploitation-exploration setting, where retrieving one document at a time builds a belief about the utility of a given sub-queries.<n>Our main finding is that estimating document relevance using rank information and human judgments yields a 35% gain in document-level precision, 15% increase in alpha-nDCG, and better performance on the downstream task of long-form generation.
  arXiv  Detail & Related papers  (2025-10-21T13:37:11Z)
• Relevance to Utility: Process-Supervised Rewrite for RAG [38.81331265140413]
  We show how "bridge" modules fail to capture true document utility.<n>We propose R2U, with a key distinction of directly optimizing to maximize the probability of generating a correct answer.
  arXiv  Detail & Related papers  (2025-09-19T04:24:57Z)
• Improving Document Retrieval Coherence for Semantically Equivalent Queries [63.97649988164166]
  We propose a variation of the Multi-Negative Ranking loss for training DR that improves the coherence of models in retrieving the same documents.<n>The loss penalizes discrepancies between the top-k ranked documents retrieved for diverse but semantic equivalent queries.
  arXiv  Detail & Related papers  (2025-08-11T13:34:59Z)
• CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval [30.341167520613197]
  First-stage retrieval is often suboptimal in the scientific domain, so relevant documents are ranked lower.<n>We propose CoRank, a training-free, model-agnostic reranking framework for scientific retrieval.
  arXiv  Detail & Related papers  (2025-05-19T22:10:27Z)
• Breaking the Lens of the Telescope: Online Relevance Estimation over Large Retrieval Sets [14.494301139974455]
  We propose a novel paradigm for re-ranking called online relevance estimation.<n>Online relevance estimation continuously updates relevance estimates for a query throughout the ranking process.<n>We validate our approach on TREC benchmarks under two scenarios: hybrid retrieval and adaptive retrieval.
  arXiv  Detail & Related papers  (2025-04-12T22:05:50Z)
• Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search [65.53881294642451]
  Deliberate Thinking based Dense Retriever (DEBATER)<n>DEBATER enhances recent dense retrievers by enabling them to learn more effective document representations through a step-by-step thinking process.<n> Experimental results show that DEBATER significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• Gumbel Reranking: Differentiable End-to-End Reranker Optimization [61.16471123356738]
  RAG systems rely on rerankers to identify relevant documents.<n> fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs.<n>We propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap.
  arXiv  Detail & Related papers  (2025-02-16T13:23:39Z)
• Guiding Retrieval using LLM-based Listwise Rankers [15.3583908068962]
  We propose an adaptation of an existing adaptive retrieval method that supports the listwise setting.<n>Specifically, our proposed algorithm merges results both from the initial ranking and feedback documents.<n>We demonstrate that our method can improve nDCG@10 by up to 13.23% and recall by 28.02%--all while keeping the total number of LLM inferences constant and overheads due to the adaptive process minimal.
  arXiv  Detail & Related papers  (2025-01-15T22:23:53Z)
• Drowning in Documents: Consequences of Scaling Reranker Inference [35.499018267073964]
  We measure reranker performance for full retrieval, not just re-scoring first-stage retrieval.<n>Our results reveal a surprising trend: the best existing rerankers provide initial improvements when scoring progressively more documents.
  arXiv  Detail & Related papers  (2024-11-18T17:46:32Z)
• JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking [81.88787401178378]
  We introduce JudgeRank, a novel agentic reranker that emulates human cognitive processes when assessing document relevance. We evaluate JudgeRank on the reasoning-intensive BRIGHT benchmark, demonstrating substantial performance improvements over first-stage retrieval methods. In addition, JudgeRank performs on par with fine-tuned state-of-the-art rerankers on the popular BEIR benchmark, validating its zero-shot generalization capability.
  arXiv  Detail & Related papers  (2024-10-31T18:43:12Z)
• Lexically-Accelerated Dense Retrieval [29.327878974130055]
  'LADR' (Lexically-Accelerated Dense Retrieval) is a simple-yet-effective approach that improves the efficiency of existing dense retrieval models. LADR consistently achieves both precision and recall that are on par with an exhaustive search on standard benchmarks.
  arXiv  Detail & Related papers  (2023-07-31T15:44:26Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.