Your Dense Retriever is Secretly an Expeditious Reasoner

• URL: http://arxiv.org/abs/2510.21727v2
• Date: Tue, 28 Oct 2025 02:31:06 GMT
• Title: Your Dense Retriever is Secretly an Expeditious Reasoner
• Authors: Yichi Zhang, Jun Bai, Zhixin Cai, Shuhan Qin, Zhuofan Chen, Jinghua Guan, Wenge Rong,
• Abstract summary: We propose Adaptive Query Reasoning (AdaQR), a hybrid query rewriting framework.<n>AdaQR reduces reasoning cost by 28% while preserving-or even improving-retrieval performance by 7%.
• Score: 12.123445960145693
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dense retrievers enhance retrieval by encoding queries and documents into continuous vectors, but they often struggle with reasoning-intensive queries. Although Large Language Models (LLMs) can reformulate queries to capture complex reasoning, applying them universally incurs significant computational cost. In this work, we propose Adaptive Query Reasoning (AdaQR), a hybrid query rewriting framework. Within this framework, a Reasoner Router dynamically directs each query to either fast dense reasoning or deep LLM reasoning. The dense reasoning is achieved by the Dense Reasoner, which performs LLM-style reasoning directly in the embedding space, enabling a controllable trade-off between efficiency and accuracy. Experiments on large-scale retrieval benchmarks BRIGHT show that AdaQR reduces reasoning cost by 28% while preserving-or even improving-retrieval performance by 7%.

Related papers

• ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs [14.25887925588904]
  We propose a retrieval-augmented framework that combines query-aware neighborhood retrieval with large language model (LLM) chain-of-thought reasoning.<n>ROG decomposes a multi-operator query into a sequence of single-operator sub-queries.<n> Intermediate answer sets are cached and reused across steps, improving consistency on deep reasoning chains.
  arXiv  Detail & Related papers  (2026-02-02T17:45:43Z)
• OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning [51.58235452818926]
  We introduce OrLog, a neuro-symbolic retrieval framework that decouples predicate-level plausibility estimation from logical reasoning.<n>A large language model (LLM) provides plausibility scores for atomic predicates in one decoding-free forward pass, from which a probabilistic reasoning engine derives the posterior probability of query satisfaction.
  arXiv  Detail & Related papers  (2026-01-30T15:31:58Z)
• Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents [50.212640395029744]
  We study how to allocate reasoning budget in deep search pipelines.<n>Using the BrowseComp-Plus benchmark, we analyze tradeoffs between model scale, reasoning effort, reranking depth, and total token cost.
  arXiv  Detail & Related papers  (2026-01-20T18:38:35Z)
• Reinforced Efficient Reasoning via Semantically Diverse Exploration [73.41112984160992]
  Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs)<n>We propose reinforced efficient reasoning via semantically diverse explorations, i.e., ROSE, for LLMs.<n>Our method incorporates a semantic-entropy-based branching strategy and an $varepsilon$-exploration mechanism.
  arXiv  Detail & Related papers  (2026-01-08T15:56:44Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval [36.38599923075882]
  DIVER is a retrieval pipeline designed for reasoning-intensive information retrieval.<n>It consists of four components: the document preprocessing stage, the query expansion stage, the retrieval stage and the reranking stage.<n>On the BRIGHT benchmark, DIVER achieves state-of-the-art nDCG@10 scores of 45.8 overall and 28.9 on original queries, consistently outperforming competitive reasoning-aware models.
  arXiv  Detail & Related papers  (2025-08-11T13:57:49Z)
• LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval [54.2765452810124]
  We introduce LogiCoL, a logically-informed contrastive learning objective for dense retrievers.<n>We show that models trained with LogiCoL yield improvement both in terms of retrieval performance and logical consistency in the results.
  arXiv  Detail & Related papers  (2025-05-26T07:00:32Z)
• GuRE:Generative Query REwriter for Legal Passage Retrieval [20.387315810696368]
  Legal Passage Retrieval (LPR) systems are crucial as they help practitioners save time when drafting legal arguments.<n>One primary reason is the significant vocabulary mismatch between the query and the target passage.<n>We propose a simple yet effective method, the Generative query REwriter (GuRE)
  arXiv  Detail & Related papers  (2025-05-19T10:42:36Z)
• Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models [29.934928091542375]
  Scaling dense retrievers to larger large language model (LLM) backbones has been a dominant strategy for improving their retrieval effectiveness.<n>We introduce PromptPRF, a feature-based pseudo-relevance feedback (PRF) framework that enables small LLM-based dense retrievers to achieve effectiveness comparable to much larger models.
  arXiv  Detail & Related papers  (2025-03-19T04:30:20Z)
• DeepRAG: Thinking to Retrieve Step by Step for Large Language Models [92.87532210660456]
  We propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP)<n>By iteratively decomposing queries, DeepRAG dynamically determines whether to retrieve external knowledge or rely on parametric reasoning at each step.<n> Experiments show that DeepRAG improves retrieval efficiency and boosts answer accuracy by 26.4%, demonstrating its effectiveness in enhancing retrieval-augmented reasoning.
  arXiv  Detail & Related papers  (2025-02-03T08:22:45Z)
• Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval [12.83513794686623]
  In this paper, we propose and study a more challenging type of retrieval task, called hidden rationale retrieval.<n>To address such problems, an instruction-tuned Large language model (LLM) with a cross-encoder architecture could be a reasonable choice.<n>We name this retrieval framework by RaHoRe and verify its zero-shot and fine-tuned performance superiority on Emotional Support Conversation (ESC)
  arXiv  Detail & Related papers  (2024-12-21T13:19:15Z)

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.