Aligning Dense Retrievers with LLM Utility via DistillationAligning Dense Retrievers with LLM Utility via Distillation

• URL: http://arxiv.org/abs/2604.22722v1
• Date: Fri, 24 Apr 2026 17:18:56 GMT
• Title: Aligning Dense Retrievers with LLM Utility via DistillationAligning Dense Retrievers with LLM Utility via Distillation
• Abstract summary: Utility-Aligned Embeddings (UAE) is a framework designed to merge retrieval with generative utility.<n>UAE improves retrieval Recall@1 by 30.59%, MAP by 30.16% and Token F1 by 17.3% over the strong semantic baseline BGE-Base.<n>UAE is over 180x faster than the efficient LLM re-ranking methods preserving competitive performance.
• Score: 13.439895359551853
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dense vector retrieval is the practical backbone of Retrieval- Augmented Generation (RAG), but similarity search can suffer from precision limitations. Conversely, utility-based approaches leveraging LLM re-ranking often achieve superior performance but are computationally prohibitive and prone to noise inherent in perplexity estimation. We propose Utility-Aligned Embeddings (UAE), a framework designed to merge these advantages into a practical, high-performance retrieval method. We formulate retrieval as a distribution matching problem, training a bi-encoder to imitate a utility distribution derived from perplexity reduction using a Utility-Modulated InfoNCE objective. This approach injects graded utility signals directly into the embedding space without requiring test-time LLM inference. On the QASPER benchmark, UAE improves retrieval Recall@1 by 30.59%, MAP by 30.16% and Token F1 by 17.3% over the strong semantic baseline BGE-Base. Crucially, UAE is over 180x faster than the efficient LLM re-ranking methods preserving competitive performance, demonstrating that aligning retrieval with generative utility yields reliable contexts at scale.

Related papers

• LLM-as-a-Verifier: A General-Purpose Verification Framework [74.40111651545979]
  We introduce LLM-as-a-Verifier, a general-purpose verification framework.<n>It provides fine-grained feedback for agentic tasks without requiring additional training.<n>It achieves state-of-the-art performance on several benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:59:35Z)
• iCoRe: An Iterative Correlation-Aware Retriever for Bug Reproduction Test Generation [10.824024745675281]
  iCoRe is an iterative, correlation-aware context retrieval approach.<n>Our method achieves a Fail-to-Pass rate of 42.0% and 52.8% respectively.
  arXiv  Detail & Related papers  (2026-04-21T08:26:30Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning [57.24524263804788]
  Code verifiers play a critical role in post-verification for LLM-based code generation.<n>Existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency.<n>We show that naive RL with only functionality rewards fails to generate effective unit tests for difficult branches and samples.
  arXiv  Detail & Related papers  (2026-01-30T10:33:29Z)
• LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG [15.963908827464296]
  We propose Lightweight Utility-driven Reranking for Efficient RAG.<n>It augments any black-box retriever with an efficient Lambda-based reranker.<n>It achieves competitive performance, reaching 97-98% of the state-of-the-art dense neural baseline.
  arXiv  Detail & Related papers  (2026-01-27T12:26:31Z)
• Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation [110.610512800947]
  Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating retrieved information.<n>In RAG, the emphasis has shifted to utility, which considers the usefulness of passages for generating accurate answers.<n>Our approach focuses on utility-based selection rather than ranking, enabling dynamic passage selection tailored to specific queries without the need for fixed thresholds.<n>Our experiments demonstrate that utility-based selection provides a flexible and cost-effective solution for RAG, significantly reducing computational costs while improving answer quality.
  arXiv  Detail & Related papers  (2025-07-25T09:32:29Z)
• Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers [17.658542084440082]
  Large Language Models (LLMs) have been applied to reranking tasks in information retrieval, achieving strong performance.<n>Existing studies evaluate the efficiency of LLM-based rerankers using proxy metrics such as latency, the number of forward passes, input tokens, and output tokens.<n>We propose RPP (ranking metrics per PetaFLOP), measuring how much ranking quality (e.g., NDCG or MRR) a method achieves per PetaFLOP, and QPP (queries per PetaFLOP), measuring how many queries can be processed per PetaFLOP.
  arXiv  Detail & Related papers  (2025-07-08T17:56:28Z)
• Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers [74.17516978246152]
  Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques.<n>We propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds.<n>Experiments on four knowledge-intensive benchmarks show that EXSEARCH substantially outperforms baselines.
  arXiv  Detail & Related papers  (2025-05-26T15:27:55Z)
• Effective Inference-Free Retrieval for Learned Sparse Representations [19.54810957623511]
  Learned Sparse Retrieval (LSR) is an effective IR approach that exploits pre-trained language models for encoding text into a learned bag of words.<n>Recently, new efficient -- inverted index-based -- retrieval engines have been proposed, leading to a natural question: has the role of regularization changed in training LSR models?<n>We show that regularization can be relaxed to produce more effective LSR encoders.
  arXiv  Detail & Related papers  (2025-04-30T09:10:46Z)
• SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction [20.6787276745193]
  We introduce an automatic evaluation method that measures retrieval quality through the lens of information gain within the RAG framework.<n>We quantify the utility of retrieval by the extent to which it reduces semantic perplexity post-retrieval.
  arXiv  Detail & Related papers  (2025-03-03T12:37:34Z)
• FIRST: Faster Improved Listwise Reranking with Single Token Decoding [56.727761901751194]
  First, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
  arXiv  Detail & Related papers  (2024-06-21T21:27:50Z)

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.