# Beyond Relevance: Utility-Centric Retrieval in the LLM Era

arXiv: https://arxiv.org/abs/2604.08920 · HTML: https://mlsanity.com/paper/2604.08920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [Bridging the Preference Gap between Retrievers and LLMs](https://mlsanity.com/paper/2401.06954/) (2024)
- [DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models](https://mlsanity.com/paper/2403.10081/) (2024)
- [LLatrieval: LLM-Verified Retrieval for Verifiable Generation](https://mlsanity.com/paper/2311.07838/) (2023)
- [EvolveSearch: An Iterative Self-Evolving Search Agent](https://mlsanity.com/paper/2505.22501/) (2025)
- [SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction](https://mlsanity.com/paper/2503.01478/) (2025)
- [Are Large Language Models Good at Utility Judgments?](https://mlsanity.com/paper/2403.19216/) (2024)
- [SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback](https://mlsanity.com/paper/2410.18141/) (2024)
- [Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence](https://mlsanity.com/paper/2305.03507/) (2023)
- [Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts](https://mlsanity.com/paper/2405.19893/) (2024)
- [From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification](https://mlsanity.com/paper/2310.11675/) (2023)
- [Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling](https://mlsanity.com/paper/2207.03030/) (2022)
- [Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation](https://mlsanity.com/paper/2409.15895/) (2024)
- [SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.11315/) (2024)
- [Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling](https://mlsanity.com/paper/2504.05216/) (2025)
- [U-rank: Utility-oriented Learning to Rank with Implicit Feedback](https://mlsanity.com/paper/2011.00550/) (2020)
- [Modeling Contextual Passage Utility for Multihop Question Answering](https://mlsanity.com/paper/2512.06464/) (2025)
- [Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.19102/) (2025)

## Abstract (arXiv)

Information retrieval systems have traditionally optimized for topical relevance-the degree to which retrieved documents match a query. However, relevance only approximates a deeper goal: utility, namely, whether retrieved information helps accomplish a user's underlying task. The emergence of retrieval-augmented generation (RAG) fundamentally changes this paradigm. Retrieved documents are no longer consumed directly by users but instead serve as evidence for large language models (LLMs) that produce answers. As a result, retrieval effectiveness must be evaluated by its contribution to generation quality rather than by relevance-based ranking metrics alone. This tutorial argues that retrieval objectives are evolving from relevance-centric optimization toward LLM-centric utility. We present a unified framework covering LLM-agnostic versus LLM-specific utility, context-independent versus context-dependent utility, and the connection with LLM information needs and agentic RAG. By synthesizing recent advances, the tutorial provides conceptual foundations and practical guidance for designing retrieval systems aligned with the requirements of LLM-based information access.