Beyond Relevance: Utility-Centric Retrieval in the LLM Era
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913021027155968 |
|---|---|
| author | Zhang, Hengran Tang, Minghao Bi, Keping Guo, Jiafeng |
| author_facet | Zhang, Hengran Tang, Minghao Bi, Keping Guo, Jiafeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08920 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Relevance: Utility-Centric Retrieval in the LLM Era Zhang, Hengran Tang, Minghao Bi, Keping Guo, Jiafeng Information Retrieval Artificial Intelligence Computation and Language Machine Learning 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. |
| title | Beyond Relevance: Utility-Centric Retrieval in the LLM Era |
| topic | Information Retrieval Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2604.08920 |