# LLM-Specific Utility for Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2510.11358 · HTML: https://mlsanity.com/paper/2510.11358/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 25 of its 51 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [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)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards](https://mlsanity.com/paper/2402.18571/) (2024)
- [Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering](https://mlsanity.com/paper/1905.05733/) (2019)
- [Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization](https://mlsanity.com/paper/2405.02816/) (2024)
- [Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception](https://mlsanity.com/paper/2502.11677/) (2025)
- [Are Large Language Models Good at Utility Judgments?](https://mlsanity.com/paper/2403.19216/) (2024)
- [From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification](https://mlsanity.com/paper/2310.11675/) (2023)
- [Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization](https://mlsanity.com/paper/2410.09942/) (2024)
- [Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents](https://mlsanity.com/paper/2503.08684/) (2025)
- [Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion](https://mlsanity.com/paper/2204.10936/) (2022)

## Built on by (most cited first, 4 of 4)

- [MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning](https://mlsanity.com/paper/2603.03379/) (2026)
- [What Would Fix This RAG Failure? Auditing Counterfactual Response with Paired Evidence Interventions](https://mlsanity.com/paper/2608.08944/) (2026)
- [Preference Is Not Intervention: The Structure and Stability Boundaries of Reader-Specific Evidence Utility](https://mlsanity.com/paper/2608.17781/) (2026)
- [Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG](https://mlsanity.com/paper/2609.37469/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) is typically optimized for topical relevance, yet its success ultimately depends on whether retrieved passages are useful for a large language model (LLM) to generate correct and complete answers. We argue that such utility is often LLM-specific rather than universal, due to differences in models' knowledge, reasoning, and ability to leverage evidence. We formalize LLM-specific utility as the performance improvement of a target LLM when a passage is provided, compared to answering without evidence. To systematically study LLM-specific utility, we construct a benchmark of LLM-specific gold utilitarian passages for four LLMs (Qwen3-8B/14B/32B and Llama 3.1-8B) on three QA datasets (Natural Questions, TriviaQA, and MS MARCO-FQA). Our analysis shows that utilitarian passages are model-dependent and non-transferable: each LLM performs best with its own utilitarian evidence, while evidence optimized for other LLMs is consistently suboptimal. Human-annotated evidence remains a strong general baseline but does not fully match individual LLM utility needs. We further introduce the LLM-specific utility judgment task and construct the corresponding benchmark, i.e., SpecUBench (LLM-Specific Utility Benchmark). Experiments show that existing utility-aware selection and scoring methods largely capture model-agnostic usefulness and struggle to reliably estimate LLM-specific utility. Overall, our findings highlight the limitations of current utility-aware retrieval and motivate generator-tailored evidence selection for improving RAG. Our code and datasets can be found at https://github.com/Trustworthy-Information-Access/LLM_specific_utility.