Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability

• URL: http://arxiv.org/abs/2608.11238v1
• Date: Fri, 31 Jul 2026 09:21:43 GMT
• Title: Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability
• Abstract summary: We propose Q-CARE, a query-agnostic and fully reference-free framework for fine-grained assessment.<n>Q-CARE decomposes queries into sub-queries and answers into atomic claims.<n>On a human-annotated benchmark, Q-CARE achieves higher correlation with human judgments than four existing RAG evaluation metrics.
• Score: 29.6470498810458
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-augmented generation improves the factuality of large language models by grounding responses in retrieved evidence, yet existing evaluation frameworks struggle to provide consistent, fine-grained diagnostics across the diverse spectrum of user queries, ranging from close-ended fact-seeking to open-ended explanatory requests. We propose Q-CARE, a query-agnostic and fully reference-free framework that enables fine-grained assessment by decomposing queries into sub-queries and answers into atomic claims. Q-CARE establishes a unified evaluation principle based on query coverage and claim verifiability, yielding coverage-aware retriever metrics (C-Prec@k, C-nDCG@k) and claim-level generator metrics (Completeness, Conciseness, and Verifiableness). On a human-annotated benchmark spanning eight datasets, Q-CARE achieves higher correlation with human judgments than four existing RAG evaluation metrics, including RAGEval and RAGChecker, proving its effectiveness as a reliable, automated evaluation framework. Code and data are publicly available at https://github.com/DISL-Lab/Q-CaRE-COLM-26.

Related papers

• CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency [9.50454647525075]
  We introduce CQC-RAG, a framework that co-designs query-level diversity injection with cross-Query Consistency evaluation.<n>CQC-RAG rewrites the original question into diverse but meaning-preserving queries.<n>It applies an evidence-grounded protocol to extract answer-evidence pairs and selects answers according to confidence stability.
  arXiv  Detail & Related papers  (2026-06-11T15:01:49Z)
• LongSumEval: Question-Answering Based Evaluation and Feedback-Driven Refinement for Long Document Summarization [5.106530060248491]
  LongSumEval is a unified framework bridging evaluation and generation through structured question-answering feedback.<n>The framework operationalizes summary quality as answerability and factual alignment of question-answer pairs.<n> Structured feedback enables significant quality improvements through self-refinement without retraining.
  arXiv  Detail & Related papers  (2026-04-28T02:07:56Z)
• A Knowledge Graph and a Tripartite Evaluation Framework Make Retrieval-Augmented Generation Scalable and Transparent [0.0]
  This study presents a Retrieval Augmented Generation (RAG) that harnesses a knowledge graph and vector search retrieval to deliver context-rich responses.<n>A central innovation of this work is the introduction of RAG Evaluation (RAG-Eval), a novel chain-of-thought tripartite evaluation framework.<n>RAG-Eval reliably detects factual gaps and query mismatches, thereby fostering trust in high demand, data centric environments.
  arXiv  Detail & Related papers  (2025-09-23T16:29:22Z)
• Controlled Retrieval-augmented Context Evaluation for Long-form RAG [58.14561461943611]
  Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources.<n>We argue that providing a comprehensive retrieval-augmented context is important for long-form RAG tasks like report generation.<n>We introduce CRUX, a framework designed to directly assess retrieval-augmented contexts.
  arXiv  Detail & Related papers  (2025-06-24T23:17:48Z)
• RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning [64.46921169261852]
  RAG-Zeval is a novel end-to-end framework that formulates faithfulness and correctness evaluation as a rule-guided reasoning task.<n>Our approach trains evaluators with reinforcement learning, facilitating compact models to generate comprehensive and sound assessments.<n>Experiments demonstrate RAG-Zeval's superior performance, achieving the strongest correlation with human judgments.
  arXiv  Detail & Related papers  (2025-05-28T14:55:33Z)
• Unanswerability Evaluation for Retrieval Augmented Generation [74.3022365715597]
  UAEval4RAG is a framework designed to evaluate whether RAG systems can handle unanswerable queries effectively.<n>We define a taxonomy with six unanswerable categories, and UAEval4RAG automatically synthesizes diverse and challenging queries.
  arXiv  Detail & Related papers  (2024-12-16T19:11:55Z)
• Human-Calibrated Automated Testing and Validation of Generative Language Models [3.2855317710497633]
  This paper introduces a comprehensive framework for the evaluation and validation of generative language models (GLMs)<n>It focuses on Retrieval-Augmented Generation (RAG) systems deployed in high-stakes domains such as banking.
  arXiv  Detail & Related papers  (2024-11-25T13:53:36Z)
• RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation [61.14660526363607]
  We propose a fine-grained evaluation framework, RAGChecker, that incorporates a suite of diagnostic metrics for both the retrieval and generation modules. RAGChecker has significantly better correlations with human judgments than other evaluation metrics. The metrics of RAGChecker can guide researchers and practitioners in developing more effective RAG systems.
  arXiv  Detail & Related papers  (2024-08-15T10:20:54Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [66.93260816493553]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios.<n>With a focus on factual accuracy, we propose three novel metrics: Completeness, Hallucination, and Irrelevance.<n> Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)
• The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA [1.2839205715237014]
  QB-RAG is a framework for enhancing Retrieval-Augmented Generation systems in healthcare question-answering.<n>A key component of QB-RAG is an LLM-based filtering mechanism that ensures that only relevant and answerable questions are included in the database.<n>Our empirical evaluation on a healthcare data set demonstrates the superior performance of QB-RAG compared to existing retrieval methods.
  arXiv  Detail & Related papers  (2024-07-25T13:47:01Z)
• SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References [73.67707138779245]
  We propose a new evaluation metric: SQuArE (Sentence-level QUestion AnsweRing Evaluation) We evaluate SQuArE on both sentence-level extractive (Answer Selection) and generative (GenQA) QA systems.
  arXiv  Detail & Related papers  (2023-09-21T16:51:30Z)

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.