Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.03541 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915832902189056 |
|---|---|
| author | Sivakumar, Aswini Sugumaran, Vijayan Qiang, Yao |
| author_facet | Sivakumar, Aswini Sugumaran, Vijayan Qiang, Yao |
| contents | Automated question-answering (QA) systems increasingly rely on retrieval-augmented generation (RAG) to ground large language models (LLMs) in authoritative medical knowledge, ensuring clinical accuracy and patient safety in Artificial Intelligence (AI) applications for healthcare. Despite progress in RAG evaluation, current benchmarks focus only on simple multiple-choice QA tasks and employ metrics that poorly capture the semantic precision required for complex QA tasks. These approaches fail to diagnose whether an error stems from faulty retrieval or flawed generation, limiting developers from performing targeted improvement. To address this gap, we propose RAG-X, a diagnostic framework that evaluates the retriever and generator independently across a triad of QA tasks: information extraction, short-answer generation, and multiple-choice question (MCQ) answering. RAG-X introduces Context Utilization Efficiency (CUE) metrics to disaggregate system success into interpretable quadrants, isolating verified grounding from deceptive accuracy. Our experiments reveal an ``Accuracy Fallacy", where a 14\% gap separates perceived system success from evidence-based grounding. By surfacing hidden failure modes, RAG-X offers the diagnostic transparency needed for safe and verifiable clinical RAG systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03541 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering Sivakumar, Aswini Sugumaran, Vijayan Qiang, Yao Computation and Language Artificial Intelligence Automated question-answering (QA) systems increasingly rely on retrieval-augmented generation (RAG) to ground large language models (LLMs) in authoritative medical knowledge, ensuring clinical accuracy and patient safety in Artificial Intelligence (AI) applications for healthcare. Despite progress in RAG evaluation, current benchmarks focus only on simple multiple-choice QA tasks and employ metrics that poorly capture the semantic precision required for complex QA tasks. These approaches fail to diagnose whether an error stems from faulty retrieval or flawed generation, limiting developers from performing targeted improvement. To address this gap, we propose RAG-X, a diagnostic framework that evaluates the retriever and generator independently across a triad of QA tasks: information extraction, short-answer generation, and multiple-choice question (MCQ) answering. RAG-X introduces Context Utilization Efficiency (CUE) metrics to disaggregate system success into interpretable quadrants, isolating verified grounding from deceptive accuracy. Our experiments reveal an ``Accuracy Fallacy", where a 14\% gap separates perceived system success from evidence-based grounding. By surfacing hidden failure modes, RAG-X offers the diagnostic transparency needed for safe and verifiable clinical RAG systems. |
| title | RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.03541 |