Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA

• URL: http://arxiv.org/abs/2603.24580v1
• Date: Wed, 25 Mar 2026 17:54:39 GMT
• Title: Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
• Abstract summary: We study the application of RAG to AI governance and policy analysis using the AI Governance and Regulatory Archive corpus.<n>Our system combines a ColBERT-based retriever fine-tuned with contrastive learning and a generator aligned to human preferences.<n>We find that domain-specific fine-tuning improves retrieval metrics but does not consistently improve end-to-end question answering performance.
• Score: 5.182285573627426
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Retrieval-augmented generation (RAG) systems are increasingly used to analyze complex policy documents, but achieving sufficient reliability for expert usage remains challenging in domains characterized by dense legal language and evolving, overlapping regulatory frameworks. We study the application of RAG to AI governance and policy analysis using the AI Governance and Regulatory Archive (AGORA) corpus, a curated collection of 947 AI policy documents. Our system combines a ColBERT-based retriever fine-tuned with contrastive learning and a generator aligned to human preferences using Direct Preference Optimization (DPO). We construct synthetic queries and collect pairwise preferences to adapt the system to the policy domain. Through experiments evaluating retrieval quality, answer relevance, and faithfulness, we find that domain-specific fine-tuning improves retrieval metrics but does not consistently improve end-to-end question answering performance. In some cases, stronger retrieval counterintuitively leads to more confident hallucinations when relevant documents are absent from the corpus. These results highlight a key concern for those building policy-focused RAG systems: improvements to individual components do not necessarily translate to more reliable answers. Our findings provide practical insights for designing grounded question-answering systems over dynamic regulatory corpora.

Related papers

• Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval [0.0]
  Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding their responses in external knowledge.<n>This paper presents an Agent-Orchestrated Adaptive RAG framework that introduces dynamic query decomposition, iterative retrieval, and a bounded self-reflective evaluation loop.
  arXiv  Detail & Related papers  (2026-06-04T03:38:46Z)
• FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation [73.22935457705057]
  We introduce FRESCO, a benchmark for evaluating re-rankers in temporally dynamic contexts.<n>By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance.<n>Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete.
  arXiv  Detail & Related papers  (2026-04-14T17:04:25Z)
• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• Let the Barbarians In: How AI Can Accelerate Systems Performance Research [80.43506848683633]
  We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems.<n>We demonstrate that ADRS-generated solutions can match or even outperform human state-of-the-art designs.
  arXiv  Detail & Related papers  (2025-12-16T18:51:23Z)
• RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG [0.0]
  Retrieval-Augmented Generation (RAG) is a critical technique for grounding Large Language Models (LLMs) in factual evidence.<n>Existing evaluation frameworks often rely on metrics that fail to capture domain-specific nuances.<n>This paper introduces RAGalyst, an automated, human-aligned agentic framework designed for the rigorous evaluation of domain-specific RAG systems.
  arXiv  Detail & Related papers  (2025-11-06T16:22:52Z)
• Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation [55.47971671635531]
  Large Language Models (LLMs) have shown remarkable performance on general Question Answering (QA)<n>Retrieval-Augmented Generation (RAG) addresses this limitation by enriching LLMs with external knowledge.<n>Existing systems primarily rely on unstructured documents, while largely overlooking relational databases.
  arXiv  Detail & Related papers  (2025-09-30T22:19:44Z)
• From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems [6.762635083456022]
  We investigate how entity coreference affects both document retrieval and generative performance in RAG-based systems.<n>We demonstrate that coreference resolution enhances retrieval effectiveness and improves question-answering (QA) performance.<n>This study aims to provide a deeper understanding of the challenges posed by coreferential complexity in RAG, providing guidance for improving retrieval and generation in knowledge-intensive AI applications.
  arXiv  Detail & Related papers  (2025-07-10T15:26:59Z)
• Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers [0.0]
  Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models.<n>RAG introduces new challenges in retrieval quality, grounding fidelity, pipeline efficiency, and robustness against noisy or adversarial inputs.<n>This survey aims to consolidate current knowledge in RAG research and serve as a foundation for the next generation of retrieval-augmented language modeling systems.
  arXiv  Detail & Related papers  (2025-05-28T22:57:04Z)
• Transparent NLP: Using RAG and LLM Alignment for Privacy Q&A [15.86510147965235]
  General Data Protection Regulation requires precise processing information to be clear and accessible.<n>This paper examines state-of-the-art Retrieval Generation (RAG) systems enhanced with alignment techniques to fulfill obligations.
  arXiv  Detail & Related papers  (2025-02-10T16:42:00Z)
• 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)
• HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications [2.527078412319764]
  Large Language Models (LLMs) face limitations in AI legal and policy applications due to outdated knowledge, hallucinations, and poor reasoning in complex contexts.<n>Retrieval-Augmented Generation (RAG) systems address these issues by incorporating external knowledge, but suffer from retrieval errors, ineffective context integration, and high operational costs.<n>This paper presents the Hybrid.<n>Adaptive RAG (HyPA-RAG) system, designed for the AI legal domain, with NYC Local Law 144 (LL144) as the test case.
  arXiv  Detail & Related papers  (2024-08-29T16:11:20Z)
• Better Retrieval May Not Lead to Better Question Answering [59.1892787017522]
  A popular approach to improve the system's performance is to improve the quality of the retrieved context from the IR stage. We show that for StrategyQA, a challenging open-domain QA dataset that requires multi-hop reasoning, this common approach is surprisingly ineffective.
  arXiv  Detail & Related papers  (2022-05-07T16:59:38Z)

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.