arXiv:2608.22228 · v2
Prompt-Based Abstention Fails Under Misleading Context: A Controlled Study of Small Frozen RAG Models
摘要
Missing and misleading evidence are not the same problem in retrieval-augmented generation (RAG), but prompt-based abstention treats them alike. Small frozen models abstain when context is absent, not when it is misleading. We introduce GRAB-RAG (Graded Abstention Benchmark for Retrieval-Augmented Generation), a paired benchmark that tests the same questions across four context conditions (supportive, degraded, missing, and misleading) in Natural Questions and HotpotQA. In the misleading condition, we edit a gold passage to support a wrong answer and place it among other retrieved passages. We test five abstention policies on three small frozen models (3.8B-8B) across two English QA benchmarks. Models abstain reliably when evidence is missing, but under explicit abstention prompting still answer 41.6% of misleading questions, with 63% of those answers echoing the planted wrong entity. Chain-of-thought provides little additional benefit. A generator-side conflict check cuts the rate to 13.3% but discards many correct answers, while a natural language inference (NLI) verifier recovers that coverage but fails when parametric memory and the misleading passage agree on the same wrong answer. Prompt-based abstention asks whether context is sufficient, not whether it is correct. The two-pass checks are diagnostic baselines, not deployable mitigations.
作者备注:19 pages. Published in AACL-IJCNLP 2026 (Main Conference). Code and data: https://github.com/andre44s/grab-rag
期刊信息:Proceedings of IJCNLP-AACL 2026 (Volume 1: Long Papers), pages 3368-3386