{"ID":5937658,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T10:32:23.333128278Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04223","arxiv_id":"2607.04223","title":"Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)","abstract":"Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why. To close this gap, we introduce Grounding-Aware Sensitivity by Perturbation (GASP), a span-level detector that scores each answer sentence by how strongly its likelihood depends on the retrieved evidence, a quantity we term grounding sensitivity. GASP holds the answer fixed and re-scores it under the full context, under no context, and with each chunk removed, then measures the log-likelihood drops and Jensen-Shannon divergences (JSD). The likelihood of a grounded sentence collapses once its supporting passage is removed, whereas a hallucinated sentence is almost unaffected, a contrast we interpret by casting decoding as a random nonlinear iterated function system (RNIFS). We evaluate GASP on three benchmarks (RAGTruth, TofuEval, RAGBench) with three instruction-tuned scorers from two model families (Qwen2.5-0.5B, Qwen2.5-1.5B, and SmolLM2-1.7B) under a leakage-clean protocol. On RAGTruth it reaches a response-level area under the ROC curve (AUC) of about 0.73 and a span-level AUC of about 0.67, improving significantly over perplexity and by clear margins over length, whole-context natural language inference (NLI), and self-consistency baselines. The only baseline competitive at the span level is a well-configured chunk-level entailment verifier, which requires a separate model, whereas a training-free threshold on the grounding features matches the trained classifier without labeled data and serves as the default detector. Beyond RAGTruth, the signal transfers to TofuEval but not to short-answer question answering in RAGBench, showing GASP is best suited to outputs constructed from the retrieved context rather than answers recoverable from parametric knowledge.","short_abstract":"Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why. To close this gap, we introduce Grounding-Aware Sensitivity by Perturbation (GASP), a span-level detector that scores...","url_abs":"https://arxiv.org/abs/2607.04223","url_pdf":"https://arxiv.org/pdf/2607.04223v1","authors":"[\"Mohamed Aly Bouke\"]","published":"2026-07-05T10:35:30Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"RAG\",\"Large Language Model\"]","has_code":false}