HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models
Diffusion large language models generate text through multi-step denoising, where hallucination signals may emerge throughout the trajectory rather than only in the final output. Existing detectors mainly rely on output uncertainty or coarse trace statistics, which often fail to capture the richer hidden dynamics of D-LLMs. We propose HIVE, a hidden-evidence verification framework that extracts compressed hidden evidence from denoising trajectories, selects informative step-layer evidence, and conditions a verifier language model on the selected evidence through prefix embeddings. HIVE produces both a continuous hallucination score from verifier decision logits and structured verification outputs, including hallucination types, evidence pairs, and short rationales. Across two D-LLMs and three QA benchmarks, HIVE consistently outperforms eight strong baselines and achieves up to 0.9236 AUROC and 0.9537 AUPRC. Ablation studies further confirm the importance of hidden-evidence conditioning, learned evidence selection, two-stream evidence representation, and step-layer embeddings. These results suggest that selected hidden evidence from denoising trajectories provides a stronger and more usable hallucination signal than output-only uncertainty or coarse trace statistics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hallucination Detection and Correction in Medical VLMs via Counter-Evidence Verification
Vision-Language models (VLMs) reliability in medical diagnosis is challenged by trust-undermining hallucinations. Existing hallucination detection approaches mainly focus on identifying factual inconsistencies between ge…
Medical Report GenerationMedical DiagnosisVisual GroundingHIVE: Understanding Post-Hallucination Reasoning in Vision Language Models
Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence. Prior work mainly focuses on detecting or suppressing hallucination…
Multimodal ReasoningCuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification
Discharge summaries require extracting critical information from lengthy electronic health records (EHRs), a process that is labor-intensive when performed manually. Large language models (LLMs) can improve generation ef…
Critical Confabulation: Can LLMs Hallucinate for Social Good?
LLMs hallucinate, yet some confabulations can have social affordances if carefully bounded. We propose critical confabulation (inspired by critical fabulation from literary and social theory), the use of LLM hallucinatio…
E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucination evaluations are mostly claim-centric; they assess whether generated statements are supported, b…