arXiv AI
MEND: Label-Free Detection, Localisation, and Correction of Latent Hallucination in World Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Jun 25
Hallucination in World Models is Predictable and Preventable
Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the ground-truth dynamics. We hypothesize that hallucination concentrates in low-coverage regions of the state-action space, where lightweight data-centric signals can both detect it and guide mitigation.
arXiv Machine Learning
Jun 26
Hallucination in World Models is Predictable and Preventable
arXiv:2606. 27326v1 Announce Type: new Abstract: Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the ground-truth dynamics.
arXiv AI
1d ago
External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing
The paper proposes a hidden‑state probing method for detecting hallucinations at the span level in large language model outputs, moving beyond token‑wise binary classification. By examining layer‑wise activation patterns, the approach identifies the exact onset and continuation tokens of hallucinations, achieving higher precision‑recall AUC than random baselines despite class imbalance. Additionally, the authors introduce a cross‑model detection framework where one model observes another’s internal representations, showing that an external observer can match or surpass the generator’s own self‑detection of hallucination onsets, even when the observer is smaller.
arXiv Computer Vision
Sep 3
Detecting Object Hallucinations in Large Vision-Language Models via Cross-Modal Attention Drifts and Mask-Based Verification
The paper introduces CADMP, a lightweight framework for detecting object hallucinations in large vision‑language models. CADMP measures cross‑modal attention drift between adjacent layers and verifies predictions by masking visually relevant regions, combining these signals to identify hallucinated outputs. Experiments on multiple benchmarks show that CADMP achieves competitive detection performance, and ablation studies confirm the complementary roles of attention drift and mask‑based verification.
Hugging Face Trending Papers
Sep 2
Detecting Object Hallucinations in Large Vision-Language Models via Cross-Modal Attention Drifts and Mask-Based Verification
Despite recent advances in large vision-language models (LVLMs), object hallucination remains a major barrier to their reliable deployment. Existing detection methods often characterize visual groundi...
arXiv AI
Jun 8
MACD: Model-Aware Contrastive Decoding via Counterfactual Data
arXiv:2602. 01740v3 Announce Type: replace Abstract: Video language models (Video-LLMs) are prone to hallucinations, generating plausible but ungrounded content when visual evidence is weak, ambiguous, or biased.