arXiv AI
From Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language 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
Oct 13
From Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language Models
Large vision-language models often exhibit object hallucination, generating claims that are not supported by the input image. To mitigate this issue, we propose Evidence-Guided Visual Claim Admission...
arXiv AI
Jul 7
SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering
arXiv:2607. 04163v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answering.
arXiv AI
Aug 25
PatchGate: Narrowing the Verbalization Gap with Intrinsic Object Inventories in Frozen Vision-Language Models
arXiv:2608.21819v1 Announce Type: cross Abstract: Reliable image captioning in Vision-Language Models (VLMs) requires captions to be both precise and complete, avoiding unsupported object mentions wh...
arXiv Machine Learning
Aug 6
DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models
arXiv:2608. 04496v1 Announce Type: cross Abstract: Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottleneck for efficient inference.
Hugging Face Trending Papers
Oct 22
Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning
The paper investigates why long image captions often fail, arguing that failure depends not just on what facts are mentioned but also on where they appear in the caption. It introduces a position‑aware rubric that breaks down dense human references into atomic visual claims, evaluates generated captions against these claims, and identifies two distinct failure modes: unsupported specificity in the middle and vague, non‑evidential language at the end. Building on this diagnosis, the authors propose PAGER, a reinforcement‑learning objective that provides separate rewards for supported middle evidence, evidence‑bearing tail continuation, claim coverage, and length control, leading to improved position‑wise grounding and caption preference on detailed‑caption benchmarks.
arXiv AI
Jul 21
Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain
arXiv:2603. 21693v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have shown strong potential for medical Visual Question Answering (VQA), yet they remain prone to hallucinations, defined as generating responses that contradict the input image, posing serious risks in clinical settings.