Mar 2026· arXiv.org· Vol abs/2603.23934· 1 citation· 62 references
Computer Science
Abstract
Large vision-language models (LVLMs) are increasingly being applied to multi-view image inputs captured from diverse viewpoints. Despite this growing use, current LVLMs often generate incorrect responses due to visual interference from non-target instances or viewpoints, a phenomenon we term multi-view hallucination (MVH). To systematically analyze this problem, we construct MVH-Bench, a benchmark comprising 4.8k question-answer pairs targeting two types of hallucination: cross-instance and cross-view. Empirical results show that MVH is prevalent across recent LVLMs. To address this issue, we propose Reference Shift Contrastive Decoding (RSCD), a training-free decoding technique that suppresses visual interference by generating negative logits through attention masking. Experiments on MVH-Bench with LLaVA-OneVision and Qwen2.5-VL demonstrate that RSCD improves performance by up to 25.7 and 94.8 points over existing hallucination mitigation methods, highlighting the effectiveness of RSCD.
Object Hallucination in large vision-language models (LVLMs), where models generate non-factual content about input images, remains a critical barrier to their reliability in real-world applications. Existing mitigation strategies can be categorized into training-based and training-free methods. Training-based methods...
Mehran Tamjidi, Hamidreza Dastmalchi, Ali Cheraghian et al.· 0 citations
This work studies hallucination from the perspective of dynamic representation shift during generation and proposes an online projection-based intervention on intermediate hidden states to suppress the hallucination-related directions, mitigating hallucinations while preserving language quality.
Xuan-Yu Yin, Xiao-Ye Qu, Wei Wei· Proceedings of the Thirty-Fi...· 0 citations
Large vision-language models (LVLMs) have recently achieved remarkable progress across multimodal tasks, yet object hallucination remains a persistent challenge where models generate descriptions inconsistent with the visual input. Recent work mitigates hallucinations through training-free representation editing, typic...
EviAnchor is proposed, a training-free and single-branch inference framework that preserves and reactivates visual evidence throughout generation in large vision-language models and demonstrates consistent improvements in visual grounding.
Sihang Jia, Shuliang Liu, Song-Bo Yang et al.· 0 citations
Multiple object hallucination, where large vision-language models (LVLMs) generate objects not supported by the visual input, is a persistent challenge caused by visual uncertainty during decoding. Existing methods reduce hallucinations using contrastive signals, but they rely on heuristics and lack principled control...
A multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo Dropout uncertainty quantification, and temperature-scaled calibration for response-level hallucination detection is presented.
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.
