← Back to all news
arXiv Computer Vision By Mehrdad Fazli, Sina Mansouri, Mohit Marvania, Ziwei Zhu

Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods

Read the original on arXiv Computer Vision →

The paper examines six inference-time hallucination mitigation methods applied to three large vision-language models across four benchmarks, including MMStar. It finds that reducing hallucination rates often comes at the cost of lower informativeness—such as decreased object recall, visual coverage, and response detail—and that gains on hallucination benchmarks do not consistently translate to improved performance on fine-grained perception and reasoning tasks. The authors argue that current evaluation protocols may overstate progress by favoring conservative generation, and propose that hallucination mitigation should be assessed as a trade-off among faithfulness, informativeness, and overall capability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Sep 15

Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations

The article surveys hallucination issues in Large Vision‑Language Models (LVLMs), a type of multimodal foundation model that blends visual data with large language models. It categorizes hallucination causes into model architecture and data quality, presents a taxonomy of mitigation strategies, and critically evaluates existing evaluation benchmarks from both discriminative and generative viewpoints. The survey also outlines open challenges and future research directions to improve LVLM reliability and trustworthiness.

By Yinghao Guo, Wei Lan, Wenyi Chen, Qingfeng Chen, Shichao Zhang, Shirui Pan, Huiyu Zhou, Yi Pan
llmsmultimodalbenchmarkssafetydata-engineering
More like this →
arXiv AI
Jun 16

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

arXiv:2603. 24058v2 Announce Type: replace-cross Abstract: Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous driving and medical image analysis.

By Han Sun, Qin Li, Peixin Wang, Min Zhang
llmsagentsroboticsmultimodalbenchmarkssafety
More like this →
arXiv AI
Oct 9

Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations

The paper introduces AIMS (Adaptive Information Multi-source Steering), a lightweight, training‑free framework that dynamically balances visual, prefilled textual, and generated contexts during decoding to reduce hallucinations in Large Vision‑Language Models (LVLMs). By constructing compact prototypes for each context domain and estimating their affinities with the current query, AIMS assigns head‑wise steering weights that guide adaptive context integration without extra training or forward passes. Experiments across multiple LVLMs and decoding strategies show that AIMS effectively mitigates object hallucination while preserving general multimodal performance.

By Shuran Ma, JiaLe Li, Yuxin Dong, Shan Zheng, Qingyun Jiang, Xiang Chen, Qi Zhu, Deyi Ji, Yifan Yang, Jianfeng Pan, Yu Tian, Xue Yang
llmsmultimodalsafety
More like this →