arXiv AI June 9, 2026 By Abhivansh Gupta, Simardeep Singh, Advika Sinha, Shreyansh Modi, Akshat Tomar

How Many Counterfactuals Does It Take? Probing VLM Hallucinations Through Circuits and Causal Effects

arXiv:2606. 08777v1 Announce Type: cross Abstract: Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a principled understanding of how robust such predictions are under counterfactual perturbations.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

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.

By Qixin Xiao, Kun Zhou

llms safety

arXiv AI

Aug 5

UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space

arXiv:2608. 03817v1 Announce Type: cross Abstract: Large vision--language models (LVLMs) demonstrate strong multimodal reasoning capabilities but remain prone to hallucination, where model predictions are not grounded in visual evidence.

By Amir Mohammad Ezzati, Kiyan Rezaee, Bardiya Kariminia, Mohamad Amin Yousefi, Asal Mohammadjafari Mamaqani, Behrad Samimi, Mohammad Hossein Rohban

llms multimodal benchmarks safety

arXiv Machine Learning

Jun 29

On the Effect of Uncertainty on Layer-wise Inference Dynamics

arXiv:2507. 06722v2 Announce Type: replace-cross Abstract: Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations.

By Sunwoo Kim, Haneul Yoo, Alice Oh

llms safety

arXiv AI

Jul 17

Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions

arXiv:2607. 14499v1 Announce Type: new Abstract: Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain.

By Yijiang Li, Huiqi Zou, Bingyang Wang, Ziang Xiao

llms multimodal benchmarks safety

arXiv AI

Jul 9

HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models

arXiv:2607. 07507v1 Announce Type: cross Abstract: Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence.

By Feng He, Zhenting Wang, Qifan Wang, Qiang Guan, Dongfang Liu, Ruixiang Tang, Qiankun Li

llms multimodal safety

arXiv AI

Jun 29

Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding

arXiv:2606. 27596v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) exhibit sophisticated reasoning but remain susceptible to object hallucination.

By Liu Yu, Can Chen, Ping Kuang, Zhikun Feng, Fan Zhou, Gillian Dobbie

llms multimodal benchmarks safety

Related stories

MACD: Model-Aware Contrastive Decoding via Counterfactual Data

UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space

On the Effect of Uncertainty on Layer-wise Inference Dynamics

Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions

HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models

Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding