arXiv AI June 3, 2026 By Mingkuan Zhao, Wentao Hu, Tianchen Huang, Yuheng Min, Suquan Chen, Yide Gao, Yanbo Zhai, Shuangyong Song, Xuelong Li

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization

Read the original on arXiv AI →

arXiv:2606. 03022v1 Announce Type: cross Abstract: Hallucination in Large Language Models (LLMs), characterized by the generation of content inconsistent with contextual facts or logical constraints -- remains a persistent challenge for reliable deployment.

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

arXiv AI

Jun 10

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding

arXiv:2606. 09859v1 Announce Type: cross Abstract: MLLMs frequently hallucinate objects inconsistent with visual inputs.

By Yingxuan Zhuang, Jingxiao Yang, Miao Pan, Cheng Tan, Yuxiang Cai, Siwei Tan, Chen Zhi, Xuhong Zhang, Jianwei Yin, Jintao Chen

multimodal safety

arXiv Machine Learning

Jun 2

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time

arXiv:2606. 01923v1 Announce Type: cross Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations.

By Mingkuan Zhao, Yide Gao, Wentao Hu, Suquan Chen, Tianchen Huang, Zhenhua An, Zetao Chang, Xiayu Sun, Yuheng Min

llms efficiency safety

arXiv AI

Jun 24

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

arXiv:2605. 08245v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input.

By Harshvardhan Saini, Samyak Jha, Yiming Tang, Dianbo Liu

llms rag agents fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Aug 11

Wiener Representation Filtering for VLM Hallucination Suppression

arXiv:2608. 08167v1 Announce Type: cross Abstract: Vision-language models (VLMs) excel at open-ended captioning and visual QA but often describe objects, attributes, or relations absent from the image, a phenomenon known as object hallucination.

By Ameen Ali, Tamim Zoabi, Lidor Brami, Lior Wolf

llms diffusion fine-tuning multimodal benchmarks safety

arXiv AI

Jul 28

Disentangling Semantic Attention from Structural Bias in the Attention Manifold

arXiv:2607. 24017v1 Announce Type: cross Abstract: The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws.

By Pengkun Jiao, Bin Zhu, Jingjing Chen, Yu-gang Jiang

llms multimodal benchmarks 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

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

Wiener Representation Filtering for VLM Hallucination Suppression

Disentangling Semantic Attention from Structural Bias in the Attention Manifold

Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding