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.

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 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 Computer Vision

Aug 31

Dynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models

The paper introduces Dynamic Alignment Compensation (DAC), a training‑free inference‑time technique designed to reduce hallucinations in Large Vision‑Language Models (LVLMs). DAC monitors cross‑modal representation drift across decoder layers and generation steps, applying lightweight residual compensation through Layer‑wise Semantic Compensation and Sequential Semantic Correction. Experiments on nine multimodal benchmarks across various LVLM backbones demonstrate that DAC consistently lowers hallucination rates while preserving overall performance.

By Kairong Yu, Zixin Zhu, Le Yu, Hongwei Wang

llms multimodal benchmarks safety

arXiv AI

Sep 1

Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization

arXiv:2608.29924v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) are prone to hallucinations: they fluently describe objects, attributes, and scenes that are not in the image. W...

By Aditi Sarker, Rafi Ibn Sultan, Hui Zhu, Dongxiao Zhu, Prashant Khanduri

llms rag fine-tuning multimodal safety

arXiv Machine Learning

Sep 17

Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models

The paper proposes using the temporal volatility of internal attention mechanisms—measured by an unsupervised attention dispersion metric—as a diagnostic signal for hallucinations in large language models. It demonstrates that spikes in attention entropy within intermediate layers correlate with reasoning breakdowns, and shows statistically significant AUC improvements of up to +0.076 over output-based baselines on GSM8K and MATH-500 benchmarks using the Qwen2.5 model family.

By Shardul P. More, Tanuja S. Pawar

llms benchmarks safety

One email a morning, machine-written

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

Dynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models

Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization

Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models