Hugging Face Trending Papers August 19, 2026

When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models

Read the original on Hugging Face Trending Papers →

Aligned vision‑language models (VLMs) are designed to combine grounded visual reasoning with safe generation. The study finds that when safety constraints are applied, these models often abstain from answering questions that they could answer under default instruction, yet visual evidence continues to influence the decoding process. The authors show that safety‑induced abstention alters late‑stage hidden‑state dynamics, and that targeted interventions can restore grounded answering without retraining or changing visual inputs.

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 Hugging Face Trending Papers.

arXiv AI

Aug 6

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models

arXiv:2604. 14888v3 Announce Type: replace-cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear.

By Danae S\'anchez Villegas, Samuel Lewis-Lim, Nikolaos Aletras, Desmond Elliott

llms multimodal safety

arXiv Machine Learning

Sep 22

Seeing Through Conflicts: Improving Instruction Hierarchy Alignment in Vision-Language Models

arXiv:2609.22234v1 Announce Type: cross Abstract: Instruction hierarchy (IH) alignment teaches language models to prioritize higher-level instructions when inputs conflict. While studied primarily in...

By Nicholas Sansoterra, Zishuo Zheng, Sachin Kumar

llms agents reinforcement-learning multimodal safety

arXiv Machine Learning

Jun 8

Diagnosing Visual Ignorance in Vision-Language Models

arXiv:2606. 06890v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence.

By Runyu Zhou, Qi Zhang, Qixun Wang, Yisen Wang

llms multimodal benchmarks

arXiv AI

4d ago

Visual Dependence Does Not Imply Answerability: A Systematic Analysis of Answerability Signals in Frozen InstructBLIP

The study evaluates whether signals from a frozen vision‑language model, InstructBLIP, can reliably indicate answerability in visual question answering. Using a 10K subset of UNK‑VQA, the authors test predictive uncertainty, cross‑modal alignment, visual grounding, visual dependence, internal representations, and learned probes, finding that all signals yield weak discrimination (AUROC 0.50‑0.54). Even interventions that remove question‑relevant visual evidence or increase probe capacity do not substantially improve answerability detection, underscoring that visual dependence and related metrics are not robust proxies for answerability.

By Minjun Kim, Hyunmin Song, Changwon Lim

llms nlp multimodal benchmarks safety

Hugging Face Trending Papers

Jun 17

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.

llms benchmarks safety

arXiv Computation and Language

Aug 31

Steering Multimodal Large Language Models Decoding for Context-Aware Safety

The paper introduces Safety-aware Contrastive Decoding (SafeCoDe), a lightweight, model‑agnostic framework designed to improve context‑aware safety in Multimodal Large Language Models (MLLMs). SafeCoDe operates in two stages: a contrastive decoding step that highlights tokens sensitive to visual context by contrasting real and Gaussian‑noised images, and a global‑aware token modulation strategy that adjusts refusals based on scene‑level reasoning and predicted safety verdicts. Experiments across various MLLM architectures and safety benchmarks demonstrate that SafeCoDe consistently enhances context‑sensitive refusal behaviors while maintaining model helpfulness.

By Zheyuan Liu, Zhangchen Xu, Guangyao Dou, Xiangchi Yuan, Zhaoxuan Tan, Radha Poovendran, Meng Jiang

llms multimodal benchmarks safety