How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment
State-aligned distortion has been documented in China-origin text-based large language models (LLMs), but whether, and in what form, it arises in multimodal systems has not been systematically examined. We construct a balanced benchmark of 200 core entries spanning ten politically sensitive topics, plus a seven-variant visual-abstraction probe, and run nine vision-language models (VLMs), seven China-origin and two non-China, across four elicitation paradigms and two prompt languages, yielding 21
Record details
Published: 12 August 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 13 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Faithful or evasive? An empirical study on translation norm preferences of Chinese and American LLMs in Chinese official political and policy discourse
Frontiers in Artificial Intelligence · 10 August 2026
Joint Text-Audio Alignment for EEG-to-Text Decoding in Chinese Speech Production and Perception
arXiv · 28 July 2026
Geopolitical alignment: Endorsement effects in large language models
arXiv · 10 July 2026
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
arXiv · 13 June 2026
AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task
arXiv · 2 June 2026
Brain-LLM Alignment Tracks Training Data, Not Typology
arXiv · 21 May 2026
How to cite this record
ethics.ai (12 August 2026), “How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment,” evidence record 18786, https://ethics.ai/record/18786 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.