Author

Ding-Yang Lin

h-index 2 View on Semantic Scholar

We have 2 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#small language model Preprint Sep 2026

Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs

Findings show that configuration changes can affect how models use information they can still read, and attention interventions in LLaVA-NeXT suggest that configuration changes can weaken the use of readable information during answering.

Ding-Yang Lin, Ying-Feng Luo, Cheng-Long Wang et al. · 0 citations

#artificial intelligence Mar 2026

AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models

This work introduces AdaCultureSafe, a dataset designed to jointly evaluate cultural safety and knowledge and proposes a knowledge-grounded method that elicits internal cultural knowledge in LLMs during response generation, demonstrating that this approach effectively improves cultural safety.

Hankun Kang, Ding-Yang Lin, Zhi-Rong Liao et al. · arXiv.org · 0 citations