2 papers
cs.CY2025
Position: The Pitfalls of Over-Alignment: Overly Caution Health-Related Responses From LLMs are Unethical and Dangerous
Wenqi Marshall Guo, Yiyang Du, Heidi J. S. Tworek +1
Large Language Models (LLMs) are usually aligned with "human values/preferences" to prevent harmful output. Discussions around the alignment of Large Language Models (LLMs) general…
cs.CV2025
LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset
Wenqi Guo, Yiyang Du, Shan Du
Gas leakage poses a significant hazard that requires prevention. Traditionally, human inspection has been used for detection, a slow and labour-intensive process. Recent research h…