3 papers
cs.LG2026
Less Approximates More: Harmonizing Performance and Confidence Faithfulness via Hybrid Post-Training for High-Stakes Tasks
Haokai Ma, Lee Yan Zhen, Gang Yang +3
Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause severe real-world harm, bringing the previously overlooked…
cs.CR2026
TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
Mengyao Du, Han Fang, Haokai Ma +4
Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit…
cs.LG2025
Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier
Mengyao Du, Gang Yang, Han Fang +2
The widespread adoption of natural language processing techniques has led to an unprecedented growth of text classifiers across the modern web. Yet many of these models circulate w…