3 papers
cs.LG2026
PreAct-Bench: Benchmarking Predictive Monitoring in LLMs
Hainiu Xu, Italo Luis da Silva, Jiangnan Ye +7
Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective. While existing safety rese…
cs.CL2025
Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models
Shuxun Wang, Qingyu Yin, Chak Tou Leong +2
Repetition curse is a phenomenon where Large Language Models (LLMs) generate repetitive sequences of tokens or cyclic sequences. While the repetition curse has been widely observed…
cs.AI2025
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
Qingyu Yin, Chak Tou Leong, Linyi Yang +7
Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain…