Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Uncovering Uncontrolled Repetition through Residual Stream Dynamics
Yuanhe Zhang, Xinyao Zhou, Haoran Gao +5
Uncontrolled repetition can prolong autoregressive generation in large language models (LLMs) and enable resource consumption attacks. Prior analyses of repetitive generation have…
cs.CL2026
From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
Xinyue Wang, Yuanhe Zhang, Zhengshuo Gong +6
The enhanced capabilities of LLM-based agents come with an emergency for model planning and tool-use abilities. Attributing to helpful-harmless trade-off from LLM alignment, agents…