1 citations · 1 across the 7 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.AI2026
Steered LLM Activations are Non-Surjective
Aayush Mishra, Daniel Khashabi, Anqi Liu
Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in int…
cs.AI2026
LoopGuard: Breaking Self-Reinforcing Attention Loops via Dynamic KV Cache Intervention
Dongjie Xu, Hao Wu, Weijie Shi +7
Through systematic experiments on long-context generation, we observe a damaging failure mode in which decoding can collapse into persistent repetition loops. We find that this deg…
cs.LG2026
Process Supervision of Confidence Margin for Calibrated LLM Reasoning
Liaoyaqi Wang, Chunsheng Zuo, William Jurayj +2
Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward of…