5 papers
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…
Always Tell Me The Odds: Fine-grained Conditional Probability Estimation
Liaoyaqi Wang, Zhengping Jiang, Anqi Liu +1
We present a state-of-the-art model for fine-grained probability estimation of propositions conditioned on context. Recent advances in large language models (LLMs) have significant…
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…
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…
Conformal Linguistic Calibration: Trading-off between Factuality and Specificity
Zhengping Jiang, Anqi Liu, Benjamin Van Durme
Language model outputs are not always reliable, thus prompting research into how to adapt model responses based on uncertainty. Common approaches include: \emph{abstention}, where…