相关论文: Programming Refusal with Conditional Activation St…

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

Accurate vision-based action recognition is crucial for developing autonomous robots that can operate safely and reliably in complex, real-world environments. In this work, we advance video-based recognition of indoor daily actions for…

We present CREST, an approach for causal reasoning in simulation to learn the relevant state space for a robot manipulation policy. Our approach conducts interventions using internal models, which are simulations with approximate dynamics…

Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and…

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key…

Large language models can resist task-misaligned activation steering during inference, sometimes recovering mid-generation to produce improved responses even when steering remains active. We term this Endogenous Steering Resistance (ESR).…

Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks, particularly because their vision capabilities create new vulnerabilities. Existing defenses, such as input preprocessing,…

Capturing the evolving trends of user interest is important for both recommendation systems and advertising systems, and user behavior sequences have been successfully used in Click-Through-Rate(CTR) prediction problems. However, if the…

Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can distribute backdoored checkpoints that behave normally under…

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

Activation steering has emerged as a promising alternative for controlling language-model behavior at inference time by modifying intermediate representations while keeping model parameters frozen. However, large-scale evaluations such as…

Chain-of-thought (CoT) prompting has been extended to large audio-language models (LALMs) to elicit reasoning, yet enhancing its effectiveness without training remains challenging. We study inference-time model steering as a training-free…

We propose cache steering, a lightweight method for implicit steering of language models via a one-shot intervention applied directly to the key-value cache. To validate its effectiveness, we apply cache steering to induce chain-of-thought…

The use of reinforcement learning (RL) methods to support health behavior change via personalized and just-in-time adaptive interventions is of significant interest to health and behavioral science researchers focused on problems such as…

As Large Langue Models have been shown to memorize real-world facts, the need to update this knowledge in a controlled and efficient manner arises. Designed with these constraints in mind, Knowledge Editing (KE) approaches propose to alter…

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In this work, we…

Reinforcement learning (RL) is increasingly being used in the healthcare domain, particularly for the development of personalized health adaptive interventions. Inspired by the success of Large Language Models (LLMs), we are interested in…

Large Language Models (LLMs) as clinical agents require careful behavioral adaptation. While adept at reactive tasks (e.g., diagnosis reasoning), LLMs often struggle with proactive engagement, like unprompted identification of critical…

The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering methods rely on static control vectors that fail to adapt…