Related papers: Steering Without Side Effects: Improving Post-Depl…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically…

Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often…

Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…

Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLMs (MLLMs); furthermore, existing steering techniques, such…

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving benign utility.…

Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited. This study aims to understand and enhance the…

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…

Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers…

The ability to achieve long-term goals is a key challenge in the current development of large language models (LLMs). To address this, pre-trained LLMs can be fine-tuned with reinforcement learning (RL) to explore solutions that optimize a…

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregressive nature, but such approaches typically require…

Despite impressive breadth, LLMs still rely on explicit reasoning instructions or static, one-fits-all steering methods, leaving a gap for adaptive, instruction-free reasoning amplification. We present Prototype-Based Dynamic Steering…

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to generate harmful content, posing serious risks to model safety and trustworthy usage. Recent…

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…