6 accepted papers
Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tuning, current methods are susceptible to overfitting and often underperform, sometimes generating unnatural outputs. We h…
Recently, *steering vectors (SVs)* have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effective than optimization-free ones. However, current approaches to fine-tuned SVs suffer from two limitations. First, th…
Large language models (LLMs) can output sensitive information, which has emerged as a novel safety concern. Previous works focus on structured sensitive information (e.g. personal identifiable information). However, we notice that sensitive information can also be at semantic level, i.e. semantic s…
The risk of harmful contents generated by large language models (LLMs) becomes a critical concern. This paper systematically evaluates and enhances LLMs’ capability to perform course-correction, , the model can steer away from generating harmful content autonomously. First, we introduce the C2-Eval…
Explaining deep models in a human-understandable way has been explored by many works that mostly explain why an input causes a corresponding prediction (ie., Why P?). However, seldom they could handle those more complex causal questions like "why P rather than Q?" and "why one is P while another is…
Deep image inpainting aims to restore damaged or missing regions in an image with realistic contents. While having a wide range of applications such as object removal and image recovery, deep inpainting techniques also have the risk of being manipulated for image forgery. A promising countermeasure…