Related papers: DSO: Direct Steering Optimization for Bias Mitigat…

Large Language Models (LLMs) have emerged as promising solutions for a variety of medical and clinical decision support applications. However, LLMs are often subject to different types of biases, which can lead to unfair treatment of…

A variety of recent methods guide large language model outputs via the inference-time addition of steering vectors to residual-stream or attention-head representations. In contrast, we propose to inject steering vectors directly into the…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Selection bias poses a critical challenge for fairness in machine learning, as models trained on data that is less representative of the population might exhibit undesirable behavior for underrepresented profiles. Semi-supervised learning…

Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models,…

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Large Language Models (LLMs) have demonstrated remarkable performance across various domains, motivating researchers to investigate their potential use in recommendation systems. However, directly applying LLMs to recommendation tasks has…

Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to…

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization…

Direct Preference Optimization (DPO) has emerged as an effective approach for mitigating hallucination in Multimodal Large Language Models (MLLMs). Although existing methods have achieved significant progress by utilizing vision-oriented…

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Vision-Language Models (VLMs) and generative image models have achieved remarkable performance across multimodal tasks, yet their robustness and fairness under input transformations remain insufficiently explored. This work investigates…

Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to their simplicity, efficiency, and stability. However, the…

In recent years, we have witnessed significant progress in emerging deep learning models, particularly Large Language Models (LLMs) and Vision-Language Models (VLMs). These models have demonstrated promising results, indicating a new era of…

General-purpose large language models (LLMs) have demonstrated remarkable generative and reasoning capabilities but remain limited in healthcare and caregiving applications due to two key deficiencies: factual unreliability and a lack of…

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…

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the…

Long-term fluid dynamics forecasting is a critically important problem in science and engineering. While neural operators have emerged as a promising paradigm for modeling systems governed by partial differential equations (PDEs), they…

Vision-language models (VLMs) have demonstrated remarkable performance across a wide range of computer-vision tasks, sparking interest in their potential for digital health applications. Here, we apply VLMs to two fundamental challenges in…