相关论文: Controllable and explainable personality sliders f…

The advent of large language models (LLMs) has revolutionized natural language processing, enabling the generation of coherent and contextually relevant human-like text. As LLMs increasingly powerconversational agents used by the general…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

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…

Large Language Models increasingly mediate high-stakes interactions, intensifying research on their capabilities and safety. While recent work has shown that LLMs exhibit consistent and measurable synthetic personality traits, little is…

The task of persona-steered text generation requires large language models (LLMs) to generate text that reflects the distribution of views that an individual fitting a persona could have. People have multifaceted personas, but prior work on…

Psychological assessment tools have long helped humans understand behavioural patterns. While Large Language Models (LLMs) can generate content comparable to that of humans, we explore whether they exhibit personality traits. To this end,…

Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…

The alignment of large language models (LLMs) is crucial not only for unlocking their potential in specific tasks but also for ensuring that responses meet human expectations and adhere to safety and ethical principles. Current alignment…

Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF…

With the rapid advancement of large language models (LLMs), their deployment in real-world applications has become increasingly widespread. LLMs are expected to deliver robust performance across diverse tasks, user preferences, and…

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

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…

Large language models (LLMs) have become increasingly proficient at simulating various personality traits, an important capability for supporting related applications (e.g., role-playing). To further improve this capacity, in this paper, we…

Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure. Existing training-time alignment methods…

The rapid advancement of large language models (LLMs) has led to growing interest in using synthetic data to train future models. However, this creates a self-consuming retraining loop, where models are trained on their own outputs and may…

Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle distinct semantic features. In this paper, we investigate attention query activations as a…

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…

This paper presents a novel approach to aligning large language models (LLMs) with individual human preferences, sometimes referred to as Reinforcement Learning from \textit{Personalized} Human Feedback (RLPHF). Given stated preferences…

While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even…

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness. Existing methods for achieving this alignment often…