Related papers: BeaverTails: Towards Improved Safety Alignment of …

Fine-tuning on task-specific data to boost downstream performance is a crucial step for leveraging Large Language Models (LLMs). However, previous studies have demonstrated that fine-tuning the models on several adversarial samples or even…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

This report explores the convergence of large language models (LLMs) and cybersecurity, synthesizing interdisciplinary insights from network security, artificial intelligence, formal methods, and human-centered design. It examines emerging…

Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to…

Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the…

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses,…

As large language models (LLMs) become integral to safety-critical applications, ensuring their robustness against adversarial prompts is paramount. However, existing red teaming datasets suffer from inconsistent risk categorizations,…

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal,…

Studying how people interact with large language models (LLMs) in real-world scenarios is increasingly important due to their widespread use in various applications. In this paper, we introduce LMSYS-Chat-1M, a large-scale dataset…

The rapid proliferation of large language models (LLMs) in applications targeting children and adolescents necessitates a fundamental reassessment of prevailing AI safety frameworks, which are largely tailored to adult users and neglect the…

As large vision-language models (LVLMs) evolve rapidly, the demand for high-quality and diverse data to align these models becomes increasingly crucial. However, the creation of such data with human supervision proves costly and…

Large language models (LLMs) are increasingly explored as scalable tools for mental health counseling, yet evaluating their safety remains challenging due to the interactional and context-dependent nature of clinical harm. Existing…

As Large Language Models (LLMs) increasingly power applications used by children and adolescents, ensuring safe and age-appropriate interactions has become an urgent ethical imperative. Despite progress in AI safety, current evaluations…

Large Language Models (LLMs) have demonstrated wide-ranging applications across various fields and have shown significant potential in the academic peer-review process. However, existing applications are primarily limited to static review…

Despite strong performance in medical question-answering, the clinical adoption of Large Language Models (LLMs) is critically hampered by their opaque 'black-box' reasoning, limiting clinician trust. This challenge is compounded by the…

Fine-tuning on instruction data has been widely validated as an effective practice for implementing chat language models like ChatGPT. Scaling the diversity and quality of such data, although straightforward, stands a great chance of…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Long-form question answering (LFQA) demands nuanced evaluation of multi-sentence explanatory responses, yet existing metrics often fail to reflect human judgment. We present LFQA-HP-1M, a large-scale dataset comprising 1.3M human pairwise…

Data filtering strategies are a crucial component to develop safe Large Language Models (LLM), since they support the removal of harmful contents from pretraining datasets. There is a lack of research on the actual impact of these…

Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this…