相关论文: Vulnerability Mitigation for Safety-Aligned Langua…

Despite advances in large language model capabilities in recent years, a large gap remains in their capabilities and safety performance for many languages beyond a relatively small handful of globally dominant languages. This paper provides…

This paper explores the role and challenges of Artificial Intelligence (AI) algorithms, specifically AI-based software elements, in autonomous driving systems. These AI systems are fundamental in executing real-time critical functions in…

Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We…

Bias originates from both data and algorithmic design, often exacerbated by traditional fairness methods that fail to address the subtle impacts of protected attributes. This study introduces an approach to mitigate bias in machine learning…

Large language models (LLMs) are being deployed across the Global South, where everyday use involves low-resource languages, code-mixing, and culturally specific norms. Yet safety pipelines, benchmarks, and alignment still largely target…

We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Our assessment of ten leading models across five scenarios…

Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI.…

Ensuring that Large Language Models (LLMs) adhere to safety principles without refusing benign requests remains a significant challenge. While OpenAI introduces deliberative alignment (DA) to enhance the safety of its o-series models…

Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…

As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…

Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, a phenomenon attracting growing clinical and public concern. Yet most empirical work evaluates model safety in brief…

As Large Language Models (LLMs) are increasingly deployed in real-world applications, balancing helpfulness and safety has become a central challenge. A natural approach is to incorporate safety constraints into Reinforcement Learning from…

The issue of fairness in machine learning models has recently attracted a lot of attention as ensuring it will ensure continued confidence of the general public in the deployment of machine learning systems. We focus on mitigating the harm…

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…

Recently, major AI providers such as Google and OpenAI have introduced Finetuning-as-a-Service (FaaS), which allows users to customize Large Language Models (LLMs) using their own data. However, this service is vulnerable to safety…

Current safety alignment for large language models(LLMs) continues to present vulnerabilities, given that adversarial prompting can effectively bypass their safety measures.Our investigation shows that these safety mechanisms predominantly…

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial. Current safety alignment methods, such as supervised fine-tuning and…

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

The integration of vision-language-action (VLA) models into embodied AI (EAI) robots is rapidly advancing their ability to perform complex, long-horizon tasks in humancentric environments. However, EAI systems introduce critical security…