相关论文: Red Teaming Language Models to Reduce Harms: Metho…

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. Existing AI safety approaches often rely on costly human evaluation…

Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red…

The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive…

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Large language models (LLMs) used in medical applications are known to be prone to exhibiting biased and unfair patterns. Prior to deploying these in clinical decision-making, it is crucial to identify such bias patterns to enable effective…

Large language models (LLMs) have enhanced our ability to rapidly analyze and classify unstructured natural language data. However, concerns regarding cost, network limitations, and security constraints have posed challenges for their…

Large language models (LLMs) hold great potential for many natural language applications but risk generating incorrect or toxic content. To probe when an LLM generates unwanted content, the current paradigm is to recruit a \textit{red team}…

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models (LLMs) offer promising capabilities for enhancing threat…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

The exploitation of large language models (LLMs) for malicious purposes poses significant security risks as these models become more powerful and widespread. While most existing red-teaming frameworks focus on single-turn attacks,…

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

In this paper, we explore the feasibility of leveraging large language models (LLMs) to automate or otherwise assist human raters with identifying harmful content including hate speech, harassment, violent extremism, and election…

Reinforcement Learning from Human feedback (RLHF) has become a powerful tool to fine-tune or train agentic machine learning models. Similar to how humans interact in social contexts, we can use many types of feedback to communicate our…

Reasoning language models (RLMs) excel at complex tasks by leveraging a chain-of-thought process to generate structured intermediate steps. However, language mixing, i.e., reasoning steps containing tokens from languages other than the…

Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the complex, longitudinal risks inherent in therapeutic dialogue. We introduce an evaluation framework…

Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts,…

Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are…

Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of…