相关论文: When Choices Become Risks: Safety Failures of Larg…

Open-weight models provide researchers and developers with accessible foundations for diverse downstream applications. We tested the safety and security postures of eight open-weight large language models (LLMs) to identify vulnerabilities…

As diverse linguistic communities and users adopt large language models (LLMs), assessing their safety across languages becomes critical. Despite ongoing efforts to make LLMs safe, they can still be made to behave unsafely with…

Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this context remains poorly characterized. We introduce a dataset of 270 harmful instructions…

In the field of NLP, Large Language Models (LLMs) have markedly enhanced performance across a variety of tasks. However, the comprehensive evaluation of LLMs remains an inevitable challenge for the community. Recently, the adoption of…

When evaluating Large Language Models (LLMs) in question answering domains, it is common to ask the model to choose among a fixed set of choices (so-called multiple-choice question-answering, or MCQA). Although downstream tasks of interest…

Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refusal cannot maintain a low refusal ratio for harmless queries…

Large language models are meticulously aligned to be both helpful and harmless. However, recent research points to a potential overkill which means models may refuse to answer benign queries. In this paper, we investigate the factors for…

Large Language Models (LLMs) are widely used for automated code generation, yet their apparent successes often mask a tension between pretraining objectives and alignment choices. While pretraining encourages models to exploit all available…

Large Language Models (LLMs) transform artificial intelligence, driving advancements in natural language understanding, text generation, and autonomous systems. The increasing complexity of their development and deployment introduces…

Multi-modal Large Language Models (MLLMs) are increasingly deployed in interactive applications. However, their safety vulnerabilities become pronounced in multi-turn multi-modal scenarios, where harmful intent can be gradually…

Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using…

This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align…

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

Multiple choice question answering (MCQA) is popular for LLM evaluation due to its simplicity and human-like testing, but we argue for its reform. We first reveal flaws in MCQA's format, as it struggles to: 1) test generation/subjectivity;…

Large Language Models (LLMs) are trained to refuse to respond to harmful content. However, systematic analyses of whether this behavior is truly a reflection of its safety policies or an indication of political censorship, that is practiced…

Content Warning: This paper contains participant quotes and discussions related to mental health challenges, emotional distress, and suicidal ideation. Large language models (LLMs) are increasingly used for mental health support, yet the…

Large language models (LLMs) have been widely used for mental health support. However, current safety evaluations in this field are mostly limited to detecting whether LLMs output prohibited words in single-turn conversations, neglecting…

Safety-aligned Large Language Models (LLMs) still show two dominant failure modes: they are easily jailbroken, or they over-refuse harmless inputs that contain sensitive surface signals. We trace both to a common cause: current models…

The performance of Large Language Models (LLMs) on multiple-choice question (MCQ) benchmarks is frequently cited as proof of their medical capabilities. We hypothesized that LLM performance on medical MCQs may in part be illusory and driven…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…