相关论文: SafeWorld: Geo-Diverse Safety Alignment

As large language models (LLMs) evolve into autonomous "AI scientists," they promise transformative advances but introduce novel vulnerabilities, from potential "biosafety risks" to "dangerous explosions." Ensuring trustworthy deployment in…

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused…

Effective de-escalation is critical for law enforcement safety and community trust, yet traditional training methods lack scalability and realism. While Large Language Models (LLMs) enable dynamic, open-ended simulations, their substantial…

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in…

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Large language models (LLMs) have demonstrated transformative potential in scientific research, yet their deployment in high-stakes contexts raises significant trustworthiness concerns. Here, we introduce SciTrust 2.0, a comprehensive…

Large language models (LLMs) are now deployed at unprecedented scale, assisting millions of users in daily tasks. However, the risk of these models assisting unlawful activities remains underexplored. In this study, we define this high-risk…

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks. However, these models often infer and reveal sensitive biometric attributes such as race, gender, age, body weight, and eye color;…

Large language models (LLMs) are used to generate content for a wide range of tasks, and are set to reach a growing audience in coming years due to integration in product interfaces like ChatGPT or search engines like Bing. This intensifies…

Misalignment in Large Language Models (LLMs) refers to the failure to simultaneously satisfy safety, value, and cultural dimensions, leading to behaviors that diverge from human expectations in real-world settings where these dimensions…

Recent advancements in multimodal large language models for video understanding (videoLLMs) have enhanced their capacity to process complex spatiotemporal data. However, challenges such as factual inaccuracies, harmful content, biases,…

Large Language Model (LLM)-based agents are increasingly deployed in real-world applications such as "digital assistants, autonomous customer service, and decision-support systems", where their ability to "interact in multi-turn,…

Large language models (LLMs) are often trained on data that reflect WEIRD values: Western, Educated, Industrialized, Rich, and Democratic. This raises concerns about cultural bias and fairness. Using responses to the World Values Survey, we…

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such…

With the rapid development of Large language models (LLMs), understanding the capabilities of LLMs in identifying unsafe content has become increasingly important. While previous works have introduced several benchmarks to evaluate the…