Related papers: XSTest: A Test Suite for Identifying Exaggerated S…

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical behavior, posing serious compliance risks. To systematically…

Large Language Models (LLMs) like Codex are powerful tools for performing code completion and code generation tasks as they are trained on billions of lines of code from publicly available sources. Moreover, these models are capable of…

As Large Language Models (LLMs) continue to advance in understanding and generating long sequences, new safety concerns have been introduced through the long context. However, the safety of LLMs in long-context tasks remains under-explored,…

In recent years, Large Language Models have attracted growing interest for their significant potential, though concerns have rapidly emerged regarding unsafe behaviors stemming from inherent stereotypes and biases. Most research on…

Consider a scenario where a harmfulness evaluation metric intended to filter unsafe responses from a Large Language Model. When applied to individual harmful prompt-response pairs, it correctly flags them as unsafe by assigning a high-risk…

Large Language Models (LLMs) are being increasingly integrated into software systems, offering powerful capabilities but also raising concerns about fairness. Existing fairness benchmarks, however, focus on stereotype-specific associations,…

Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies…

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

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…

Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such type of safety that has been scarcely studied is commonsense…

The number of scientific articles published in the domain of food safety has consistently been increasing over the last few decades. It has therefore become unfeasible for food safety experts to read all relevant literature related to food…

Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of…

Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains…

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…

In some areas of computing, natural language processing and information science, progress is made by sharing datasets and challenging the community to design the best algorithm for an associated task. This article introduces a shared…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

Building safe Large Language Models (LLMs) across multiple languages is essential in ensuring both safe access and linguistic diversity. To this end, we conduct a large-scale, comprehensive safety evaluation of the current LLM landscape.…

As large language models (LLMs) are deployed in multilingual settings, their safety behavior in culturally diverse, low-resource languages remains poorly understood. We present the first systematic evaluation of LLM safety across 12 Indic…