Related papers: Why Do Safety Guardrails Degrade Across Languages?

Large language models (LLMs) have become increasingly integrated with various applications. To ensure that LLMs do not generate unsafe responses, they are aligned with safeguards that specify what content is restricted. However, such…

Large language models (LLMs) have seen widespread applications across various domains, yet remain vulnerable to adversarial prompt injections. While most existing research on jailbreak attacks and hallucination phenomena has focused…

Current guardian models are predominantly Western-centric and optimized for high-resource languages, leaving low-resource African languages vulnerable to evolving harms, cross-lingual failures, and cultural misalignment. Moreover, most…

Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety comes not from enumerating what is harmful, but from…

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is…

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

As large language models (LLMs) become increasingly integrated into real-world applications, scalable and rigorous safety evaluation is essential. This paper introduces Aymara AI, a programmatic platform for generating and administering…

Large Language Models (LLMs) are increasingly used for decision making in embodied agents, yet existing safety evaluations often rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these…

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…

Small language models (SLMs) have emerged as promising alternatives to large language models (LLMs) due to their low computational demands, enhanced privacy guarantees and comparable performance in specific domains through light-weight…

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on externally enforced compliance, optimizing models to detect…

The past year has seen rapid acceleration in the development of large language models (LLMs). However, without proper steering and safeguards, LLMs will readily follow malicious instructions, provide unsafe advice, and generate toxic…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating information seeking, advice, and emotionally sensitive interactions. Yet existing safety mechanisms remain largely grounded in…

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…

Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional components. However, existing safety attribution methods…

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

The safety evaluation of large language models (LLMs) remains largely centered on English, leaving non-English languages and culturally grounded risks underexplored. In this work, we investigate LLM safety in the context of the Thai…

Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achieve strong performance, their computational cost is…