Related papers: Read the Scene, Not the Script: Outcome-Aware Safe…

While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or situational violations. We propose shifting the safety frontier toward…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Ensuring the safety and alignment of Large Language Models is a significant challenge with their growing integration into critical applications and societal functions. While prior research has primarily focused on jailbreak attacks, less…

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…

Multimodal large language models (MLLMs) enable interaction over both text and images, but their safety behavior can be driven by unimodal shortcuts instead of true joint intent understanding. We introduce CSR-Bench, a benchmark for…

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Large language models (LLMs) hold promise in clinical decision support but face major challenges in safety evaluation and effectiveness validation. We developed the Clinical Safety-Effectiveness Dual-Track Benchmark (CSEDB), a…

Ensuring the safety of large language model (LLM) applications is essential for developing trustworthy artificial intelligence. Current LLM safety benchmarks have two limitations. First, they focus solely on either discriminative or…

This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain task conditions, models enter a state in which they continuously generate harmful content…

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…

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Autonomous control systems face significant challenges in performing complex tasks in the presence of latent risks. To address this, we propose an integrated framework that combines Large Language Models (LLMs), numerical optimization, and…

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

Air Traffic Control (ATC) is a safety-critical domain in which incorrect interpretation of instructions may lead to severe operational consequences. While large language models (LLMs) demonstrate strong general performance, their…

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it,…

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) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal,…

The emergence of Large Language Models (LLMs) has driven rapid progress in multi-modal learning, particularly in the development of Large Vision-Language Models (LVLMs). However, existing LVLM training paradigms place excessive reliance on…