Related papers: SAFETY-J: Evaluating Safety with Critique

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…

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…

The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable…

Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or…

Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision. Current MLLM safety evaluation tools, however, suffer from major limitations: 1)…

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) develop increasingly sophisticated capabilities and find applications in medical settings, it becomes important to assess their medical safety due to their far-reaching implications for personal and public…

Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments. However, emerging studies on a few calibration dataset-free quantization methods suggest…

Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely…

Image content safety has become a significant challenge with the rise of visual media on online platforms. Meanwhile, in the age of AI-generated content (AIGC), many image generation models are capable of producing harmful content, such as…

Large Language Models (LLMs) are acquiring a wider range of capabilities, including understanding and responding in multiple languages. While they undergo safety training to prevent them from answering illegal questions, imbalances in…

Critical thinking is essential for rational decision-making and problem-solving. This skill hinges on the ability to provide precise and reasoned critiques and is a hallmark of human intelligence. In the era of large language models (LLMs),…

Proper implementation of technical and administrative controls reinforces an organization's cybersecurity posture and business resilience, reduces risks, and enhances governance, ultimately elevating business maturity. The dynamics of the…

In the rapidly evolving field of Large Language Models (LLMs), ensuring safety is a crucial and widely discussed topic. However, existing works often overlook the geo-diversity of cultural and legal standards across the world. To…

The ability of critique is vital for models to self-improve and serve as reliable AI assistants. While extensively studied in language-only settings, multimodal critique of Large Multimodal Models (LMMs) remains underexplored despite their…

Critique ability, a meta-cognitive capability of humans, presents significant challenges for LLMs to improve. Recent works primarily rely on supervised fine-tuning (SFT) using critiques generated by a single LLM like GPT-4. However, these…

Critiques are important for enhancing the performance of Large Language Models (LLMs), enabling both self-improvement and constructive feedback for others by identifying flaws and suggesting improvements. However, evaluating the critique…

The rapid integration of Large Language Models (LLMs) across diverse sectors has marked a transformative era, showcasing remarkable capabilities in text generation and problem-solving tasks. However, this technological advancement is…

Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based methods generalize poorly, and base Large Language Models (LLMs) cannot guarantee…

Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models (MLLMs) have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM…