相关论文: Eliciting and Analyzing Emergent Misalignment in S…

Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing…

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures. We present the first systematic cross-lingual, multimodal red-teaming study comparing…

With the advancements in Large Language Models (LLMs), Vision-Language Models (VLMs) have reached a new level of sophistication, showing notable competence in executing intricate cognition and reasoning tasks. However, existing evaluation…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the…

This paper examines a critical yet unexplored dimension of the AI alignment problem: the potential for Large Language Models (LLMs) to inherit and amplify existing misalignments between human espoused theories and theories-in-use. Drawing…

Fine-tuning large language models on narrow datasets can cause them to develop broadly misaligned behaviours: a phenomena known as emergent misalignment. However, the mechanisms underlying this misalignment, and why it generalizes beyond…

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues,…

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…

Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue objectives that deviate from human values and ethical norms, a…

AI models are already deployed in societies affected by armed conflict, and journalists, humanitarian workers, governments and ordinary citizens rely on them for information or for their work processes. No established practice exists for…

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Large audio-language models (LALMs) extend text-based LLMs with auditory understanding, offering new opportunities for multimodal applications. While their perception, reasoning, and task performance have been widely studied, their safety…