相关论文: Vulnerability Mitigation for Safety-Aligned Langua…

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…

Language model alignment has become an important component of AI safety, allowing safe interactions between humans and language models, by enhancing desired behaviors and inhibiting undesired ones. It is often done by tuning the model or…

As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introduce Deliberative Alignment, a new paradigm that directly…

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience. A model that prioritizes safety will cause users to feel less engaged and assisted…

Current text-to-image (T2I) models often fail to account for diverse human experiences, leading to misaligned systems. We advocate for pluralistic alignment, where an AI understands and is steerable towards diverse, and often conflicting,…

Increasing use of large language models (LLMs) demand performant guardrails to ensure the safety of inputs and outputs of LLMs. When these safeguards are trained on imbalanced data, they can learn the societal biases. We present a…

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to…

Large Language Models (LLMs) are increasingly used in healthcare, yet ensuring their safety and trustworthiness remains a barrier to deployment. Conversational medical assistants must avoid unsafe compliance without over-refusing benign…

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Hallucination in large language models (LLMs) has been widely studied in recent years, with progress in both detection and mitigation aimed at improving truthfulness. Yet, a critical side effect remains largely overlooked: enhancing…

A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally,…

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and…

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are…

While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and…