相关论文: Guardrails in Logit Space: Safety Token Regulariza…

Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some seemingly benign data can inadvertently steer a model…

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to…

Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, real-world deployments often require context-dependent safety rules that vary across users, regions,…

The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate the finetuning process, resulting in an alignment-broken…

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue,…

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial. Current safety alignment methods, such as supervised fine-tuning and…

Fine-tuning large language models (LLMs) is a common practice to adapt generalist models to specialized domains. However, recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical…

By incorporating visual inputs, Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning. However, this integration also introduces new vulnerabilities, making MLLMs susceptible to multimodal jailbreak attacks and…

Aligned language models face a significant limitation as their fine-tuning often results in compromised safety. To tackle this, we propose a simple method RESTA that performs LLM safety realignment. RESTA stands for REstoring Safety through…

The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…

Large language models (LLMs) are increasingly deployed behind safety guardrails such as system prompts and content filters, especially in settings where product teams cannot modify model weights. In practice these guardrails are typically…

Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. [2024] reported that even benign fine-tuning on seemingly safe datasets can give rise to unsafe behaviors in the models. The…

Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, recent studies show that the alignment can be easily compromised…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

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…

Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding to socially harmful questions. Despite substantial efforts…

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…

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead…