相关论文: Towards Context-Invariant Safety Alignment for Lar…

While recent advancements in large language model (LLM) alignment have enabled the effective identification of malicious objectives involving scene nesting and keyword rewriting, our study reveals that these methods remain inadequate at…

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are…

Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as few as 100 adversarial examples. This fragility becomes critical in real-world…

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective training signals. We discover that aligned models already…

In-context learning (ICL) is now a common method for teaching large language models (LLMs) new tasks: given labeled examples in the input context, the LLM learns to perform the task without weight updates. Do models guided via ICL infer the…

A reinforcement learning (RL) control policy could fail in a new/perturbed environment that is different from the training environment, due to the presence of dynamic variations. For controlling systems with continuous state and action…

The explicit low-rank regularization, e.g., nuclear norm regularization, has been widely used in imaging sciences. However, it has been found that implicit regularization outperforms explicit ones in various image processing tasks. Another…

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning, yet they remain vulnerable to hallucination, where generated content deviates from visual evidence. Existing mitigation strategies…

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence…

As Large Language Models (LLMs) become more powerful and autonomous, they increasingly face conflicts and dilemmas in many scenarios. We first summarize and taxonomize these diverse conflicts. Then, we model the LLM's preferences to make…

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and…

Visual and textual soft prompt tuning can effectively improve the adaptability of Vision-Language Models (VLMs) in downstream tasks. However, fine-tuning on video tasks impairs the model's generalization ability to unseen classes. Existing…

Recent advancements in artificial intelligence have led to the creation of highly capable large language models (LLMs) that can perform tasks in a human-like manner. However, LLMs exhibit only infant-level cognitive abilities in certain…

The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face…

Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes alignment a complicated procedure, sometimes producing…