相关论文: Latent-space Attacks for Refusal Evasion in Langua…

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…

Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An adversary can embed a hidden backdoor into a model to manipulate its predictions by only modifying a few training data, without controlling the…

Large language models demonstrate powerful capabilities across various natural language processing tasks, yet they also harbor safety vulnerabilities. To enhance LLM safety, various jailbreak defense methods have been proposed to guard…

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

We introduce a method to reduce refusal rates of large language models (LLMs) on sensitive content without modifying model weights or prompts. Motivated by the observation that refusals in certain models were often preceded by the specific…

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…

Despite remarkable progress made in natural language processing, even the state-of-the-art models often make incorrect predictions. Such predictions hamper the reliability of systems and limit their widespread adoption in real-world…

We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a…

Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode through the geometry of reinforcement learning updates in language models and argue that…

Masked diffusion language models (MDLMs) generate text via iterative masked-token denoising, enabling mask-parallel decoding and distinct controllability and efficiency tradeoffs from autoregressive LLMs. Yet, efficient representation-level…

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

A key component of building safe and reliable language models is enabling the models to appropriately refuse to follow certain instructions or answer certain questions. We may want models to output refusal messages for various categories of…

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from…

As one of the most powerful topic models, Latent Dirichlet Allocation (LDA) has been used in a vast range of tasks, including document understanding, information retrieval and peer-reviewer assignment. Despite its tremendous popularity, the…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process…

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In this work, we…

Large-scale language models achieved state-of-the-art performance over a number of language tasks. However, they fail on adversarial language examples, which are sentences optimized to fool the language models but with similar semantic…