Related papers: Generalization Limits of Reinforcement Learning Al…

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…

Recent advancements in large language models (LLMs) have demonstrated emergent capabilities in complex reasoning, largely spurred by rule-based Reinforcement Learning (RL) techniques applied during the post-training. This has raised the…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority…

Recently, Anil et al. (2024) show that many-shot (up to hundreds of) demonstrations can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless, is it possible to use few-shot demonstrations to efficiently…

Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…

Large language models (LLMs) have demonstrated remarkable capabilities, but their power comes with significant security considerations. While extensive research has been conducted on the safety of LLMs in chat mode, the security…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can…

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…

In this paper, we investigate the safety mechanisms of instruction fine-tuned large language models (LLMs). We discover that re-weighting MLP neurons can significantly compromise a model's safety, especially for MLPs in end-of-sentence…

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing…

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…

Current Large Language Model alignment research mostly focuses on improving model robustness against adversarial attacks and misbehavior by training on examples and prompting. Research has shown that LLM jailbreak probability increases with…

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by…

The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success…