Related papers: On Prompt-Driven Safeguarding for Large Language M…

Prompt engineering is pivotal for harnessing the capabilities of large language models (LLMs) across diverse applications. While existing prompt optimization methods improve prompt effectiveness, they often lead to prompt drifting, where…

In recent years, the use of prompts to guide the output of Large Language Models have increased dramatically. However, even the best of experts struggle to choose the correct words to stitch up a prompt for the desired task. To solve this,…

In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…

Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a…

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Interaction with Large Language Models (LLMs) is primarily carried out via prompting. A prompt is a natural language instruction designed to elicit certain behaviour or output from a model. In theory, natural language prompts enable…

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

With the widespread real-world deployment of large language models (LLMs), ensuring their behavior complies with safety standards has become crucial. Jailbreak attacks exploit vulnerabilities in LLMs to induce undesirable behavior, posing a…

Recent advances in large language models (LLMs) have led to their popularity across multiple use-cases. However, prompt engineering, the process for optimally utilizing such models, remains approximation-driven and subjective. Most of the…

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak." Research on jailbreak has highlighted the safety issues of LLMs. However, prior studies have…

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…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not always faithful to the model's final output, undermining its reliability as a monitoring…

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the…

Large Language Models (LLMs) have achieved remarkable success across diverse tasks, largely driven by well-designed prompts. However, crafting and selecting such prompts often requires considerable human effort, significantly limiting its…

The capacity of large language models (LLMs) to generate honest, harmless, and helpful responses heavily relies on the quality of user prompts. However, these prompts often tend to be brief and vague, thereby significantly limiting the full…

Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization (APO) methods assume access to ground-truth references (e.g., labeled validation data) that are costly to obtain. We propose the Prompt…

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…