Related papers: Attention-Guided Reward for Reinforcement Learning…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts…

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…

Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a…

Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstrates that models refusing harmful requests often comply when…

Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak prompts by…

As large language models (LLMs) become integrated into everyday applications, ensuring their robustness and security is increasingly critical. In particular, LLMs can be manipulated into unsafe behaviour by prompts known as jailbreaks. The…

The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle…

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…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

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 with Verifiable Rewards (RLVR) has proven effective for enhancing Large Language Models (LLMs) on complex reasoning tasks. However, existing methods suffer from an exploration dilemma: the sharply peaked initial…

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on…

Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…

Small language models (SLMs) have emerged as promising alternatives to large language models (LLMs) due to their low computational demands, enhanced privacy guarantees and comparable performance in specific domains through light-weight…

Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…

Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities and the exposure of internal reasoning processes introduce…

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…