相关论文: Generalization Limits of Reinforcement Learning Al…

Large language models (LLMs) are trained on a deluge of text data with limited quality control. As a result, LLMs can exhibit unintended or even harmful behaviours, such as leaking information, fake news or hate speech. Countermeasures,…

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited. This study aims to understand and enhance the…

This research delves deeply into Meta Reinforcement Learning (Meta RL) through a exploration focusing on defining generalization limits and ensuring convergence. By employing a approach this article introduces an innovative theoretical…

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong…

Large language models (LLMs) are foundational explorations to artificial general intelligence, yet their alignment with human values via instruction tuning and preference learning achieves only superficial compliance. Here, we demonstrate…

The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments. Increasing the generalization capacity of the RL systems can…

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors…

Reinforcement learning (RL) enables agents to learn optimal behaviors through interaction with their environment and has been increasingly deployed in safety-critical applications, including autonomous driving. Despite its promise, RL is…

Modern RAN operate in highly dynamic and heterogeneous environments, where hand-tuned, rule-based RRM algorithms often underperform. While RL can surpass such heuristics in constrained settings, the diversity of deployments and…

While defenses against single-turn jailbreak attacks on Large Language Models (LLMs) have improved significantly, multi-turn jailbreaks remain a persistent vulnerability, often achieving success rates exceeding 70% against models optimized…

GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite…

Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new…

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise safety alignment and lead to harmful outputs. Existing…

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…

Alignment and adaptation in large language models heavily rely on reinforcement learning from human feedback (RLHF); yet, theoretical understanding of its generalisability remains premature, especially when the learned reward could shift,…

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real-world tasks. However, MLLMs face significant security…