相关论文: Adversary-Aware DPO: Enhancing Safety Alignment in…

Aligning large language models (LLMs) with human values is an increasingly critical step in post-training. Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback…

Vision-Language Models (VLMs) play a crucial role in the advancement of Artificial General Intelligence (AGI). As AGI rapidly evolves, addressing security concerns has emerged as one of the most significant challenges for VLMs. In this…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

While vision-language pre-training model (VLP) has shown revolutionary improvements on various vision-language (V+L) tasks, the studies regarding its adversarial robustness remain largely unexplored. This paper studied the adversarial…

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…

Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment with human values and intentions has emerged as a critical…

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of…

Ensuring and improving the safety of autonomous driving systems (ADS) is crucial for the deployment of highly automated vehicles, especially in safety-critical events. To address the rarity issue, adversarial scenario generation methods are…

In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences…

Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on individual techniques or specific dimensions, lacking a holistic…

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…

This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3)…

Aligning large language models (LLMs) with human preferences has gained significant attention, with Proximal Policy Optimization (PPO) as a standard yet computationally expensive method and Direct Preference Optimization (DPO) as a more…

Ensuring alignment with human preferences is a crucial characteristic of large language models (LLMs). Presently, the primary alignment methods, RLHF and DPO, require extensive human annotation, which is expensive despite their efficacy.…

This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse adversarial attacks. Building upon recent work demonstrating LLMs' effectiveness in…

Direct Preference Optimization (DPO) is an efficient alignment technique that steers LLMs towards preferable outputs by training on preference data, bypassing the need for explicit reward models. Its simplicity enables easy adaptation to…

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Language model alignment is crucial for ensuring that large language models (LLMs) align with human preferences, yet it often involves sensitive user data, raising significant privacy concerns. While prior work has integrated differential…