相关论文: Towards Context-Invariant Safety Alignment for Lar…

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…

Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns.…

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and…

Large Reasoning Models (LRMs) improve performance on complex tasks, but they also make safety control harder at deployment time. In black-box settings, defenders cannot modify model weights and must instead intervene at inference time. This…

In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups.…

Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Language model inversion (LMI), i.e., recovering hidden prompts from outputs, emerges as a concrete threat to user privacy and system security. We recast LMI as reusing the LLM's own latent space and propose the Invariant Latent Space…

Automated short-answer grading (ASAG) remains a challenging task due to the linguistic variability of student responses and the need for nuanced, rubric-aligned partial credit. While Large Language Models (LLMs) offer a promising solution,…

This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these…

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

In perpetrator treatment, a recurring observation is the dissociation between insight and action: offenders articulate remorse yet behavioral change does not follow. We report four preregistered studies (1,584 multi-agent simulations across…

Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can amplify risk. We propose ProSocialAlign, a test-time,…

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Alignment of Large Language Models (LLMs) remains an unsolved problem. Human preferences are highly distributed and can be captured at multiple levels of abstraction, from the individual to diverse populations. Organisational preferences,…

Collecting high-quality preference datasets for reinforcement learning from human feedback (RLHF) is resource-intensive and challenging. As a result, researchers often train reward models on extensive offline datasets which aggregate…

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model…

Given the impressive capabilities of recent Large Language Models (LLMs), we investigate and benchmark the most popular proprietary and different sized open source models on the task of explicit instruction following in conflicting…