相关论文: Reward-free Alignment for Conflicting Objectives

As large language models (LLMs) are rapidly advancing and achieving near-human capabilities on specific tasks, aligning them with human values is becoming more urgent. In scenarios where LLMs outperform humans, we face a weak-to-strong…

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…

Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models (LLMs) with human values. However, existing approaches struggle to capture the multi-dimensional, distributional nuances of human…

The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from preference data. This involves building datasets where each…

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment…

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…

Multi-objective alignment aims to align LLM responses with multiple human preference objectives. Among existing methods, guiding the generation of frozen LLMs through autoregressive reward models (ARMs) to accomplish multi-objective…

User intentions are typically formalized as evaluation rewards to be maximized when fine-tuning language models (LMs). Existing alignment methods, such as Direct Preference Optimization (DPO), are mainly tailored for pairwise preference…

Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it…

Large language models (LLMs) have achieved remarkable success, yet aligning their generations with human preferences remains a critical challenge. Existing approaches to preference modeling often rely on an explicit or implicit reward…

To date, the multi-objective optimization literature has mainly focused on conflicting objectives, studying the Pareto front, or requiring users to balance tradeoffs. Yet, in machine learning practice, there are many scenarios where such…

Reward modeling in large language models is susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily long responses. In reinforcement learning from human…

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these issues, they remain…

The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However,…

Aligning large language models with human objectives is paramount, yet common approaches including RLHF suffer from unstable and resource-intensive training. In response to this challenge, we introduce ARGS, Alignment as Reward-Guided…

Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human preferences. To prevent the forgetting of pre-trained…

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true potential depends on effective alignment to ensure correct,…

Enhancing the conformity of large language models (LLMs) to human preferences remains an ongoing research challenge. Recently, offline approaches such as Direct Preference Optimization (DPO) have gained prominence as attractive options due…