Related papers: Energy-Based Preference Model Offers Better Offlin…

Despite the efficacy of Direct Preference Optimization (DPO) in aligning Large Language Models (LLMs), reward hacking remains a pivotal challenge. This issue emerges when LLMs excessively reduce the probability of rejected completions to…

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust…

With the rapid development of Large Language Models (LLMs), numerous Reinforcement Learning from Human Feedback (RLHF) algorithms have been introduced to improve model safety and alignment with human preferences. These algorithms can be…

Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of…

Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback (RLHF) have shown remarkable generation abilities in numerous tasks. However, collecting high-quality human preferences creates costly bottlenecks in…

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…

Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values by learning rewards from human preference data. Due to various reasons, however, such data typically takes the form of rankings…

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these…

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…

Reinforcement Learning from Human Feedback (RLHF) has shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform preference alignment from a fixed dataset, which can be…

This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse viewpoints. We…

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…

We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for Large Language Models (LLMs). Over-optimization occurs when a…

The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences.…

Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models (LLMs) with human preferences. These algorithms implicitly treat the LLM as a reward…

Training energy-based models (EBMs) on discrete spaces is challenging because sampling over such spaces can be difficult. We propose to train discrete EBMs with energy discrepancy (ED), a novel type of contrastive loss functional which only…

Reinforcement learning from human feedback (RLHF) has been extensively employed to align large language models with user intent. However, proximal policy optimization (PPO) based RLHF is occasionally unstable requiring significant…

Large language models (LLMs) trained via KL-regularized reinforcement learning demonstrate strong instruction following, self-correction, and reasoning abilities. Yet their theoretical underpinnings remain limited. We exploit the…