相关论文: Conditions on Preference Relations that Guarantee …

While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised nature of their training. Existing…

Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, including in…

To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning…

Large Language Models (LLMs) have demonstrated unprecedented generative capabilities, yet their alignment with human values remains critical for ensuring helpful and harmless deployments. While Reinforcement Learning from Human Feedback…

Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant…

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

This paper presents an axiomatic approach to finite Markov decision processes where the discount rate is zero. One of the principal difficulties in the no discounting case is that, even if attention is restricted to stationary policies, a…

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…

In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedback (RLHF) with the recently proposed paradigm of direct…

With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct Preference Optimization (DPO) has emerged as a promising approach for alignment, acting as an…

Large language models in the past have typically relied on some form of reinforcement learning with human feedback (RLHF) to better align model responses with human preferences. However, because of oft-observed instabilities when…

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

Reinforcement learning (RL) faces challenges in evaluating policy trajectories within intricate game tasks due to the difficulty in designing comprehensive and precise reward functions. This inherent difficulty curtails the broader…

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…

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather…

Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks. Existing methods work…