Related papers: Reward Bias Substitution: Single-Axis Bias Mitigat…

Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, such as Group Relative Policy Optimization (GRPO), suffer from…

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

The literature has proposed various robust alternatives to empirical risk minimisation to address failure modes such as distribution shift, label noise and finite-sample degeneracies. Examples include distributionally robust optimization,…

A centerpiece of the ever-popular reinforcement learning from human feedback (RLHF) approach to fine-tuning autoregressive language models is the explicit training of a reward model to emulate human feedback, distinct from the language…

In human-in-the-loop reinforcement learning or environments where calculating a reward is expensive, the costly rewards can make learning efficiency challenging to achieve. The cost of obtaining feedback from humans or calculating expensive…

Reinforcement learning from human feedback (RLHF) implicitly aggregates heterogeneous human preferences into a single utility function, even though the underlying utilities of the participants are in practice diverse. Hence, RLHF can be…

Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness limits the model's applications in scenarios such as in-context learning and…

Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the explicit reference…

In practice, reinforcement learning (RL) agents are often trained with a possibly imperfect proxy reward function, which may lead to a human-agent alignment issue (i.e., the learned policy either converges to non-optimal performance with…

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences…

Foundation models, specifically Large Language Models (LLMs), have lately gained wide-spread attention and adoption. Reinforcement Learning with Human Feedback (RLHF) involves training a reward model to capture desired behaviors, which is…

Standard practice within Reinforcement Learning from Human Feedback (RLHF) involves optimizing against a Reward Model (RM), which itself is trained to reflect human preferences for desirable generations. A notable subject that is…

Sample efficiency is critical for online Reinforcement Learning from Human Feedback (RLHF). While existing works investigate sample-efficient online exploration strategies, the potential of utilizing misspecified yet relevant reward models…

The Bradley-Terry (BT) model is widely practiced in reward modeling for reinforcement learning with human feedback (RLHF). Despite its effectiveness, reward models (RMs) trained with BT model loss are prone to over-optimization, losing…

Aligning multimodal large language models (MLLMs) with human preferences often relies on single-signal, model-based reward methods. Such monolithic rewards often lack confidence calibration across domain-specific tasks, fail to capture…

Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data,…

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing…

Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Within a reinforcement learning (RL) framework, LRS involves…

Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based methods also suppress the chosen response when they try to suppress the rejected one, and there is no general…

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…