Thomas Mesnard

Nash Learning from Human Feedback

Remi Munos

Michal Valko

Daniele Calandriello

Mohammad Gheshlaghi Azar

Mark Rowland

Zhaohan Daniel Guo

Yunhao Tang

Matthieu Geist

Thomas Mesnard

Andrea Michi

Marco Selvi

Sertan Girgin

Nikola Momchev

Olivier Bachem

Daniel J Mankowitz

Doina Precup

Bilal Piot

Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human pref… (see more)erences. Typically, RLHF involves the initial step of learning a reward model from human feedback, often expressed as preferences between pairs of text generations produced by a pre-trained LLM. Subsequently, the LLM's policy is fine-tuned by optimizing it to maximize the reward model through a reinforcement learning algorithm. However, an inherent limitation of current reward models is their inability to fully represent the richness of human preferences and their dependency on the sampling distribution. In this study, we introduce an alternative pipeline for the fine-tuning of LLMs using pairwise human feedback. Our approach entails the initial learning of a preference model, which is conditioned on two inputs given a prompt, followed by the pursuit of a policy that consistently generates responses preferred over those generated by any competing policy, thus defining the Nash equilibrium of this preference model. We term this approach Nash learning from human feedback (NLHF). In the context of a tabular policy representation, we present a novel algorithmic solution, Nash-MD, founded on the principles of mirror descent. This algorithm produces a sequence of policies, with the last iteration converging to the regularized Nash equilibrium. Additionally, we explore parametric representations of policies and introduce gradient descent algorithms for deep-learning architectures. To demonstrate the effectiveness of our approach, we present experimental results involving the fine-tuning of a LLM for a text summarization task. We believe NLHF offers a compelling avenue for preference learning and policy optimization with the potential of advancing the field of aligning LLMs with human preferences.

2023-12-01

ArXiv (preprint)

doi.org

arxiv.org

Nash Learning from Human Feedback

Remi Munos

Michal Valko

Daniele Calandriello

Mohammad Gheshlaghi Azar

Mark Rowland

Zhaohan Daniel Guo

Yunhao Tang

Matthieu Geist

Thomas Mesnard

Andrea Michi

Marco Selvi

Sertan Girgin

Nikola Momchev

Olivier Bachem

Daniel J Mankowitz

Doina Precup

Bilal Piot

Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human pref… (see more)erences. Typically, RLHF involves the initial step of learning a reward model from human feedback, often expressed as preferences between pairs of text generations produced by a pre-trained LLM. Subsequently, the LLM's policy is fine-tuned by optimizing it to maximize the reward model through a reinforcement learning algorithm. However, an inherent limitation of current reward models is their inability to fully represent the richness of human preferences and their dependency on the sampling distribution. In this study, we introduce an alternative pipeline for the fine-tuning of LLMs using pairwise human feedback. Our approach entails the initial learning of a preference model, which is conditioned on two inputs given a prompt, followed by the pursuit of a policy that consistently generates responses preferred over those generated by any competing policy, thus defining the Nash equilibrium of this preference model. We term this approach Nash learning from human feedback (NLHF). In the context of a tabular policy representation, we present a novel algorithmic solution, Nash-MD, founded on the principles of mirror descent. This algorithm produces a sequence of policies, with the last iteration converging to the regularized Nash equilibrium. Additionally, we explore parametric representations of policies and introduce gradient descent algorithms for deep-learning architectures. To demonstrate the effectiveness of our approach, we present experimental results involving the fine-tuning of a LLM for a text summarization task. We believe NLHF offers a compelling avenue for preference learning and policy optimization with the potential of advancing the field of aligning LLMs with human preferences.

2023-12-01

ArXiv (preprint)

doi.org

arxiv.org

Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks

Thomas Mesnard

Gaetan Vignoud

João Sacramento

Walter Senn

Yoshua Bengio

2018-09-05

2018 Conference on Cognitive Computational Neuroscience (published)

doi.org

arxiv.org

Generalization of Equilibrium Propagation to Vector Field Dynamics

The biological plausibility of the backpropagation algorithm has long been doubted by neuroscientists. Two major reasons are that neurons wo… (see more)uld need to send two different types of signal in the forward and backward phases, and that pairs of neurons would need to communicate through symmetric bidirectional connections. We present a simple two-phase learning procedure for fixed point recurrent networks that addresses both these issues. In our model, neurons perform leaky integration and synaptic weights are updated through a local mechanism. Our learning method generalizes Equilibrium Propagation to vector field dynamics, relaxing the requirement of an energy function. As a consequence of this generalization, the algorithm does not compute the true gradient of the objective function, but rather approximates it at a precision which is proven to be directly related to the degree of symmetry of the feedforward and feedback weights. We show experimentally that our algorithm optimizes the objective function.

2018-08-14

ArXiv (preprint)

arxiv.org