Publications

Large language models: What could they do for neurology?

Guillaume Lajoie

2023-12-01

Journal of the Neurological Sciences (published)

A large-scale exploratory study of android sports apps in the google play store

Bhagya Chembakottu

Heng Li

Foutse Khomh

2023-12-01

Information and Software Technology (published)

Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models

Amirhossein Kazemnejad

Mehdi Rezagholizadeh

Prasanna Parthasarathi

Sarath Chandar

2023-12-01

Findings of the Association for Computational Linguistics: EMNLP 2023 (published)

openreview.net

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

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)

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

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)

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

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)

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

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)

Nash Learning from Human Feedback

R'emi Munos

Michal Valko

Daniele Calandriello

M. G. 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

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)

Predictive inference for travel time on transportation networks

Mohamad Elmasri

Aurélie Labbe

Denis Larocque

Laurent Charlin

2023-12-01

The Annals of Applied Statistics (published)

Samira Abbasgholizadeh-Rahimi

Qualitative Code Suggestion: A Human-Centric Approach to Qualitative Coding

Cesare Spinoso-Di Piano

Jackie Cheung

Qualitative coding is a content analysis method in which researchers read through a text corpus and assign descriptive labels or qualitative… (see more) codes to passages. It is an arduous and manual process which human-computer interaction (HCI) studies have shown could greatly benefit from NLP techniques to assist qualitative coders. Yet, previous attempts at leveraging language technologies have set up qualitative coding as a fully automatable classification problem. In this work, we take a more assistive approach by defining the task of qualitative code suggestion (QCS) in which a ranked list of previously assigned qualitative codes is suggested from an identified passage. In addition to being user-motivated, QCS integrates previously ignored properties of qualitative coding such as the sequence in which passages are annotated, the importance of rare codes and the differences in annotation styles between coders. We investigate the QCS task by releasing the first publicly available qualitative coding dataset, CVDQuoding, consisting of interviews conducted with women at risk of cardiovascular disease. In addition, we conduct a human evaluation which shows that our systems consistently make relevant code suggestions.

2023-12-01

Findings of the Association for Computational Linguistics: EMNLP 2023 (published)

openreview.net

Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data

Maxime DARRIN

Pablo Piantanida

Pierre Colombo

Implementing effective control mechanisms to ensure the proper functioning and security of deployed NLP models, from translation to chatbots… (see more), is essential. A key ingredient to ensure safe system behaviour is Out-Of-Distribution (OOD) detection, which aims to detect whether an input sample is statistically far from the training distribution. Although OOD detection is a widely covered topic in classification tasks, most methods rely on hidden features output by the encoder. In this work, we focus on leveraging soft-probabilities in a black-box framework, i.e. we can access the soft-predictions but not the internal states of the model. Our contributions include: (i) RAINPROOF a Relative informAItioN Projection OOD detection framework; and (ii) a more operational evaluation setting for OOD detection. Surprisingly, we find that OOD detection is not necessarily aligned with task-specific measures. The OOD detector may filter out samples well processed by the model and keep samples that are not, leading to weaker performance. Our results show that RAINPROOF provides OOD detection methods more aligned with task-specific performance metrics than traditional OOD detectors.

2023-12-01

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (published)