activity
20242026
collaborators

5 papers

cs.AI2026

Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs

Jonathan Cook, Silvia Sapora, Arash Ahmadian +4

Large language models (LLMs) are typically trained to acquire behaviours from demonstrations or experience, yet much of their training data is declarative: instructions, rules, and…

cs.CL2025

Command A: An Enterprise-Ready Large Language Model

Team Cohere, :, Aakanksha +227

In this report we describe the development of Command A, a powerful large language model purpose-built to excel at real-world enterprise use cases. Command A is an agent-optimised…

cs.LG2025

Self-Improving Robust Preference Optimization

Eugene Choi, Arash Ahmadian, Matthieu Geist +2

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from f…

cs.LG2025

Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion

Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub +8

Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recen…

cs.LG2024

Averaging log-likelihoods in direct alignment

Nathan Grinsztajn, Yannis Flet-Berliac, Mohammad Gheshlaghi Azar +8

To better align Large Language Models (LLMs) with human judgment, Reinforcement Learning from Human Feedback (RLHF) learns a reward model and then optimizes it using regularized RL…