145 citations · 309 across the 13 of their papers we have counts for
6 papers · 1 filter
On Teacher Hacking in Language Model Distillation
Daniil Tiapkin, Daniele Calandriello, Johan Ferret +4
Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii)…
Diversity-Rewarded CFG Distillation
Geoffrey Cideron, Andrea Agostinelli, Johan Ferret +5
Generative models are transforming creative domains such as music generation, with inference-time strategies like Classifier-Free Guidance (CFG) playing a crucial role. However, CF…
BOND: Aligning LLMs with Best-of-N Distillation
Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot +17
Reinforcement learning from human feedback (RLHF) is a key driver of quality and safety in state-of-the-art large language models. Yet, a surprisingly simple and strong inference-t…
Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning
Kaiwen Wang, Rahul Kidambi, Ryan Sullivan +17
Reward-based finetuning is crucial for aligning language policies with intended behaviors (e.g., creativity and safety). A key challenge is to develop steerable language models tha…
WARP: On the Benefits of Weight Averaged Rewarded Policies
Alexandre Ramé, Johan Ferret, Nino Vieillard +7
Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human p…
WARM: On the Benefits of Weight Averaged Reward Models
Alexandre Ramé, Nino Vieillard, Léonard Hussenot +4
Aligning large language models (LLMs) with human preferences through reinforcement learning (RLHF) can lead to reward hacking, where LLMs exploit failures in the reward model (RM)…