most citedFactually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback

4 citations · 4 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG20241 cited

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…

cs.LG20243 cited

MusicRL: Aligning Music Generation to Human Preferences

Geoffrey Cideron, Sertan Girgin, Mauro Verzetti +11

We propose MusicRL, the first music generation system finetuned from human feedback. Appreciation of text-to-music models is particularly subjective since the concept of musicality…

cs.LG20243 cited

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)…

cs.CL20234 cited

Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback

Paul Roit, Johan Ferret, Lior Shani +16

Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon i…

cs.RO2023

Get Back Here: Robust Imitation by Return-to-Distribution Planning

Geoffrey Cideron, Baruch Tabanpour, Sebastian Curi +6

We consider the Imitation Learning (IL) setup where expert data are not collected on the actual deployment environment but on a different version. To address the resulting distribu…