Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Gaetan Narozniak

Gaetan Narozniak

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

AI×1

Frequent co-authors

Gérard Biau1×
Rémi Munos1×
Ahmad Rammal1×
Pierre Marion1×

Research Timeline

2026
Distilling LLM Feedback for Lean Theorem Proving

The paper introduces Feedback Distillation, a novel training method that uses a language model's privileged feedback to provide token-level supervision, significantly improving complex reasoning tasks like Lean theorem-proving compared to standard RL methods like GRPO.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 29, 2026

Distilling LLM Feedback for Lean Theorem Proving

Gaetan Narozniak, Gérard Biau, Rémi Munos, Ahmad Rammal +1 more

The paper introduces Feedback Distillation, a novel training method that uses a language model's privileged feedback to provide token-level supervision, significantly improving complex reasoning tasks…

View →