🧑‍🔬 Matthieu Geist

🏛️ Affiliations

🎓University of ZurichZurich · Switzerland2025–2026 · 3 paperscurrent🏢GoogleMountain View · United States2018–2025 · 67 papers🎓SupélecGif-sur-Yvette · France2008–2014 · 54 papers🔬Georgia Tech-CNRS LaboratoryMetz · France2011–2016 · 18 papers🔬Centre National de la Recherche ScientifiqueParis · France2011–2020 · 17 papers🔬Laboratoire Interdisciplinaire des Environnements ContinentauxVandœuvre-lès-Nancy · France2016–2020 · 13 papers🎓Georgia Tech-EuropeMetz · France2011–2016 · 12 papers🎓Université de LorraineNancy · France2017–2020 · 11 papers🔬CentraleSupélecGif-sur-Yvette · France2015–2017 · 9 papers🏢CohereSan Francisco · United States2023–2024 · 8 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 12 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes (2023 · 299 citations)
   Distilling a large autoregressive language model into a smaller student usually means training on a fixed set of sequences, either ground-truth targets or outputs the teacher generated.
2. Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback (2023 · 70 citations)
   Abstractive summarizers often produce statements that their source article does not support or even contradicts.

All works

8 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. On-Policy Distillation of Language Models: Learning from Self-Generated MistakesarXiv:2306.13649Rishabh Agarwal, Nino Vieillard, Yongchao Zhou, et al.2023 · 299 citations
2. What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study ↗arXiv:2006.05990 · no summary yetMarcin Andrychowicz et al.2020 · 118 citations
3. Factually Consistent Summarization via Reinforcement Learning with Textual Entailment FeedbackAnnual Meeting of the Association for Computational Linguistics (ACL)Paul Roit, Johan Ferret, Lior Shani, et al.2023 · 70 citations
4. Nash Learning from Human Feedback ↗arXiv:2312.00886 · no summary yetRemi Munos et al.2023 · 32 citations
5. IQ-Learn: Inverse soft-Q Learning for Imitation ↗arXiv (Cornell University) · no summary yetDivyansh Garg et al.2021 · 11 citations
6. Extreme Q-Learning: MaxEnt RL without Entropy ↗arXiv (Cornell University) · no summary yetDivyansh Garg et al.2023 · 7 citations
7. A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning ↗arXiv (Cornell University) · no summary yetBenjamin Eysenbach et al.2023 · 1 citation
8. Optimisation d'un tuteur intelligent à partir d'un jeu de données fixé (Optimization of a tutoring system from a fixed set of data) [in French] ↗Proceedings of the Joint Conference JEP-TALN-RECITAL 2012, volume 1: JEP · no summary yetLucie Daubigney, Matthieu Geist, Olivier Pietquin2012

🤝 Co-authors here

6 co-authors with a page, the most papers together first.

• Orgad Keller
• Paul Roit
• Rishabh Agarwal
• Roee Aharoni
• Sertan Girgin
• Yongchao Zhou

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2023
• Proceedings of the Joint Conference JEP-TALN-RECITAL 2012, volume 1: JEP

🔗 Cited by

Papers of our library cite their works 2,632 times (of the 149,439 papers whose bibliographies we read); 484 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/matthieu-geist/