| 2024 | ACL | Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning. | Mathieu Rita, Florian Strub, Rahma Chaabouni, Paul Michel, Emmanuel Dupoux, Olivier Pietquin |
| 2023 | ICLR | AANG : Automating Auxiliary Learning. | Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar |
| 2023 | ICLR | Revisiting Populations in multi-agent Communication. | Paul Michel, Mathieu Rita, Kory Wallace Mathewson, Olivier Tieleman, Angeliki Lazaridou |
| 2023 | ICLR | Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication. | Valentin Taillandier, Dieuwke Hupkes, Benot Sagot, Emmanuel Dupoux, Paul Michel |
| 2022 | ICLR | Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative. | Lucio M. Dery, Paul Michel, Ameet Talwalkar, Graham Neubig |
| 2022 | ICLR | Distributionally Robust Models with Parametric Likelihood Ratios. | Paul Michel, Tatsunori Hashimoto, Graham Neubig |
| 2021 | ICLR | Modeling the Second Player in Distributionally Robust Optimization. | Paul Michel, Tatsunori Hashimoto, Graham Neubig |
| 2021 | ICML | Examining and Combating Spurious Features under Distribution Shift. | Chunting Zhou, Xuezhe Ma, Paul Michel, Graham Neubig |
| 2020 | ACL | Weight Poisoning Attacks on Pretrained Models. | Keita Kurita, Paul Michel, Graham Neubig |
| 2020 | ICML | Optimizing Data Usage via Differentiable Rewards. | Xinyi Wang, Hieu Pham, Paul Michel, Antonios Anastasopoulos, Jaime G. Carbonell, Graham Neubig |
| 2019 | NAACL | On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models. | Paul Michel, Xian Li, Graham Neubig, Juan Miguel Pino |
| 2019 | NAACL | compare-mt: A Tool for Holistic Comparison of Language Generation Systems. | Graham Neubig, Zi-Yi Dou, Junjie Hu, Paul Michel, Danish Pruthi, Xinyi Wang |
| 2018 | ACL | Extreme Adaptation for Personalized Neural Machine Translation. | Paul Michel, Graham Neubig |
| 2018 | EMNLP | MTNT: A Testbed for Machine Translation of Noisy Text. | Paul Michel, Graham Neubig |
| 2017 | ACL | Blind Phoneme Segmentation With Temporal Prediction Errors. | Paul Michel, Okko Rsnen, Roland Thiollire, Emmanuel Dupoux |