Flavien Prost — accepted AI-conference papers

2025

InfAlign: Inference-aware language model alignment

Ananth Balashankar, Ziteng Sun, Jonathan Berant, Jacob Eisenstein, Michael Collins, Adrian Hutter +6

ICML 2025poster

Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base model. Today, we are increasingly using inference-time algorithms (e.g., Best-of-$N$ , controlled decoding, tree search…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything

Alexandru Tifrea, Preethi Lahoti, Ben Packer, Yoni Halpern, Ahmad Beirami, Flavien Prost

ICML 2024poster

Despite achieving promising fairness-error trade-offs, in-processing mitigation techniques for group fairness cannot be employed in numerous practical applications with limited computation resources or no access to the training pipeline of the prediction model. In these situations, post-processing i…

Cited by 8 Source ↗PDF ↗Scholar ↗

2020

Fairness without Demographics through Adversarially Reweighted Learning

Preethi Lahoti, Alex Beutel, Jilin Chen, Kang Wook Lee, Flavien Prost, Nithum Thain +2

NeurIPS 2020poster

Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns. However, in practice factors like privacy and regulation often preclude the collection of protected feat…

Cited by 418 Source ↗PDF ↗code ↗Scholar ↗