This user has not added any information to their profile yet.
- Compositional preference models for aligning LMs
The International Conference on Learning Representations (ICLR), Vienna, Austria, 7-11 May, 2024
- Compositional preference models for alignment with scalable oversight
Socially Responsible Language Modelling Research (SoLaR)at NeurIPS 2023, 16 December 2023
- Should one marginalize over possible tokenizations?
61st Annual Meeting of the Association for Computational Linguistics (ACL), Toronto, Canada, 9-14 July, 2023
- Should you marginalize over possible tokenizations?
Published on arXiv.org
- disco: a toolkit for DIStributional COntrol of generative models
61st Annual Meeting of the Association for Computational Linguistics (ACL), Toronto, Canada, 9-14 July, 2023
- Aligning language models with preferences through f-divergence minimization
Published on arXiv.org
- On reinforcement learning and distribution matching for fine-tuning language models with no catastrophic forgetting
Neural Information Processing Systems (NeurIPS), hybrid event, New Orleans, Louisiana, USA, 28 November – 9 December, 2022
- Beyond the imitation game: quantifying and extrapolating the capabilities of language models
Published on arXiv.org
- BLOOM: a 176B-parameter open-access multilingual language model
Published on arXiv.org