Natural Language Processing
Much of the information that can help transform enterprises is locked away in text, like documents, tables, and charts. We’re building advanced AI systems that can parse vast bodies of text to help unlock that data, but also ones flexible enough to be applied to any language problem.
Our work
An air traffic controller for LLMs
ExplainerKim MartineauWhy we’re teaching LLMs to forget things
ExplainerKim MartineauTeaching AI models to improve themselves
ResearchPeter HessWhat’s an LLM context window and why is it getting larger?
NewsKim MartineauCan AI help to promote endangered Indigenous languages?
NewsKim MartineauMitigating the environmental harm of PFAS ‘forever chemicals’
NewsKim Martineau- See more of our work on Natural Language Processing
Publications
- William Brandon
- Mayank Mishra
- et al.
- 2024
- NeurIPS 2024
- Paul Soulos
- Aleksandar Terzic
- et al.
- 2024
- NeurIPS 2024
- Irene Ko
- Sihui Dai
- et al.
- 2024
- NeurIPS 2024
- Jonathan Thomm
- Aleksandar Terzic
- et al.
- 2024
- NeurIPS 2024
- Holt Bui
- Brandi Ransom
- et al.
- 2024
- MRS Fall Meeting 2024
- Tim Erdmann
- Stefan Zecevic
- et al.
- 2024
- MRS Fall Meeting 2024