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
Can a personalized AI be more useful?
NewsKim MartineauIBM Granite has new experimental features for developers to test
NewsKim MartineauA new tool to unlock data from enterprise documents for generative AI
NewsKim MartineauServing customized AI models at scale with LoRA
ResearchKim MartineauAn air traffic controller for LLMs
ExplainerKim MartineauWhy we’re teaching LLMs to forget things
ExplainerKim Martineau- See more of our work on Natural Language Processing
Publications
QGen Studio: An Adaptive Question-Answer Generation, Training and Evaluation Platform
- 2025
- AAAI 2025
From Multiple-Choice to Extractive QA: A Case Study for English and Arabic
- Teresa Lynn
- Malik Altakrori
- et al.
- 2025
- COLING 2025
Beyond neuropsychological tests: AI speech analysis in PKU
- Susan Waisbren
- Kely Norel
- et al.
- 2024
- J. Inherit. Metab. Dis.
MESS+: Energy-Optimal Inferencing in Language Model Zoos with Service Level Guarantees
- Ryan Zhang
- Herbert Woisetschläger
- et al.
- 2024
- NeurIPS 2024
Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature
- 2024
- NeurIPS 2024
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
- William Brandon
- Mayank Mishra
- et al.
- 2024
- NeurIPS 2024