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
A benchmark for evaluating conversational RAG
ResearchKim MartineauCan 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 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
Sentence-level Aggregation of Lexical Metrics Correlate Stronger with Human Judgements than Corpus-level Aggregation
- Paulo Rodrigo Cavalin
- Pedro Henrique Leite Da Silva Pires Domingues
- et al.
- 2025
- AAAI 2025
Bridging Planning and Reasoning in Natural Languages with Foundational Models (PLAN-FM)
- 2025
- AAAI 2025
Data Wrangling task automation using Code-Generating Language Models
- Akella Ashlesha
- Krishnasuri Narayanam
- 2025
- AAAI 2025
Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
- Xiaomeng Xu
- Pin-Yu Chen
- et al.
- 2025
- AAAI 2025
Retention Score: Quantifying Jailbreak Risks for Vision Language Models
- Zhaitang Li
- Pin-Yu Chen
- et al.
- 2025
- AAAI 2025