How IBM Granite became a leader in responsible AI
Explainer
Kim Martineau
Trustworthy Generation
Data is key to technological innovations. We develop theoretical and algorithmic frameworks for generative AI to synthesize realistic, diverse, and targeted data. Our methods facilitate data augmentation for trustworthy machine learning and accelerate novel designs for drug and material discovery, and beyond.
Our work
Lightweight tools for ‘steering’ LLMs down the right path
ResearchKim MartineauDebugging LLMs to improve their credibility
ResearchKim MartineauA 360 review of AI agent benchmarks
ResearchKim MartineauAn invisible watermark to keep tabs on tabular data
ResearchKim MartineauTeaching AI models to improve themselves
ResearchPeter Hess- See more of our work on Trustworthy Generation
