Lightweight tools for ‘steering’ LLMs down the right path
Research
Kim Martineau
Blog
71 results for Trustworthy AI
IBM at the intersection of human-computer interaction and AI
ResearchZahra AshktorabCharacterizing the evolution of tasks within occupations
ResearchMartin Fleming and Subhro Das4 minute readIBM joins Stanford Human-Centered AI Institute’s partner program
NewsJeff WelserIntroducing AI Explainability 360
ReleaseAleksandra MojsilovicChanging the way the world works: IBM Research’s “5 in 5”
NewsArvind Krishna4 minute readIBM Research releases ‘Diversity in Faces’ dataset to advance study of fairness in facial recognition systems
NewsJohn R SmithIntroducing AI Fairness 360
ReleaseKush VarshneyFactsheets for AI Services
ResearchThe Adversarial Robustness Toolbox v0.3.0: closing the backdoor in AI security
Release