Knowledge and Reasoning
For AI to be useful, it needs to understand what’s being asked of it, and to know how to respond. At IBM Research, we’re working on systems to help AI better reason with the tasks it’s presented, such as understanding context and analogies, comprehension, and planning through scenarios.
Our work
AI, you have a lot of explaining to do
ReleaseDinesh Garg, Parag Singla, Dinesh Khandelwal, Shourya Aggarwal, Divyanshu Mandowara, and Vishwajeet Agrawal5 minute read- Explainable AI
- Generative AI
- Knowledge and Reasoning
- Natural Language Processing
- Neuro-symbolic AI
- Trustworthy AI
IBM, MIT and Harvard release “Common Sense AI” dataset at ICML 2021
ReleaseDan Gutfreund, Abhishek Bhandwaldar, and Chuang Gan6 minute read- AI
- Knowledge and Reasoning
- Neuro-symbolic AI
IBM’s new AI outperforms competition in table entry search with question-answering
ReleaseAlfio Gliozzo, Michael Glass, and Mustafa Canim7 minute read- Knowledge and Reasoning
- Natural Language Processing
Getting AI to reason: using neuro-symbolic AI for knowledge-based question answering
ResearchSalim Roukos, Alexander Gray, and Pavan Kapanipathi7 minute read- Knowledge and Reasoning
- Natural Language Processing
- Neuro-symbolic AI
DualTKB: A Dual Learning Bridge between Text and Knowledge Base
ResearchPierre Dognin6 minute read- Knowledge and Reasoning
- Natural Language Processing
- Trustworthy Generation
Publications
- Remo Christen
- Salomé Eriksson
- et al.
- 2023
- ECAI 2023
- Harsha Kokel
- Junkyu Lee
- et al.
- 2023
- IJCAI 2023
- 2023
- IJCAI 2023
- Achille Fokoue
- Ibrahim Abdelaziz
- et al.
- 2023
- IJCAI 2023
- Tom Silver
- Soham Dan
- et al.
- 2023
- IJCAI 2023
- Turguy Caglar
- Sirine Belhaj
- et al.
- 2023
- IJCAI 2023