I am a Principal Research Scientist at IBM Research AI and the MIT-IBM Watson AI Lab, where my primary focus is on developing reliable AI solutions.
My research interests encompass:
- Generative Modeling and Large Language Models
- Uncertainty Quantification for AI systems
- Learning with Limited Data
- LLM Governance, Safety, and Alignment
- Human-AI Collaboration
My current projects are focused on establishing both theoretical frameworks and practical systems that ensure large language models are reliable and trustworthy.
I have played a significant role in the development of several widely-adopted trustworthy AI toolkits:
- AI Fairness 360 - Detecting and mitigating bias in ML models
- AI Explainability 360 - Explaining AI decisions
- Uncertainty Quantification 360 - Quantifying uncertainty in AI predictions
- Granite Guardian - LLM safeguarding for harmful content, jailbreaking, and hallucination detection
- March 2025 - IBM Research Blog: IBM Granite now has adapters designed to control AI outputs - featuring our work on LLM calibration from MIT-IBM Watson AI Lab
- February 2025 - IBM Research Blog: How we slimmed down Granite Guardian - announcing Granite Guardian 3.2 5B and MoE 3B models
- 2025 - Paper accepted at NAACL 2025: "Evaluating the Prompt Steerability of Large Language Models"
- 2025 - Paper accepted at NAACL 2025 Industry Track: "Granite Guardian: Comprehensive LLM Safeguarding"
- 2025 - New preprint: "Agentic AI Needs a Systems Theory" - position paper on holistic approaches to agentic AI development
- December 2024 - Released Granite Guardian - a suite of safeguards for LLM risk detection achieving state-of-the-art results
- December 2024 - Papers accepted at NeurIPS 2024:
- "Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?"
- "WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia"
- "Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI"
- November 2024 - Papers accepted at EMNLP 2024:
- "Language Models in Dialogue: Conversational Maxims for Human-AI Interactions"
- "Value Alignment from Unstructured Text" (Industry Track)
- July 2024 - Paper accepted at ICML 2024: "Thermometer: Towards Universal Calibration for Large Language Models"
- June 2024 - Invited talk on LLM Governance and Alignment at the NAACL TrustNLP Workshop. Slides
- 2024 - Panel participation and talk on Reliable AI-assisted Decision Making at the National Academy of Sciences Decadal Survey
- December 2023 - Papers accepted at NeurIPS 2023:
- "Efficient Equivariant Transfer Learning from Pretrained Models"
- "Effective Human-AI Teams via Learned Natural Language Rules and Onboarding"
- August 2023 - Invited talk on Uncertainty Calibration and AI-assisted Decision Making at the Workshop on Uncertainty Reasoning and Quantification in Decision Making, KDD
- August 2023 - Panel participation and talk on Generative AI and Safety at the DSHealth Workshop, KDD
- August 2023 - Panel participation on Trustworthy LLMs at the AI for Open Society Day, KDD
- February 2023 - Papers accepted at AAAI 2023 and EACL 2023:
- "Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model" (AAAI)
- "Reliable Gradient-free and Likelihood-free Prompt Tuning" (EACL Findings)