Curriculum Vitae

Back to Home

Professional Experience

Principal Research Scientist

IBM Research AI, MIT-IBM Watson AI Lab | December 2015 - Present

Key Roles:

Principal Investigator on joint project with Prof. Greg Wornell (MIT): “Principles and Methods for Trustworthy Learning With Limited Data”
Principal Investigator on joint project with Prof. David Sontag (MIT): “Human-Centric AI: Novel Algorithms for Shared Decision Making”
Lead researcher for Granite Guardian - IBM’s LLM safeguarding models

Responsibilities:

Conduct research on foundational topics in machine learning and artificial intelligence including efficiency, robustness, interpretability and trustworthiness of AI models
Develop analytical tools to solve challenging business problems
Disseminate research results through scholarly publications and generate intellectual property
Development of tools for computer vision, natural language processing, healthcare and signal processing

Selected Projects:

Leading Granite Guardian project - a suite of safeguards for LLM risk detection achieving state-of-the-art results on harmful content and hallucination benchmarks
Leading research on LLM calibration and uncertainty quantification for foundation models
Joint project with MIT through the MIT-IBM Watson AI Lab on machine learning with limited human supervision, domain generalization and transfer learning
Designed and developed the technique of co-regularization that produced state-of-the-art results for unsupervised domain adaptation
Investigated domain shift in healthcare ML models (Best Paper Award)
Contributed to the development of AI Fairness 360, AI Explainability 360, and Uncertainty Quantification 360 toolkits

Software Engineer

Yelp Inc., San Francisco, CA | December 2014 - December 2015

Developed machine learning algorithms and incorporated them into products used by large consumer userbase
Proposed natural language processing techniques and image understanding algorithms to improve search results for user queries
Prototyped systems for quantitative measurement of deployed data science algorithms

Research Assistant

School of ECEE, Arizona State University | January 2009 - December 2014

Designed and developed methods for learning hierarchical representations using low rank and sparse structure of data
Proposed methods leveraging multiple sparse coding models to create strong ensemble models
Developed sparse code framework for image classification and retrieval with GPU optimization
Lead student researcher on NSF project developing ion-channel sensors
Multidisciplinary collaboration with ASU Center for Solid State Research, BioDesign Institute, and UC-Riverside

Teaching Assistant

School of ECEE, Arizona State University | August 2011 - December 2013

Served as TA for Signals and Systems course covering fundamentals of DSP, communication and control systems
Responsibilities included updating, conducting and grading lab sessions
Assisted approximately 400 students

Education

Ph.D. in Electrical Engineering | December 2014

Arizona State University, USA

Bachelor of Technology in Electronics Engineering | April 2008

National Institute of Technology, India

Honors and Awards

Year	Award
2025	Granite Guardian #1 on GuardBench (86% accuracy across 40 datasets)
2025	Granite Guardian #1 on REVEAL benchmark (outperforms GPT-4o)
2025	Granite Guardian #3 on LLM-AggreFact benchmark
2021	IBM Research Technical Achievement Award - Science of Uncertainty Quantification
2021	IBM Research Technical Achievement Award - Science of Accurate, Robust, and Generalizable AI
2020	IBM Research Technical Achievement Award - Science in Learning with Less Labels (LwLL)
2020	IBM Research Technical Achievement Award - Dynamic Neural Networks for Efficient AI
2020	Harvard Belfer Center Tech Spotlight Runner-up for AI Fairness 360
2019	IBM Outstanding Technical Achievement Award - Contributions to Trustworthy AI
2019	Best Paper at KDD Applied Data Science for Healthcare Workshop
2014	University Graduate Fellowship, Arizona State University

Professional Service

Leadership Roles:

Senior Program Committee / Area Chair - AAAI 2021, ICLR 2018
Associate Editor - Digital Signal Processing, Pattern Recognition

Workshop Organization:

Workshop on Practical Bayesian Methods for Big Data (PBMB), AI Research Week, MIT, 2019
AAAI Fall Symposium on Gathering for Artificial Intelligence And Natural Systems (GAINS), 2018

Review Service:

NeurIPS, ICML, AAAI, ICLR, EMNLP, ACL, IEEE Trans. PAMI, IEEE Trans. Signal Processing, and others

Invited Talks, Tutorials and Panels

Year	Event	Topic
2024	MIT AI Conference	AI Ethics and Change Management
2024	NAACL TrustNLP Workshop	LLM Governance and Alignment
2024	National Academy of Sciences	Reliable AI-assisted Decision Making
2024	CHI TREW Workshop	Trust and Reliance in Evolving Human-AI Workflows
2023	KDD Workshop	Uncertainty Calibration and AI-assisted Decision Making
2023	DSHealth Workshop, KDD	Generative AI and Safety
2023	AI for Open Society Day, KDD	Trustworthy LLMs (Panel)
2021	KDD Responsible AI Workshop	Trustworthy AI Toolkits
2021	PyData Global	AI Uncertainty Quantification Tutorial
2021	ACM CODS-COMAD	UQ360 Hands-on Tutorial
2021	ARC Training Centre, Australia	AI Uncertainty Quantification
2019	AI Research Week, MIT	Trusted AI (Talk and Panel)
2019	Harvard ComputeFest	AI Fairness (Talk and Tutorial)
2018	AAAI Fall Symposium	AI and Trust (Talk and Panel)

Selected Press Coverage

IBM Research Blog - “Granite Guardian tops third-party AI benchmark” (April 2025)
IBM Research Blog - “IBM Granite now has adapters designed to control AI outputs” (March 2025)
IBM Research Blog - “How we slimmed down Granite Guardian” (February 2025)
MIT IDE Medium - “What Does Ethical AI Look Like?” - featuring MIT AI Conference remarks (2024)
BBC News - “IBM launches tool aimed at detecting AI bias” by Zoe Kleinman (September 2018)
Economic Times ETCIO - “What to do when your ML model suffers from overconfidence?” by Riya Pahuja (November 2021)
VentureBeat - “What to do when AI brings more questions than answers?” by Kyle Wiggers (July 2021)
SiliconANGLE - “IBM is teaching AI models to express how confident they are about their decisions” by Mike Wheatley (June 2021)

Selected Publications

2025

Paes, L.M., Wei, D., Do, H.J., Strobelt, H., Luss, R., Dhurandhar, A., Nagireddy, M., Ramamurthy, K.N., Sattigeri, P., Geyer, W., Ghosh, S. “Multi-Level Explanations for Generative Language Models.” ACL, 2025.
Miehling, E., Desmond, M., Ramamurthy, K.N., Daly, E.M., Varshney, K.R., et al., Sattigeri, P. “Evaluating the Prompt Steerability of Large Language Models.” NAACL, 2025.
Padhi, I., Nagireddy, M., Cornacchia, G., et al., Sattigeri, P. “Granite Guardian: Comprehensive LLM Safeguarding.” NAACL Industry Track, 2025.
Huang, Y., Hua, H., Zhou, Y., et al., Sattigeri, P., Zhang, X. “Building a Foundational Guardrail for General Agentic Systems via Synthetic Data.” arXiv:2510.09781, 2025.
66 co-authors incl. Sattigeri, P. “On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective.” arXiv:2502.14296, 2025.
Richards, J.T., Dhurandhar, A., Daly, E.M., Hind, M., Sattigeri, P., Wei, D., et al. “Agentic AI Needs a Systems Theory.” arXiv:2503.00237, 2025.

2024

Shen, M., Ryu, J.J., Ghosh, S., Bu, Y., Sattigeri, P., Das, S., Wornell, G.W. “Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?” NeurIPS, 2024.
Hou, Y., Pascale, A., Carnerero-Cano, J., Tchrakian, T., Marinescu, R., Daly, E., Padhi, I., Sattigeri, P. “WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia.” NeurIPS Datasets and Benchmarks, 2024.
Rawat, A., Schoepf, S., Zizzo, G., Cornacchia, G., et al., Sattigeri, P., Chen, P.Y., Varshney, K.R. “Attack Atlas: A Practitioner’s Perspective on Challenges and Pitfalls in Red Teaming GenAI.” NeurIPS, 2024.
Shen, M., Das, S., Greenewald, K.H., Sattigeri, P., Wornell, G.W., Ghosh, S. “Thermometer: Towards Universal Calibration for Large Language Models.” ICML, 2024.
Miehling, E., Nagireddy, M., Sattigeri, P., Daly, E.M., Piorkowski, D., Richards, J.T. “Language Models in Dialogue: Conversational Maxims for Human-AI Interactions.” EMNLP Findings, 2024.
Padhi, I., Ramamurthy, K.N., Sattigeri, P., Nagireddy, M., Dognin, P., Varshney, K.R. “Value Alignment from Unstructured Text.” EMNLP Industry Track, 2024.
Pedapati, T., Dhurandhar, A., Ghosh, S., Dan, S., Sattigeri, P. “Large Language Model Confidence Estimation via Black-Box Access.” arXiv:2406.04370, 2024.
Paes, L.M., Wei, D., Do, H.J., Strobelt, H., Luss, R., Dhurandhar, A., Nagireddy, M., Ramamurthy, K.N., Sattigeri, P., Geyer, W., Ghosh, S. “Multi-Level Explanations for Generative Language Models.” arXiv:2403.14459, 2024.
Nagireddy, M., Padhi, I., Ghosh, S., Sattigeri, P. “When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails.” arXiv:2407.06323, 2024.
Jiang, M., Ruan, Y., Sattigeri, P., Roukos, S., Hashimoto, T. “Graph-based Uncertainty Metrics for Long-form Language Model Outputs.” arXiv:2410.20783, 2024.
Achintalwar, S., Baldini, I., Bouneffouf, D., et al., Sattigeri, P., et al., Varshney, K.R. “Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations.” arXiv:2403.09704, 2024.

2023

Basu, S., Katdare, P., Sattigeri, P., Chenthamarakshan, V., Driggs-Campbell, K., Das, P., Varshney, L.R. “Efficient Equivariant Transfer Learning from Pretrained Models.” NeurIPS, 2023.
Mozannar, H., Lee, J.J., Wei, D., Sattigeri, P., Das, S., Sontag, D. “Effective Human-AI Teams via Learned Natural Language Rules and Onboarding.” NeurIPS, 2023.
Shen, M., Bu, Y., Sattigeri, P., Ghosh, S., Das, S., Wornell, G.W. “Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model.” AAAI, 2023.
Shen, M., Ghosh, S., Sattigeri, P., Das, S., Bu, Y., Wornell, G.W. “Reliable Gradient-free and Likelihood-free Prompt Tuning.” EACL Findings, 2023.
Shah, A., Shen, M., Ryu, J.J., Das, S., Sattigeri, P., Bu, Y., Wornell, G.W. “Group Fairness with Uncertainty in Sensitive Attributes.” arXiv:2302.08077, 2023.

2022

Shah, A., Bu, Y., Lee, J., Sattigeri, P., et al. “Selective Regression Under Fairness Criteria.” ICML, 2022.
Lee, J., Bu, Y., Sattigeri, P., et al. “A maximal correlation approach to imposing fairness in machine learning.” ICASSP, 2022.
Varici, B., Shanmugam, K., Sattigeri, P., Tajer, A. “Intervention Target Estimation in the Presence of Latent Variables.” UAI, 2022.
Lee, J., Bu, Y., Sattigeri, P., et al. “A Maximal Correlation Framework for Fair Machine Learning.” Entropy 24(4): 461, 2022.
Ghosh, S., Liao, Q.V., Ramamurthy, K.N., Navratil, J., Sattigeri, P., Varshney, K., Zhang, Y. “Uncertainty Quantification 360: A Hands-on Tutorial.” ACM CODS-COMAD, 2022.

2021

Varici, B., Shanmugam, K., Sattigeri, P., Tajer, A. “Scalable Intervention Target Estimation in Linear Models.” NeurIPS 34: 1494-1505, 2021.
Ahuja, K., Sattigeri, P., et al. “Conditionally independent data generation.” UAI, pp. 2050-2060, 2021.
Luss, R., Chen, P.Y., Dhurandhar, A., Sattigeri, P., et al. “Leveraging latent features for local explanations.” KDD, pp. 1139-1149, 2021.
Bhatt, U., et al. “Uncertainty as a form of transparency: Measuring, communicating, and using uncertainty.” AAAI/ACM AIES, pp. 401-413, 2021.
Lee, J.K., Bu, Y., Rajan, D., Sattigeri, P., et al. “Fair Selective Classification via Sufficiency.” ICML, pp. 6076-6086, 2021.
Meng, Y., Panda, R., Lin, C.C., Sattigeri, P., et al. “AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition.” ICLR, 2021.
Galhotra, S., Shanmugam, K., Sattigeri, P., Varshney, K.R. “Interventional Fairness with Indirect Knowledge of Unobserved Protected Attributes.” Entropy 23(12): 1571, 2021.

2020

Kinyanjui, N.M., et al. “Fairness of classifiers across skin tones in dermatology.” MICCAI, pp. 320-329, 2020.
Tatro, N., Chen, P.Y., Das, P., Melnyk, I., Sattigeri, P., Lai, R. “Optimizing mode connectivity via neuron alignment.” NeurIPS 33: 15300-15311, 2020.
Thiagarajan, J.J., Venkatesh, B., Sattigeri, P., Bremer, P.T. “Building calibrated deep models via uncertainty matching with auxiliary interval predictors.” AAAI, 2020.
Meng, Y., Lin, C.C., Panda, R., Sattigeri, P., et al. “AR-Net: Adaptive Frame Resolution for Efficient Action Recognition.” ECCV, pp. 86-104, 2020.

2019

Lee, J., Sattigeri, P., Wornell, G. “Learning New Tricks From Old Dogs: Multi-Source Transfer Learning From Pre-Trained Networks.” NeurIPS, 2019.
Thiagarajan, J.J., Rajan, D., Sattigeri, P. “Understanding Behavior of Clinical Models under Domain Shifts.” KDD Healthcare Workshop, 2019. (Best Paper)
Bellamy, R.K.E., et al. “AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias.” IBM Journal of Research and Development, 2019.
Sattigeri, P., Hoffman, S.C., Chenthamarakshan, V., Varshney, K.R. “Fairness GAN: Generating Datasets with Fairness Properties.” IBM Journal of Research and Development, 2019.

2018

Kumar, A., Sattigeri, P., et al. “Co-regularized alignment for unsupervised domain adaptation.” NeurIPS, pp. 9345-9356, 2018.
Kumar, A., Sattigeri, P., Balakrishnan, A. “Variational inference of disentangled latent concepts from unlabeled observations.” ICLR, 2018.

2017

Sattigeri, P., Kumar, A., Fletcher, T. “Semi-supervised learning with GANs: manifold invariance with improved inference.” NeurIPS, pp. 5534-5544, 2017.

Patents

Luss, R., Chen, P.Y., Dhurandhar, A., Sattigeri, P., Shanmugam, K. “Contrastive explanations for images with monotonic attribute functions.” U.S. Patent 11,222,242 (January 2022)
Ramamurthy, K., Thiagarajan, J., Sattigeri, P., Spanias, A. “Ensemble sparse models for image analysis and restoration.” U.S. Patent 9,875,428 (January 2018)
Chen, P.Y., Das, P., Melnyk, I., Sattigeri, P., Lai, R., Tatro, N. “Efficient search of robust accurate neural networks.” U.S. Patent Application 16/926,407 (January 2022)
Lee, J.K., Sattigeri, P., Wornell, G. “Multi-source transfer learning from pre-trained networks.” U.S. Patent Application 16/843,173 (October 2021)

Professional Membership

IEEE Senior Member