TRACE Lab

Publications

Papers

2019–2026

Filter

Measuring and Mitigating Overreliance to Build Human-Compatible AI
Lujain Ibrahim, Katherine M. Collins, Sunnie S. Y. Kim, Anka Reuel, Max Lamparth, Kevin Feng, Lama Ahmad, Prajna Soni, Alia El Kattan, Merlin Stein, Siddharth Swaroop, Vishakh Padmakumar, and 5 others
AIES
A reporting checklist for large language models in behavioural science
Stefan Feuerriegel, Christopher Barrie, M. J. Crockett, Laura K. Globig, Killian L. McLoughlin, Dan-Mircea Mirea, Arthur Spirling, Diyi Yang, Tim Althoff, Maria Antoniak, Lisa P. Argyle, Ashwini Ashokkumar, and 69 others
Nature Human Behaviour
RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies
Patricia Paskov, Kevin Wei, Shen Zhou Hong, Dan Bateyko, Xavier Roberts-Gaal, Carson Ezell, Gailius Praninskas, Valerie Chen, Umang Bhatt, Ella Guest
AIES
Revisiting Rogers’ Paradox in the context of human–AI interaction
Katherine M. Collins, Umang Bhatt, Ilia Sucholutsky
Philosophical Transactions of the Royal Society A
The next Turing tests: Reimagining conceptions and measures of AI
Jose Hernandez-Orallo, Katherine M. Collins, Lucy Cheke, Laura Weidinger, Umang Bhatt, Thomas L. Griffiths, Stephen Cave
Science

Towards Interactive Evaluations for Interaction Harms in Human-AI Systems
Lujain Ibrahim, Saffron Huang, Lama Ahmad, Umang Bhatt, Markus Anderljung
AIES
Beyond Quantification: Navigating Uncertainty in Professional AI Systems
Sylvie Delacroix, Diana Robinson, Umang Bhatt, Jacopo Domenicucci, Jessica Montgomery, Gaël Varoquaux, Carl Henrik Ek, Vincent Fortuin, Yulan He, Tom Diethe, Neill Campbell, Mennatallah El‐Assady, and 3 others
RSS: Data Science and AI
Context-specific certification of AI systems: a pilot in the financial industry
Kendall Brogle, Emma Kallina, Holli Sargeant, Var Shankar, Adrian Weller, Ashley Casovan, Umang Bhatt
AI and Ethics
Learning Personalized Decision Support Policies
Umang Bhatt, Valerie Chen, Katherine M. Collins, Parameswaran Kamalaruban, Emma Kallina, Adrian Weller, Ameet Talwalkar
AAAI
Documenting Deployment with Fabric: A Repository of Real-World AI Governance
Mackenzie Jorgensen, Kendall Brogle, Katherine M. Collins, Lujain Ibrahim, Arina Shah, Petra Ivanovic, Noah Broestl, Gabriel Piles, Paul Dongha, Hatim Abdulhussein, Adrian Weller, Jillian Powers, Umang Bhatt
AIES

Building machines that learn and think with people
Katherine M. Collins, Ilia Sucholutsky, Umang Bhatt, Kartik Chandra, Lionel Wong, Mina Lee, Cedegao E. Zhang, Tan Zhi‐Xuan, Mark K. Ho, Vikash K. Mansinghka, Adrian Weller, Joshua B. Tenenbaum, Thomas L. Griffiths
Nature Human Behaviour
Evaluating language models for mathematics through interactions
Katherine M. Collins, Albert Q. Jiang, Simon Frieder, Lionel Wong, Miri Zilka, Umang Bhatt, Thomas Lukasiewicz, Yuhuai Wu, Joshua B. Tenenbaum, William Hart, W. T. Gowers, Wenda Li, Adrian Weller, Mateja Jamnik
PNAS
Large Language Models Must Be Taught to Know What They Don’t Know
Sanyam Kapoor, Nate Gruver, Manley Roberts, Katherine M. Collins, Arka Pal, Umang Bhatt, Adrian Weller, Samuel Dooley, Micah Goldblum, Andrew Wilson
NeurIPS
When Should Algorithms Resign? A Proposal for AI Governance
Umang Bhatt, Holli Sargeant
IEEE Computer

Harms from Increasingly Agentic Algorithmic Systems
Alan Chan, Rebecca Salganik, Alva Markelius, Chris Pang, Nitarshan Rajkumar, Dmitrii Krasheninnikov, Lauro Langosco, Zhonghao He, Yawen Duan, Micah Carroll, Michelle Lin, Alex Mayhew, and 10 others
FAccT
Human Uncertainty in Concept-Based AI Systems
Katherine M. Collins, Matthew L Barker, Mateo Espinosa Zarlenga, Naveen Raman, Umang Bhatt, Mateja Jamnik, Ilia Sucholutsky, Adrian Weller, Krishnamurthy Dvijotham
AIES
Perspectives on incorporating expert feedback into model updates
Valerie Chen, Umang Bhatt, Hoda Heidari, Adrian Weller, Ameet Talwalkar
Patterns
FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
Matthew L Barker, Emma Kallina, Dhananjay Ashok, Katherine M. Collins, Ashley Casovan, Adrian Weller, Ameet Talwalkar, Valerie Chen, Umang Bhatt
EAAMO
Towards Robust Metrics for Concept Representation Evaluation
Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams, Dmitry Kazhdan, Umang Bhatt, Adrian Weller, Mateja Jamnik
AAAI
Approximating Full Conformal Prediction at Scale via Influence Functions
Javier Abad Martinez, Umang Bhatt, Adrian Weller, Giovanni Cherubin
AAAI
Selective Concept Models: Permitting Stakeholder Customisation at Test-Time
Matthew L Barker, Katherine M. Collins, Krishnamurthy Dvijotham, Adrian Weller, Umang Bhatt
HCOMP

How transparency modulates trust in artificial intelligence
John Zerilli, Umang Bhatt, Adrian Weller
Patterns
On the Fairness of Causal Algorithmic Recourse
Julius von Kügelgen, Amir-Hossein Karimi, Umang Bhatt, Isabel Valera, Adrian Weller, Bernhard Schölkopf
AAAI
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis
Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, Louis‐Philippe Morency
EMNLP
Eliciting and Learning with Soft Labels from Every Annotator
Katherine M. Collins, Umang Bhatt, Adrian Weller
HCOMP
Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates
Dan Ley, Umang Bhatt, Adrian Weller
AAAI
On the Utility of Prediction Sets in Human-AI Teams
Varun Babbar, Umang Bhatt, Adrian Weller
IJCAI

Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Umang Bhatt, Javier Antorán, Yunfeng Zhang, Q. Vera Liao, Prasanna Sattigeri, Riccardo Fogliato, Gabrielle Gauthier Melançon, Ranganath Krishnan, Jason Stanley, Omesh Tickoo, Lama Nachman, Rumi Chunara, and 3 others
AIES
FIMAP: Feature Importance by Minimal Adversarial Perturbation
Matt Chapman-Rounds, Umang Bhatt, Erik Pazos, Marc-André Schulz, Konstantinos Georgatzis
AAAI
Getting a CLUE: A Method for Explaining Uncertainty Estimates
Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández-Lobato
ICLR

You shouldn’t trust me: Learning models which conceal unfairness from multiple explanation methods.
Botty Dimanov, Umang Bhatt, Mateja Jamnik, Adrian Weller
ECAI
Evaluating and Aggregating Feature-based Model Explanations
Umang Bhatt, Adrian Weller, José M. F. Moura
IJCAI
Explainable machine learning in deployment
Umang Bhatt, Alice Xiang, Shubham Sharma, Adrian Weller, Ankur Taly, Yunhan Jia, Joydeep Ghosh, Ruchir Puri, José M. F. Moura, Peter Eckersley
FAccT
On Network Science and Mutual Information for Explaining Deep Neural Networks
Brian M. Davis, Umang Bhatt, Kartikeya Bhardwaj, Radu Mărculescu, José M. F. Moura
ICASSP

Building Human-Machine Trust via Interpretability
Umang Bhatt, Pradeep Ravikumar, José M. F. Moura
AAAI
Diagnostic Model Explanations: A Medical Narrative.
Umang Bhatt, Brian M. Davis, José M. F. Moura
AAAI
A Robot’s Expressive Language Affects Human Strategy and Perceptions in a Competitive Game
Aaron M. Roth, Samantha Reig, Umang Bhatt, Jonathan Shulgach, Tamara Amin, Afsaneh Doryab, Fei Fang, Manuela Veloso
RO-MAN