When Should We Orchestrate Multiple Agents?Bhatt, U., Kapoor, S., Upadhyay, M., Sucholutsky, I., Quinzan, F., Collins, K.M., ...Human-AI Interaction Agentic AIarXiv Read Paper
Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG SystemsBarker, M., Bell, A., Thomas, E., Carr, J., Andrews, T., Bhatt, U.Machine LearningarXiv Read Paper
Measuring and Mitigating Overreliance is Necessary for Building Human-Compatible AIIbrahim, L., Collins, K.M., Kim, S.S.Y., Reuel, A., Lamparth, M., Feng, K., Ahmad, L., ...Human-AI InteractionarXiv Read Paper
Beyond Quantification: Navigating Uncertainty in Professional AI SystemsDelacroix, S., Robinson, D., Bhatt, U., Domenicucci, J., Montgomery, J., ...UncertaintyRSS: Data Science and AI Read Paper
Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AISargeant, H., Jorgensen, M., Shah, A., Weller, A., Bhatt, U.Uncertainty FairnessarXiv Read Paper
AI Impact on Human Proof Formalization WorkflowsCollins, K.M., Frieder, S., Bayer, J., Loader, J., Lim, J., Song, P., Zaiser, F., Zhou, L., ...MathematicsNeurIPS 2025 Workshop Read Paper
Enhancing Football Refereeing with AI: VARS and X-VARS for Assisted Decision-MakingHeld, J., Cioppa, A., Giancola, S., Almahmoud, E., Collins, K.M., Bhatt, U., ...Decision Support Sports AIMathSport Conference Read Paper
Revisiting Rogers' Paradox in the Context of Human-AI InteractionCollins, K.M., Bhatt, U., Sucholutsky, I.Human-AI Interaction Cognitive SciencearXiv Read Paper
Representational Alignment Supports Effective TeachingSucholutsky, I., Collins, K.M., Malaviya, M., Jacoby, N., Liu, W., Sumers, T.R., ...Cognitive SciencePMLR Read Paper
Context-Specific Certification of AI Systems: A Pilot in the Financial IndustryBrogle, K., Kallina, E., Sargeant, H., Shankar, V., Weller, A., Casovan, A., Bhatt, U.AI GovernanceAI and Ethics Read Paper
Documenting Deployment with Fabric: A Repository of Real-World AI GovernanceJorgensen, M., Brogle, K., Collins, K.M., Ibrahim, L., Shah, A., Ivanovic, P., ...AI Governance DeploymentAIES 2025 Read Paper
Towards Interactive Evaluations for Interaction Harms in Human-AI SystemsIbrahim, L., Huang, S., Ahmad, L., Bhatt, U., Anderljung, M.Human-AI InteractionAIES 2025 Read Paper
Learning Personalized Decision Support PoliciesBhatt, U., Chen, V., Collins, K.M., Kamalaruban, P., Kallina, E., Weller, A., Talwalkar, A.Human-AI Interaction Decision SupportAAAI 2025 Read Paper
Building Machines that Learn and Think with PeopleCollins, K.M., Sucholutsky, I., Bhatt, U., Chandra, K., Wong, L., Lee, M., Zhang, C.E., ...Human-AI Interaction Cognitive ScienceNature Human Behaviour Read Paper
Evaluating Language Models for Mathematics through InteractionsCollins, K.M., Jiang, A.Q., Frieder, S., Wong, L., Zilka, M., Bhatt, U., Lukasiewicz, T., ...Machine Learning MathematicsPNAS Read Paper
Large Language Models Must Be Taught to Know What They Don't KnowKapoor, S., Gruver, N., Roberts, M., Collins, K., Pal, A., Bhatt, U., Weller, A., ...Machine LearningNeurIPS 2024 Read Paper
When Should Algorithms Resign? A Proposal for AI GovernanceBhatt, U., Sargeant, H.AI GovernanceIEEE Computer Read Paper
Modulating Language Model Experiences through FrictionsCollins, K.M., Chen, V., Sucholutsky, I., Kirk, H.R., Sadek, M., Sargeant, H., ...Human-AI Interaction Machine LearningNeurIPS 2024 Workshop Read Paper
Trustworthy Machine Learning: From Algorithmic Transparency to Decision SupportBhatt, U.Human-AI Interaction Trust Decision SupportPhD Thesis Read Paper
Comparing Abstraction in Humans and Machines Using Multimodal Serial ReproductionKumar, S., Marjieh, R., Zhang, B., Campbell, D., Hu, M.Y., Bhatt, U., Lake, B., ...Cognitive ScienceCogSci 2024 Read Paper
Harms from Increasingly Agentic Algorithmic SystemsChan, A., Salganik, R., Markelius, A., Pang, C., Rajkumar, N., Krasheninnikov, D., ...Agentic AIFAccT 2023 Read Paper
Towards Robust Metrics for Concept Representation EvaluationZarlenga, M.E., Barbiero, P., Shams, Z., Kazhdan, D., Bhatt, U., Weller, A., ...Cognitive ScienceAAAI 2023 Read Paper
Human Uncertainty in Concept-Based AI SystemsCollins, K.M., Barker, M., Espinosa Zarlenga, M., Raman, N., Bhatt, U., Jamnik, M., ...Uncertainty Cognitive ScienceAIES 2023 Read Paper
On the Informativeness of Supervision SignalsSucholutsky, I., Battleday, R.M., Collins, K.M., Marjieh, R., Peterson, J., Singh, P., ...Cognitive ScienceUAI 2023 Read Paper
Approximating Full Conformal Prediction at Scale via Influence FunctionsMartinez, J.A., Bhatt, U., Weller, A., Cherubin, G.UncertaintyAAAI 2023 Read Paper
Algorithmic Loafing and Mitigation Strategies in Human-AI TeamsInuwa-Dutse, I., Toniolo, A., Weller, A., Bhatt, U.Human-AI InteractionComputers in Human Behavior: AI Read Paper
Feedbacklogs: Recording and Incorporating Stakeholder Feedback into Machine Learning PipelinesBarker, M., Kallina, E., Ashok, D., Collins, K., Casovan, A., Weller, A., Talwalkar, A., ...Human-AI Interaction FeedbackEAAMO 2023 Read Paper
Human-in-the-Loop MixupCollins, K.M., Bhatt, U., Liu, W., Piratla, V., Sucholutsky, I., Love, B., Weller, A.Human-AI Interaction Machine LearningUAI 2023 Read Paper
Iterative Teaching by Data HallucinationQiu, Z., Liu, W., Xiao, T.Z., Liu, Z., Bhatt, U., Luo, Y., Weller, A., Schölkopf, B.Cognitive Science Machine LearningAISTATS 2023 Read Paper
Selective Concept Models: Permitting Stakeholder Customisation at Test-TimeBarker, M., Collins, K.M., Dvijotham, K., Weller, A., Bhatt, U.Human-AI Interaction Cognitive ScienceHCOMP 2023 Read Paper
Perspectives on Incorporating Expert Feedback into Model UpdatesChen, V., Bhatt, U., Heidari, H., Weller, A., Talwalkar, A.FeedbackPatterns Read Paper
GeValDi: Generative Validation of Discriminative ModelsPalaniappan, V., Ashman, M., Collins, K.M., Heo, J., Weller, A., Bhatt, U.Machine LearningICLR 2023 Workshop Read Paper