Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

Umang Bhatt, Javier Antorán, Yunfeng Zhang, +12

Artificial IntelligenceEngineeringMachine LearningVerificationUncertain Reasoning +21

Harms from Increasingly Agentic Algorithmic Systems

Alan Chan, Rebecca Salganik, Alva Markelius, +19

Artificial IntelligenceEngineeringMachine LearningAlgorithmic AccountabilityLaw +20

You shouldn’t trust me: Learning models which conceal unfairness from multiple explanation methods.

Botty Dimanov, Umang Bhatt, Mateja Jamnik, +1

Apollo (University of Cambridge)

Artificial IntelligenceEngineeringMachine LearningInformation SecurityVerification +26

On the Fairness of Causal Algorithmic Recourse

Julius von Kügelgen, Amir-Hossein Karimi, Umang Bhatt, +3

Proceedings of the AAAI Conference on Artificial Intelligence

EngineeringDiscriminationAlgorithmic AccountabilityFairness In Natural Language ProcessingLaw +20

Getting a CLUE: A Method for Explaining Uncertainty Estimates

Javier Antorán, Umang Bhatt, Tameem Adel, +2

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningBayesian Neural NetworksUncertain Reasoning +17

Machine Learning Explainability for External Stakeholders

Umang Bhatt, McKane Andrus, Adrian Weller, +1

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningMachine Learning ToolAi Safety +14

Evaluating language models for mathematics through interactions

Katherine M. Collins, Albert Q. Jiang, Simon Frieder, +10

Proceedings of the National Academy of Sciences

Llm Fine-tuningEngineeringMathematical LinguisticsLarge Language ModelCorpus Linguistics +18

Evaluating and Aggregating Feature-based Model Explanations

Umang Bhatt, Adrian Weller, José M. F. Moura

Artificial IntelligenceNatural Language ProcessingEngineeringMachine LearningData Science +13

Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

Umang Bhatt, Q. Vera Liao, Prasanna Sattigeri, +7

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningVerificationUncertain Reasoning +21

Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis

Yuxin Xiao, Paul Pu Liang, Umang Bhatt, +3

Llm Fine-tuningEngineeringMultilingual PretrainingLarge Language ModelLanguage Learning +24