2024
When Should Algorithms Resign? A Proposal for AI Governance.
Computer, October, 2024
Building Machines that Learn and Think with People.
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
Modulating Language Model Experiences through Frictions.
CoRR, 2024
Large Language Models Must Be Taught to Know What They Don't Know.
CoRR, 2024
Representational Alignment Supports Effective Machine Teaching.
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
When Should Algorithms Resign?
CoRR, 2024
Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction.
CoRR, 2024
2023
Perspectives on incorporating expert feedback into model updates.
Patterns, July, 2023
Selective Concept Models: Permitting Stakeholder Customisation at Test-Time.
CoRR, 2023
Evaluating Language Models for Mathematics through Interactions.
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2023
Learning Personalized Decision Support Policies.
CoRR, 2023
On the informativeness of supervision signals.
Proceedings of the Uncertainty in Artificial Intelligence, 2023
Proceedings of the Uncertainty in Artificial Intelligence, 2023
GeValDi: Generative Validation of Discriminative Models.
Proceedings of the First Tiny Papers Track at ICLR 2023, 2023
Harms from Increasingly Agentic Algorithmic Systems.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023
FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines.
Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms, 2023
Iterative Teaching by Data Hallucination.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023
Human Uncertainty in Concept-Based AI Systems.
Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 2023
Towards Robust Metrics for Concept Representation Evaluation.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
Approximating Full Conformal Prediction at Scale via Influence Functions.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
2022
How transparency modulates trust in artificial intelligence.
Patterns, 2022
Web-based Elicitation of Human Perception on mixup Data.
CoRR, 2022
Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users.
CoRR, 2022
On the Utility of Prediction Sets in Human-AI Teams.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022
Eliciting and Learning with Soft Labels from Every Annotator.
Proceedings of the Tenth AAAI Conference on Human Computation and Crowdsourcing, 2022
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022, 2022
Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
On the Fairness of Causal Algorithmic Recourse.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
2021
DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement.
CoRR, 2021
Do Concept Bottleneck Models Learn as Intended?
CoRR, 2021
δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates.
CoRR, 2021
A Multistakeholder Approach Towards Evaluating AI Transparency Mechanisms.
CoRR, 2021
Getting a CLUE: A Method for Explaining Uncertainty Estimates.
Proceedings of the 9th International Conference on Learning Representations, 2021
Fast conformal classification using influence functions.
Proceedings of the Conformal and Probabilistic Prediction and Applications, 2021
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the AIES '21: AAAI/ACM Conference on AI, 2021
FIMAP: Feature Importance by Minimal Adversarial Perturbation.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021
2020
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty.
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2020
Machine Learning Explainability for External Stakeholders.
CoRR, 2020
Evaluating and Aggregating Feature-based Model Explanations.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020
On Network Science and Mutual Information for Explaining Deep Neural Networks.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020
Explainable machine learning in deployment.
Proceedings of the FAT* '20: Conference on Fairness, 2020
You Shouldn't Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods.
Proceedings of the Workshop on Artificial Intelligence Safety, 2020
2019
Towards Aggregating Weighted Feature Attributions.
CoRR, 2019
NIF: A Framework for Quantifying Neural Information Flow in Deep Networks.
CoRR, 2019
A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game.
Proceedings of the 28th IEEE International Conference on Robot and Human Interactive Communication, 2019
Diagnostic Model Explanations: A Medical Narrative.
Proceedings of the Symposium Interpretable AI for Well-being: Understanding Cognitive Bias and Social Embeddedness co-located with Association for the Advancement of Artificial Intelligence 2019 Spring Symposium (AAAI-Spring Symposium 2019), 2019
Building Human-Machine Trust via Interpretability.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019
2018
The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting.
CoRR, 2018
Maintaining the Humanity of Our Models.
Proceedings of the 2018 AAAI Spring Symposia, 2018
2017
Intelligent Pothole Detection and Road Condition Assessment.
CoRR, 2017