b'Umang Bhatt'

research

∙ 07/28/2023

FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines

Even though machine learning (ML) pipelines affect an increasing array o...

0 Matthew Barker, et al. ∙

research

∙ 06/14/2023

Selective Concept Models: Permitting Stakeholder Customisation at Test-Time

Concept-based models perform prediction using a set of concepts that are...

0 Matthew Barker, et al. ∙

research

∙ 06/02/2023

Evaluating Language Models for Mathematics through Interactions

The standard methodology of evaluating large language models (LLMs) base...

0 Katherine M. Collins, et al. ∙

research

∙ 04/13/2023

Learning Personalized Decision Support Policies

Individual human decision-makers may benefit from different forms of sup...

0 Umang Bhatt, et al. ∙

research

∙ 03/22/2023

Human Uncertainty in Concept-Based AI Systems

Placing a human in the loop may abate the risks of deploying AI systems ...

7 Katherine M. Collins, et al. ∙

research

∙ 02/20/2023

Harms from Increasingly Agentic Algorithmic Systems

Research in Fairness, Accountability, Transparency, and Ethics (FATE) ha...

0 Alan Chan, et al. ∙

research

∙ 01/25/2023

Towards Robust Metrics for Concept Representation Evaluation

Recent work on interpretability has focused on concept-based explanation...

0 Mateo Espinosa Zarlenga, et al. ∙

research

∙ 11/02/2022

Web-based Elicitation of Human Perception on mixup Data

Synthetic data is proliferating on the web and powering many advances in...

0 Katherine M. Collins, et al. ∙

research

∙ 10/31/2022

Iterative Teaching by Data Hallucination

We consider the problem of iterative machine teaching, where a teacher s...

0 Zeju Qiu, et al. ∙

research

∙ 07/06/2022

Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users

When using medical images for diagnosis, either by clinicians or artific...

15 Ana Lucic, et al. ∙

research

∙ 07/02/2022

Eliciting and Learning with Soft Labels from Every Annotator

The labels used to train machine learning (ML) models are of paramount i...

0 Katherine M. Collins, et al. ∙

research

∙ 05/13/2022

Perspectives on Incorporating Expert Feedback into Model Updates

Machine learning (ML) practitioners are increasingly tasked with develop...

0 Valerie Chen, et al. ∙

research

∙ 05/03/2022

On the Utility of Prediction Sets in Human-AI Teams

Research on human-AI teams usually provides experts with a single label,...

0 Varun Babbar, et al. ∙

research

∙ 02/02/2022

Approximating Full Conformal Prediction at Scale via Influence Functions

Conformal prediction (CP) is a wrapper around traditional machine learni...

0 Javier Abad, et al. ∙

research

∙ 12/05/2021

Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates

To interpret uncertainty estimates from differentiable probabilistic mod...

0 Dan Ley, et al. ∙

research

∙ 07/13/2021

DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement

As the complexity of machine learning (ML) models increases, resulting i...

0 Umang Bhatt, et al. ∙

research

∙ 05/10/2021

Do Concept Bottleneck Models Learn as Intended?

Concept bottleneck models map from raw inputs to concepts, and then from...

0 Andrei Margeloiu, et al. ∙

research

∙ 04/13/2021

δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates

To interpret uncertainty estimates from differentiable probabilistic mod...

1 Dan Ley, et al. ∙

research

∙ 03/27/2021

A Multistakeholder Approach Towards Evaluating AI Transparency Mechanisms

Given that there are a variety of stakeholders involved in, and affected...

0 Ana Lucic, et al. ∙

research

∙ 11/15/2020

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

Transparency of algorithmic systems entails exposing system properties t...

6 Umang Bhatt, et al. ∙

research

∙ 10/13/2020

On the Fairness of Causal Algorithmic Recourse

While many recent works have studied the problem of algorithmic fairness...

3 Julius von Kügelgen, et al. ∙

research

∙ 07/10/2020

Machine Learning Explainability for External Stakeholders

As machine learning is increasingly deployed in high-stakes contexts aff...

78 Umang Bhatt, et al. ∙

research

∙ 06/11/2020

Getting a CLUE: A Method for Explaining Uncertainty Estimates

Both uncertainty estimation and interpretability are important factors f...

0 Javier Antoran, et al. ∙

research

∙ 05/01/2020

Evaluating and Aggregating Feature-based Model Explanations

A feature-based model explanation denotes how much each input feature co...

14 Umang Bhatt, et al. ∙

research

∙ 10/24/2019

A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game

As robots are increasingly endowed with social and communicative capabil...

0 Aaron M. Roth, et al. ∙

research

∙ 09/13/2019

Explainable Machine Learning in Deployment

Explainable machine learning seeks to provide various stakeholders with ...

15 Umang Bhatt, et al. ∙

research

∙ 01/20/2019

NIF: A Framework for Quantifying Neural Information Flow in Deep Networks

In this paper, we present a new approach to interpreting deep learning m...

0 Brian Davis, et al. ∙

research

∙ 01/20/2019

Towards Aggregating Weighted Feature Attributions

Current approaches for explaining machine learning models fall into two ...

0 Umang Bhatt, et al. ∙

research

∙ 06/10/2018

The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting

With the rapid development of robot and other intelligent and autonomous...

0 Aaron M. Roth, et al. ∙

research

∙ 11/15/2017

Maintaining The Humanity of Our Models

Artificial intelligence and machine learning have been major research in...

0 Umang Bhatt, et al. ∙

research

∙ 10/06/2017

Intelligent Pothole Detection and Road Condition Assessment

Poor road conditions are a public nuisance, causing passenger discomfort...

0 Umang Bhatt, et al. ∙

Umang Bhatt

Featured Co-authors