Umang Bhatt

1.1k total citations · 1 hit paper
28 papers, 381 citations indexed

About

Umang Bhatt is a scholar working on Artificial Intelligence, Safety Research and Computer Vision and Pattern Recognition. According to data from OpenAlex, Umang Bhatt has authored 28 papers receiving a total of 381 indexed citations (citations by other indexed papers that have themselves been cited), including 21 papers in Artificial Intelligence, 8 papers in Safety Research and 3 papers in Computer Vision and Pattern Recognition. Recurrent topics in Umang Bhatt's work include Explainable Artificial Intelligence (XAI) (16 papers), Adversarial Robustness in Machine Learning (10 papers) and Ethics and Social Impacts of AI (8 papers). Umang Bhatt is often cited by papers focused on Explainable Artificial Intelligence (XAI) (16 papers), Adversarial Robustness in Machine Learning (10 papers) and Ethics and Social Impacts of AI (8 papers). Umang Bhatt collaborates with scholars based in United Kingdom, United States and Germany. Umang Bhatt's co-authors include Adrian Weller, John Zerilli, Omesh Tickoo, Jason Stanley, Alice Xiang, Prasanna Sattigeri, Rumi Chunara, Yunfeng Zhang, Q. Vera Liao and Lama Nachman and has published in prestigious journals such as Proceedings of the National Academy of Sciences, Computer and Nature Human Behaviour.

In The Last Decade

Umang Bhatt

26 papers receiving 361 citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

How transparency modulates trust in artificial intelligence

2022 91 citations John Zerilli, Umang Bhatt et al. Patterns profile →

Peers

Umang Bhatt

AI

SR

HI

SP

IS

Jasper van der Waa Netherlands

Harsha Nori United States

Ana Marasović United States

Alon Jacovi Israel

Arkadiusz Janz Poland

Bartłomiej Koptyra Poland

Julita Bielaniewicz Poland

Mateusz Kochanek Poland

Oliwier Kaszyca Poland

Igor Cichecki Poland

Jasper van der Waa Netherlands

Umang Bhatt

224 ×0.9

AI

69 ×0.8

SR

59 ×1.1

HI

27 ×0.7

SP

18 ×0.8

IS

Citations per year, relative to Umang Bhatt Umang Bhatt (= 1×) peers Jasper van der Waa

Countries citing papers authored by Umang Bhatt

Since Specialization

Citations

This map shows the geographic impact of Umang Bhatt's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Umang Bhatt with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Umang Bhatt more than expected).

Fields of papers citing papers by Umang Bhatt

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Umang Bhatt. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Umang Bhatt. The network helps show where Umang Bhatt may publish in the future.

Co-authorship network of co-authors of Umang Bhatt

This figure shows the co-authorship network connecting the top 25 collaborators of Umang Bhatt. A scholar is included among the top collaborators of Umang Bhatt based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Umang Bhatt. Umang Bhatt is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

1.

Bhatt, Umang, et al.. (2025). Towards Interactive Evaluations for Interaction Harms in Human-AI Systems. Proceedings of the AAAI/ACM Conference on AI Ethics and Society. 8(2). 1302–1310. 1 indexed citations

2.

Shankar, Venkatesh, et al.. (2025). Context-specific certification of AI systems: a pilot in the financial industry. AI and Ethics. 5(4). 4223–4240.

3.

Delacroix, Sylvie, Diana Robinson, Umang Bhatt, et al.. (2025). Beyond Quantification: Navigating Uncertainty in Professional AI Systems. Research Portal (King's College London). 1(1).

4.

Bhatt, Umang, Valerie Chen, Katherine M. Collins, et al.. (2025). Learning Personalized Decision Support Policies. Proceedings of the AAAI Conference on Artificial Intelligence. 39(13). 14203–14211. 1 indexed citations

5.

Collins, Katherine M., Ilia Sucholutsky, Umang Bhatt, et al.. (2024). Building machines that learn and think with people. Nature Human Behaviour. 8(10). 1851–1863. 11 indexed citations

6.

Collins, Katherine M., Albert Q. Jiang, Miri Zilka, et al.. (2024). Evaluating language models for mathematics through interactions. Proceedings of the National Academy of Sciences. 121(24). e2318124121–e2318124121. 20 indexed citations

7.

Bhatt, Umang, et al.. (2024). When Should Algorithms Resign? A Proposal for AI Governance. Computer. 57(10). 99–103. 1 indexed citations

8.

Collins, Katherine M., Matthew L Barker, Mateo Espinosa Zarlenga, et al.. (2023). Human Uncertainty in Concept-Based AI Systems. 869–889. 7 indexed citations

9.

Barker, Matthew L, Katherine M. Collins, Adrian Weller, et al.. (2023). FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines. 1–15. 4 indexed citations

10.

Bhatt, Umang, et al.. (2023). Approximating Full Conformal Prediction at Scale via Influence Functions. Proceedings of the AAAI Conference on Artificial Intelligence. 37(6). 6631–6639. 3 indexed citations

11.

Barker, Matthew L, Katherine M. Collins, Krishnamurthy Dvijotham, Adrian Weller, & Umang Bhatt. (2023). Selective Concept Models: Permitting Stakeholder Customisation at Test-Time. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 11(1). 2–13. 1 indexed citations

12.

Zarlenga, Mateo Espinosa, et al.. (2023). Towards Robust Metrics for Concept Representation Evaluation. Proceedings of the AAAI Conference on Artificial Intelligence. 37(10). 11791–11799. 2 indexed citations

13.

Chen, Valerie, et al.. (2023). Perspectives on incorporating expert feedback into model updates. Patterns. 4(7). 100780–100780. 4 indexed citations

14.

Xiao, Yuxin, Paul Pu Liang, Umang Bhatt, et al.. (2022). Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis. 7273–7284. 13 indexed citations

15.

Zerilli, John, Umang Bhatt, & Adrian Weller. (2022). How transparency modulates trust in artificial intelligence. Patterns. 3(4). 100455–100455. 91 indexed citations breakdown →

16.

Bhatt, Umang, et al.. (2022). Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates. Proceedings of the AAAI Conference on Artificial Intelligence. 36(7). 7390–7398. 8 indexed citations

17.

Collins, Katherine M., Umang Bhatt, & Adrian Weller. (2022). Eliciting and Learning with Soft Labels from Every Annotator. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 10(1). 40–52. 10 indexed citations

18.

Bhatt, Umang, et al.. (2021). FIMAP: Feature Importance by Minimal Adversarial Perturbation. Proceedings of the AAAI Conference on Artificial Intelligence. 35(13). 11433–11441. 10 indexed citations

19.

Davis, Brian M., et al.. (2020). On Network Science and Mutual Information for Explaining Deep Neural Networks. arXiv (Cornell University). 11. 8399–8403. 3 indexed citations

20.

Bhatt, Umang, Brian M. Davis, & José M. F. Moura. (2019). Diagnostic Model Explanations: A Medical Narrative.. National Conference on Artificial Intelligence. 1 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact