Estimating Training Data Influence by Tracing Gradient Descent (2020 · 223 citations)
The paper asks which training examples are responsible for a model's prediction on a given input. The authors propose TracIn. It attributes to each training example the drop in the test example's loss that occurred during the optimization steps where that example was used. The exact version would require knowing the…
Did the Model Understand the Question? (2018 · 214 citations)
The paper asks whether high-accuracy question answering networks actually use the meaningful words in a question.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Estimating Training Data Influence by Tracing Gradient DescentarXiv:2002.08484Garima Pruthi, Frederick Liu, Mukund Sundararajan, et al.2020 · 223 citations
Did the Model Understand the Question?Annual Meeting of the Association for Computational Linguistics (ACL)Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan, et al.2018 · 214 citations
A Learning-Based Approach to Reactive Security ↗IEEE Transactions on Dependable and Secure Computing · no summary yetAdam Barth et al.2011 · 43 citations

Co-authors here

2 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 3,688 times (of the 149,439 papers whose bibliographies we read); 822 citing papers with a page here →.

Updated 2 November 2026