Share This Author
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
- Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
- Computer ScienceHLT-NAACL Demos
- 16 February 2016
TLDR
Anchors: High-Precision Model-Agnostic Explanations
- Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
- Computer ScienceAAAI
- 25 April 2018
We introduce a novel model-agnostic system that explains the behavior of complex models with high-precision rules called anchors, representing local, "sufficient" conditions for predictions. We…
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
- Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, Matt Gardner
- Computer ScienceNAACL
- 1 March 2019
TLDR
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
- Marco Tulio Ribeiro, Tongshuang Sherry Wu, Carlos Guestrin, Sameer Singh
- Computer ScienceACL
- 8 May 2020
Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models…
Knowledge Enhanced Contextual Word Representations
- Matthew E. Peters, Mark Neumann, Noah A. Smith
- Computer ScienceEMNLP
- 9 September 2019
TLDR
Generating Natural Adversarial Examples
- Zhengli Zhao, Dheeru Dua, Sameer Singh
- Computer ScienceICLR
- 31 October 2017
TLDR
Universal Adversarial Triggers for Attacking and Analyzing NLP
- Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh
- Computer ScienceEMNLP
- 20 August 2019
Adversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a…
Model-Agnostic Interpretability of Machine Learning
- Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
- Computer ScienceArXiv
- 16 June 2016
TLDR
Calibrate Before Use: Improving Few-Shot Performance of Language Models
- Tony Zhao, Eric Wallace, Shi Feng, D. Klein, Sameer Singh
- Computer ScienceICML
- 19 February 2021
TLDR
Semantically Equivalent Adversarial Rules for Debugging NLP models
- Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
- Computer ScienceACL
- 1 July 2018
TLDR
...
...