Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models

Tongshuang Wu, Marco Túlio Ribeiro, Jeffrey Heer, Daniel S. Weld

Type: Preprint

Publication Date: 2021-01-01

Citations: 15

DOI: https://doi.org/10.48550/arxiv.2101.00288

View Publication

Locations

arXiv (Cornell University) - View - PDF
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Polyjuice: Automated, General-purpose Counterfactual Generation.	2021	Tongshuang Wu Marco Túlio Ribeiro Jeffrey Heer Daniel S. Weld
+	CREST: A Joint Framework for Rationalization and Counterfactual Text Generation	2023	Marcos Treviso Alexis Ross Ricardo Rei André F. T. Martins
+	CREST: A Joint Framework for Rationalization and Counterfactual Text Generation	2023	Marcos Treviso Alexis Ross Ricardo Rei André F. T. Martins
+	Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals	2023	Yair Ori Gat Nitay Calderon Amir Feder Alexander Chapanin Amit Sharma Roi Reichart
+ PDF Chat	A Survey on Natural Language Counterfactual Generation	2024	Yongjie Wang Xiaoqi Qiu Yue Yu Xu Guo Zhiwei Zeng Yuhong Feng Zhiqi Shen
+ PDF Chat	Zero-shot LLM-guided Counterfactual Generation for Text	2024	Amrita Bhattacharjee Raha Moraffah Joshua Garland Huan Liu
+	DISCO: Distilling Counterfactuals with Large Language Models	2022	Zeming Chen Qiyue Gao Kyle Richardson Antoine Bosselut Ashish Sabharwal
+	DISCO: Distilling Counterfactuals with Large Language Models	2023	Zeming Chen Qiyue Gao Antoine Bosselut Ashish Sabharwal Kyle Richardson
+	CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation	2022	Tanay Dixit Bhargavi Paranjape Hannaneh Hajishirzi Luke Zettlemoyer
+	CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation	2022	Tanay Dixit Bhargavi Paranjape Hannaneh Hajishirzi Luke Zettlemoyer
+ PDF Chat	Enhancing adversarial robustness in Natural Language Inference using explanations	2024	Alexandros Koulakos Maria Lymperaiou Giorgos Filandrianos Giorgos Stamou
+	Plug and Play Counterfactual Text Generation for Model Robustness	2022	Nishtha Madaan Srikanta Bedathur Diptikalyan Saha
+ PDF Chat	Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text	2021	Nishtha Madaan Inkit Padhi Naveen Panwar Diptikalyan Saha
+	NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation	2022	Phillip Howard Gadi Singer Vasudev Lal Yejin Choi Swabha Swayamdipta
+	NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation	2022	Phillip Howard Gadi Singer Vasudev Lal Yejin Choi Swabha Swayamdipta
+ PDF Chat	LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study	2024	Van Bach Nguyen Paul Youssef Jörg Schlötterer Christin Seifert
+	Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text.	2021	Nishtha Madaan Inkit Padhi Naveen Panwar Diptikalyan Saha
+ PDF Chat	FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation	2025	Qianli Wang Nils Feldhus Simon Ostermann Luis Felipe Villa-Arenas Sebastian Möller Vera Schmitt
+	Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text	2020	Nishtha Madaan Inkit Padhi Naveen Panwar Diptikalyan Saha
+	Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals	2023	Ananth Balashankar Xuezhi Wang Yao Qin Ben Packer Nithum Thain Jilin Chen Ed H. Alex Beutel

Works That Cite This (13)

Action	Title	Year	Authors
+	Explaining the Road Not Taken	2021	Hua Shen Ting-Hao Huang
+	Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond	2021	Amir Feder Katherine A. Keith Emaad Manzoor Reid Pryzant Dhanya Sridhar Zach Wood-Doughty Jacob Eisenstein Justin Grimmer Roi Reichart Margaret E. Roberts
+	Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey	2021	Bonan Min Hayley Ross Elior Sulem Amir Pouran Ben Veyseh Thien Huu Nguyen Oscar Sainz Eneko Agirre Ilana Heintz Dan Roth
+	Explaining NLP Models via Minimal Contrastive Editing (MiCE)	2020	Alexis Ross Ana Marasović Matthew E. Peters
+	Counterfactual Explanations for Models of Code	2022	Jürgen Cito Işıl Dillig Vijayaraghavan Murali Satish Chandra
+	Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation	2021	Prakhar Gupta Yulia Tsvetkov Jeffrey P. Bigham
+	How Well do Feature Visualizations Support Causal Understanding of CNN Activations	2021	R. Zimmermann Judy Borowski Robert Geirhos Matthias Bethge Thomas S. A. Wallis Wieland Brendel
+	Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests.	2021	Victor Veitch Alexander D’Amour Steve Yadlowsky Jacob Eisenstein
+ PDF Chat	AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts	2022	Tongshuang Wu Michael Terry Carrie J. Cai
+	Teach Me to Explain: A Review of Datasets for Explainable NLP.	2021	Sarah Wiegreffe Ana Marasović

Works Cited by This (52)

Action	Title	Year	Authors
+	A large annotated corpus for learning natural language inference	2015	Samuel R. Bowman Gabor Angeli Christopher Potts Christopher D. Manning
+	Yelp Dataset Challenge: Review Rating Prediction	2016	Nabiha Asghar
+	Toward Controlled Generation of Text	2017	Zhiting Hu Zichao Yang Xiaodan Liang Ruslan Salakhutdinov Eric P. Xing
+ PDF Chat	Snorkel	2017	Alexander Ratner Stephen H. Bach Henry R. Ehrenberg Jason Fries Sen Wu Christopher Ré
+	Breaking NLI Systems with Sentences that Require Simple Lexical Inferences	2018	Max Glockner Vered Shwartz Yoav Goldberg
+	Unsupervised Text Style Transfer using Language Models as Discriminators	2018	Zichao Yang Zhiting Hu Chris Dyer Eric P. Xing Taylor Berg-Kirkpatrick
+ PDF Chat	SemEval-2017 Task 4: Sentiment Analysis in Twitter	2017	Sara Rosenthal Noura Farra Preslav Nakov
+	Probing What Different NLP Tasks Teach Machines about Function Word Comprehension	2019	Najoung Kim Roma Patel Adam Poliak Patrick Xia Alex Wang Tom McCoy Ian Tenney Alexis Ross Tal Linzen Benjamin Van Durme
+ PDF Chat	Generating Fluent Adversarial Examples for Natural Languages	2020	Huangzhao Zhang Hao Zhou Ning Miao Lei Li
+	Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference	2019	Tom McCoy Ellie Pavlick Tal Linzen