Pathologies of Neural Models Make Interpretations Difficult

20 April 2018

Jordan L. Boyd-Graber

AAML

FAtt

ArXiv PDF HTML

Papers citing "Pathologies of Neural Models Make Interpretations Difficult"

50 / 76 papers shown

Title
Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models Sepehr Kamahi Yadollah Yaghoobzadeh 55 0 0 21 Aug 2024
CELL your Model: Contrastive Explanations for Large Language Models Ronny Luss Erik Miehling Amit Dhurandhar 47 0 0 17 Jun 2024
How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation Yoo Yeon Sung Ishani Mondal Jordan L. Boyd-Graber 30 0 0 20 Jan 2024
Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion Nishtha Madaan Srikanta J. Bedathur DiffM 38 0 0 21 Dec 2023
Explaining high-dimensional text classifiers Odelia Melamed Rich Caruana 23 0 0 22 Nov 2023
Toward Stronger Textual Attack Detectors Pierre Colombo Marine Picot Nathan Noiry Guillaume Staerman Pablo Piantanida 62 5 0 21 Oct 2023
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks Xinyu Zhang Hanbin Hong Yuan Hong Peng Huang Binghui Wang Zhongjie Ba Kui Ren SILM 44 18 0 31 Jul 2023
Explaining Math Word Problem Solvers Abby Newcomb Jugal Kalita 18 1 0 24 Jul 2023
Do not Mask Randomly: Effective Domain-adaptive Pre-training by Masking In-domain Keywords Shahriar Golchin Mihai Surdeanu N. Tavabi A. Kiapour 21 4 0 14 Jul 2023
Open Set Relation Extraction via Unknown-Aware Training Jun Zhao Xin Zhao Wenyu Zhan Qi Zhang Tao Gui Zhongyu Wei Yunwen Chen Xiang Gao Xuanjing Huang 38 1 0 08 Jun 2023
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap Q. V. Liao J. Vaughan 58 159 0 02 Jun 2023
Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text Ashim Gupta Carter Blum Temma Choji Yingjie Fei Shalin S Shah Alakananda Vempala Vivek Srikumar AAML 32 9 0 25 May 2023
Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification Jiasheng Si Yingjie Zhu Deyu Zhou AAML 52 3 0 16 May 2023
Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models Lukávs Mikula Michal vStefánik Marek Petrovivc Petr Sojka 41 3 0 11 May 2023
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection Weijia Xu Sweta Agrawal Eleftheria Briakou Marianna J. Martindale Marine Carpuat HILM 27 47 0 18 Jan 2023
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods Josip Jukić Martin Tutek Jan Snajder FAtt 29 0 0 15 Nov 2022
AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning Tao Yang Jinghao Deng Xiaojun Quan Qifan Wang Shaoliang Nie 32 3 0 12 Oct 2022
U3E: Unsupervised and Erasure-based Evidence Extraction for Machine Reading Comprehension Suzhe He Shumin Shi Chenghao Wu 46 0 0 06 Oct 2022
What Do NLP Researchers Believe? Results of the NLP Community Metasurvey Julian Michael Ari Holtzman Alicia Parrish Aaron Mueller Alex Jinpeng Wang ... Divyam Madaan Nikita Nangia Richard Yuanzhe Pang Jason Phang Sam Bowman 30 37 0 26 Aug 2022
ferret: a Framework for Benchmarking Explainers on Transformers Giuseppe Attanasio Eliana Pastor C. Bonaventura Debora Nozza 33 30 0 02 Aug 2022
An Interpretability Evaluation Benchmark for Pre-trained Language Models Ya-Ming Shen Lijie Wang Ying-Cong Chen Xinyan Xiao Jing Liu Hua Wu 37 4 0 28 Jul 2022
Fooling Explanations in Text Classifiers Adam Ivankay Ivan Girardi Chiara Marchiori P. Frossard AAML 35 20 0 07 Jun 2022
Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images Tom Ron M. Weiler-Sagie Tamir Hazan FAtt MedIm 27 6 0 06 Jun 2022
Optimizing Relevance Maps of Vision Transformers Improves Robustness Hila Chefer Idan Schwartz Lior Wolf ViT 40 38 0 02 Jun 2022
Learning to Ignore Adversarial Attacks Yiming Zhang Yan Zhou Samuel Carton Chenhao Tan 57 2 0 23 May 2022
A Fine-grained Interpretability Evaluation Benchmark for Neural NLP Lijie Wang Yaozong Shen Shu-ping Peng Shuai Zhang Xinyan Xiao Hao Liu Hongxuan Tang Ying-Cong Chen Hua Wu Haifeng Wang ELM 19 21 0 23 May 2022
The Solvability of Interpretability Evaluation Metrics Yilun Zhou J. Shah 76 8 0 18 May 2022
It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers Zheng Tang Mihai Surdeanu 27 6 0 25 Apr 2022
Learning to Scaffold: Optimizing Model Explanations for Teaching Patrick Fernandes Marcos Vinícius Treviso Danish Pruthi André F. T. Martins Graham Neubig FAtt 30 22 0 22 Apr 2022
XAI for Transformers: Better Explanations through Conservative Propagation Ameen Ali Thomas Schnake Oliver Eberle G. Montavon Klaus-Robert Muller Lior Wolf FAtt 15 89 0 15 Feb 2022
Diagnosing AI Explanation Methods with Folk Concepts of Behavior Alon Jacovi Jasmijn Bastings Sebastian Gehrmann Yoav Goldberg Katja Filippova 36 15 0 27 Jan 2022
Measure and Improve Robustness in NLP Models: A Survey Xuezhi Wang Haohan Wang Diyi Yang 139 130 0 15 Dec 2021
Quantifying and Understanding Adversarial Examples in Discrete Input Spaces Volodymyr Kuleshov Evgenii Nikishin S. Thakoor Tingfung Lau Stefano Ermon AAML 27 1 0 12 Dec 2021
Counterfactual Explanations for Models of Code Jürgen Cito Işıl Dillig V. Murali S. Chandra AAML LRM 32 48 0 10 Nov 2021
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models? Thang M. Pham Trung H. Bui Long Mai Anh Totti Nguyen 21 7 0 22 Oct 2021
Interpreting Deep Learning Models in Natural Language Processing: A Review Xiaofei Sun Diyi Yang Xiaoya Li Tianwei Zhang Yuxian Meng Han Qiu Guoyin Wang Eduard H. Hovy Jiwei Li 19 45 0 20 Oct 2021
The Irrationality of Neural Rationale Models Yiming Zheng Serena Booth J. Shah Yilun Zhou 35 16 0 14 Oct 2021
CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learning Jiun-hao Jhan Chao-Peng Liu Shyh-Kang Jeng Hung-yi Lee 69 9 0 08 Oct 2021
AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses Yaman Kumar Singla Swapnil Parekh Somesh Singh Junjie Li R. Shah Changyou Chen AAML 41 14 0 24 Sep 2021
Let the CAT out of the bag: Contrastive Attributed explanations for Text Saneem A. Chemmengath A. Azad Ronny Luss Amit Dhurandhar FAtt 34 10 0 16 Sep 2021
Neuron-level Interpretation of Deep NLP Models: A Survey Hassan Sajjad Nadir Durrani Fahim Dalvi MILM AI4CE 35 82 0 30 Aug 2021
On the Lack of Robust Interpretability of Neural Text Classifiers Muhammad Bilal Zafar Michele Donini Dylan Slack Cédric Archambeau Sanjiv Ranjan Das K. Kenthapadi AAML 16 21 0 08 Jun 2021
On the Sensitivity and Stability of Model Interpretations in NLP Fan Yin Zhouxing Shi Cho-Jui Hsieh Kai-Wei Chang FAtt 19 33 0 18 Apr 2021
VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks Hung Le Nancy F. Chen Guosheng Lin MLLM 28 19 0 16 Apr 2021
Explaining the Road Not Taken Hua Shen Ting-Hao 'Kenneth' Huang FAtt XAI 27 9 0 27 Mar 2021
Local Interpretations for Explainable Natural Language Processing: A Survey Siwen Luo Hamish Ivison S. Han Josiah Poon MILM 43 48 0 20 Mar 2021
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging Han Guo Nazneen Rajani Peter Hase Joey Tianyi Zhou Caiming Xiong TDI 41 102 0 31 Dec 2020
Self-Explaining Structures Improve NLP Models Zijun Sun Chun Fan Qinghong Han Xiaofei Sun Yuxian Meng Fei Wu Jiwei Li MILM XAI LRM FAtt 46 38 0 03 Dec 2020
Interpretation of NLP models through input marginalization Siwon Kim Jihun Yi Eunji Kim Sungroh Yoon MILM FAtt 25 58 0 27 Oct 2020
Counterfactual Variable Control for Robust and Interpretable Question Answering S. Yu Yulei Niu Shuohang Wang Jing Jiang Qianru Sun AAML OOD 44 9 0 12 Oct 2020