Perturbation Sensitivity Analysis to Detect Unintended Model Biases

9 October 2019

Papers citing "Perturbation Sensitivity Analysis to Detect Unintended Model Biases"

25 / 25 papers shown

Title
CERT-ED: Certifiably Robust Text Classification for Edit Distance Zhuoqun Huang Yipeng Wang Seunghee Shin Benjamin I. P. Rubinstein AAML 48 1 0 01 Aug 2024
Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection Fatma Elsafoury 29 3 0 31 Aug 2023
Reducing Sensitivity on Speaker Names for Text Generation from Dialogues Qi Jia Haifeng Tang Kenny Q. Zhu 24 2 0 23 May 2023
Comparing Biases and the Impact of Multilingual Training across Multiple Languages Sharon Levy Neha Ann John Ling Liu Yogarshi Vyas Jie Ma Yoshinari Fujinuma Miguel Ballesteros Vittorio Castelli Dan Roth 26 25 0 18 May 2023
On the Origins of Bias in NLP through the Lens of the Jim Code Fatma Elsafoury Gavin Abercrombie 44 4 0 16 May 2023
Surfacing Biases in Large Language Models using Contrastive Input Decoding G. Yona Or Honovich Itay Laish Roee Aharoni 27 11 0 12 May 2023
Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns Zhongbin Xie Vid Kocijan Thomas Lukasiewicz Oana-Maria Camburu 10 2 0 11 Feb 2023
Nationality Bias in Text Generation Pranav Narayanan Venkit Sanjana Gautam Ruchi Panchanadikar Ting-Hao 'Kenneth' Huang Shomir Wilson 33 51 0 05 Feb 2023
On the Blind Spots of Model-Based Evaluation Metrics for Text Generation Tianxing He Jingyu Zhang Tianle Wang Sachin Kumar Kyunghyun Cho James R. Glass Yulia Tsvetkov 40 44 0 20 Dec 2022
Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction Grace Yang Mingzi Cao L. Jiang Xujin C. Liu Alexander T. M. Cheung Hannah Weiss Davied Kurland Kyunghyun Cho Eric K. Oermann LM&MA 16 3 0 13 Nov 2022
Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information I. Nejadgholi Esma Balkir Kathleen C. Fraser S. Kiritchenko 40 3 0 19 Oct 2022
A Human Rights-Based Approach to Responsible AI Vinodkumar Prabhakaran Margaret Mitchell Timnit Gebru Iason Gabriel 41 36 0 06 Oct 2022
Re-contextualizing Fairness in NLP: The Case of India Shaily Bhatt Sunipa Dev Partha P. Talukdar Shachi Dave Vinodkumar Prabhakaran 14 54 0 25 Sep 2022
Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models Esma Balkir S. Kiritchenko I. Nejadgholi Kathleen C. Fraser 21 36 0 08 Jun 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
Fairness-aware Class Imbalanced Learning Shivashankar Subramanian Afshin Rahimi Timothy Baldwin Trevor Cohn Lea Frermann FaML 109 28 0 21 Sep 2021
Evaluating the Robustness of Neural Language Models to Input Perturbations M. Moradi Matthias Samwald AAML 48 95 0 27 Aug 2021
On Measures of Biases and Harms in NLP Sunipa Dev Emily Sheng Jieyu Zhao Aubrie Amstutz Jiao Sun ... M. Sanseverino Jiin Kim Akihiro Nishi Nanyun Peng Kai-Wei Chang 31 80 0 07 Aug 2021
Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics Paula Czarnowska Yogarshi Vyas Kashif Shah 21 104 0 28 Jun 2021
How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation Swaroop Mishra Anjana Arunkumar 34 24 0 10 Jun 2021
Re-imagining Algorithmic Fairness in India and Beyond Nithya Sambasivan Erin Arnesen Ben Hutchinson Tulsee Doshi Vinodkumar Prabhakaran FaML 17 174 0 25 Jan 2021
Interpretation of NLP models through input marginalization Siwon Kim Jihun Yi Eunji Kim Sungroh Yoon MILM FAtt 20 58 0 27 Oct 2020
Beyond Accuracy: Behavioral Testing of NLP models with CheckList Marco Tulio Ribeiro Tongshuang Wu Carlos Guestrin Sameer Singh ELM 19 1,081 0 08 May 2020
Social Biases in NLP Models as Barriers for Persons with Disabilities Ben Hutchinson Vinodkumar Prabhakaran Emily L. Denton Kellie Webster Yu Zhong Stephen Denuyl 11 302 0 02 May 2020
Deceptive AI Explanations: Creation and Detection Johannes Schneider Christian Meske Michalis Vlachos 14 28 0 21 Jan 2020