Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI

25 September 2024

Papers citing "Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI"

45 / 45 papers shown

Title
Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection Saachi Jain Kimia Hamidieh Kristian Georgiev Andrew Ilyas Marzyeh Ghassemi Aleksander Madry 54 3 0 24 Jun 2024
What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions Sang Keun Choe Hwijeen Ahn Juhan Bae Kewen Zhao Minsoo Kang ... Teruko Mitamura Jeff Schneider Eduard Hovy Roger C. Grosse Eric Xing TDI 50 34 0 22 May 2024
Training Data Attribution via Approximate Unrolled Differentiation Juhan Bae Wu Lin Jonathan Lorraine Roger C. Grosse TDI MU 90 15 0 20 May 2024
Dissecting users' needs for search result explanations Prerna Juneja Wenjuan Zhang Alison Smith-Renner Hemank Lamba Joel R. Tetreault Alex Jaimes FAtt 31 5 0 29 Jan 2024
Error Discovery by Clustering Influence Embeddings Fulton Wang Julius Adebayo Sarah Tan Diego Garcia-Olano Narine Kokhlikyan 49 3 0 07 Dec 2023
Intriguing Properties of Data Attribution on Diffusion Models Xiaosen Zheng Tianyu Pang Chao Du Jing Jiang Min Lin TDI 57 25 1 01 Nov 2023
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models Yongchan Kwon Eric Wu K. Wu James Zou DiffM TDI 25 61 0 02 Oct 2023
Studying Large Language Model Generalization with Influence Functions Roger C. Grosse Juhan Bae Cem Anil Nelson Elhage Alex Tamkin ... Karina Nguyen Nicholas Joseph Sam McCandlish Jared Kaplan Sam Bowman TDI 14 164 0 07 Aug 2023
ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing Hua Shen Huang Chieh-Yang Tongshuang Wu Ting-Hao 'Kenneth' Huang 46 39 0 16 May 2023
In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making Raymond Fok Daniel S. Weld 54 62 0 12 May 2023
TRAK: Attributing Model Behavior at Scale Sung Min Park Kristian Georgiev Andrew Ilyas Guillaume Leclerc Aleksander Madry TDI 49 142 0 24 Mar 2023
Revisiting the Fragility of Influence Functions Jacob R. Epifano Ravichandran Ramachandran A. Masino Ghulam Rasool TDI 34 14 0 22 Mar 2023
Users are the North Star for AI Transparency Alex Mei Michael Stephen Saxon Shiyu Chang Zachary Chase Lipton William Yang Wang 45 9 0 09 Mar 2023
Invisible Users: Uncovering End-Users' Requirements for Explainable AI via Explanation Forms and Goals Weina Jin Jianyu Fan D. Gromala Philippe Pasquier Ghassan Hamarneh 38 7 0 10 Feb 2023
Training Data Influence Analysis and Estimation: A Survey Zayd Hammoudeh Daniel Lowd TDI 42 89 0 09 Dec 2022
Robust Speech Recognition via Large-Scale Weak Supervision Alec Radford Jong Wook Kim Tao Xu Greg Brockman C. McLeavey Ilya Sutskever OffRL 89 3,442 0 06 Dec 2022
Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations Yao Rong Tobias Leemann Thai-trang Nguyen Lisa Fiedler Peizhu Qian Vaibhav Unhelkar Tina Seidel Gjergji Kasneci Enkelejda Kasneci ELM 48 93 0 20 Oct 2022
If Influence Functions are the Answer, Then What is the Question? Juhan Bae Nathan Ng Alston Lo Marzyeh Ghassemi Roger C. Grosse TDI 43 92 0 12 Sep 2022
Visual correspondence-based explanations improve AI robustness and human-AI team accuracy Giang Nguyen Mohammad Reza Taesiri Anh Totti Nguyen 45 42 0 26 Jul 2022
Datamodels: Predicting Predictions from Training Data Andrew Ilyas Sung Min Park Logan Engstrom Guillaume Leclerc Aleksander Madry TDI 71 136 0 01 Feb 2022
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI Meike Nauta Jan Trienes Shreyasi Pathak Elisa Nguyen Michelle Peters Yasmin Schmitt Jorg Schlotterer M. V. Keulen C. Seifert ELM XAI 55 404 0 20 Jan 2022
HIVE: Evaluating the Human Interpretability of Visual Explanations Sunnie S. Y. Kim Nicole Meister V. V. Ramaswamy Ruth C. Fong Olga Russakovsky 74 114 0 06 Dec 2021
The Who in XAI: How AI Background Shapes Perceptions of AI Explanations Upol Ehsan Samir Passi Q. V. Liao Larry Chan I-Hsiang Lee Michael J. Muller Mark O. Riedl 39 88 0 28 Jul 2021
Combining Feature and Instance Attribution to Detect Artifacts Pouya Pezeshkpour Sarthak Jain Sameer Singh Byron C. Wallace TDI 44 43 0 01 Jul 2021
Interactive Label Cleaning with Example-based Explanations Stefano Teso A. Bontempelli Fausto Giunchiglia Andrea Passerini 43 45 0 07 Jun 2021
Input Similarity from the Neural Network Perspective Guillaume Charpiat N. Girard Loris Felardos Y. Tarabalka 32 71 0 10 Feb 2021
Expanding Explainability: Towards Social Transparency in AI systems Upol Ehsan Q. V. Liao Michael J. Muller Mark O. Riedl Justin D. Weisz 47 398 0 12 Jan 2021
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation Vitaly Feldman Chiyuan Zhang TDI 74 452 0 09 Aug 2020
Influence Functions in Deep Learning Are Fragile S. Basu Phillip E. Pope Soheil Feizi TDI 71 223 0 25 Jun 2020
Estimating Training Data Influence by Tracing Gradient Descent G. Pruthi Frederick Liu Mukund Sundararajan Satyen Kale TDI 23 389 0 19 Feb 2020
Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach Upol Ehsan Mark O. Riedl 22 216 0 04 Feb 2020
Questioning the AI: Informing Design Practices for Explainable AI User Experiences Q. V. Liao D. Gruen Sarah Miller 63 709 0 08 Jan 2020
PyTorch: An Imperative Style, High-Performance Deep Learning Library Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury ... Sasank Chilamkurthy Benoit Steiner Lu Fang Junjie Bai Soumith Chintala ODL 17 41,890 0 03 Dec 2019
On Second-Order Group Influence Functions for Black-Box Predictions S. Basu Xuchen You Soheil Feizi TDI 40 69 0 01 Nov 2019
On the Accuracy of Influence Functions for Measuring Group Effects Pang Wei Koh Kai-Siang Ang H. Teo Percy Liang TDI 27 187 0 30 May 2019
Sanity Checks for Saliency Maps Julius Adebayo Justin Gilmer M. Muelly Ian Goodfellow Moritz Hardt Been Kim FAtt AAML XAI 92 1,939 0 08 Oct 2018
Explanation in Artificial Intelligence: Insights from the Social Sciences Tim Miller XAI 195 4,216 0 22 Jun 2017
SmoothGrad: removing noise by adding noise D. Smilkov Nikhil Thorat Been Kim F. Viégas Martin Wattenberg FAtt ODL 161 2,211 0 12 Jun 2017
A Unified Approach to Interpreting Model Predictions Scott M. Lundberg Su-In Lee FAtt 36 21,459 0 22 May 2017
Understanding Black-box Predictions via Influence Functions Pang Wei Koh Percy Liang TDI 89 2,849 0 14 Mar 2017
Axiomatic Attribution for Deep Networks Mukund Sundararajan Ankur Taly Qiqi Yan OOD FAtt 52 5,920 0 04 Mar 2017
Towards A Rigorous Science of Interpretable Machine Learning Finale Doshi-Velez Been Kim XAI FaML 310 3,728 0 28 Feb 2017
"Why Should I Trust You?": Explaining the Predictions of Any Classifier Marco Tulio Ribeiro Sameer Singh Carlos Guestrin FAtt FaML 98 16,765 0 16 Feb 2016
Deep Residual Learning for Image Recognition Kaiming He Xinming Zhang Shaoqing Ren Jian Sun MedIm 671 192,387 0 10 Dec 2015
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps Karen Simonyan Andrea Vedaldi Andrew Zisserman FAtt 42 7,252 0 20 Dec 2013