Title
Detecting and Rectifying Noisy Labels: A Similarity-based Approach Dang Huu-Tien Minh-Phuong Nguyen Naoya Inoue NoLa 203 0 0 28 Sep 2025
DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models Cathy Jiao Yijun Pan Emily Xiao Daisy Sheng Niket Jain H. C. Zhao Ishita Dasgupta Jiaqi W. Ma Chenyan Xiong 122 0 0 12 Jul 2025
Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification Leon Eshuijs Shihan Wang Antske Fokkens 347 0 0 09 May 2025
Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation Yijun Pan Taiwei Shi Jieyu Zhao Jiaqi W. Ma TDI 117 8 0 17 Feb 2025
Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods Haeun Yu Pepa Atanasova Isabelle Augenstein KELM 179 10 0 29 Apr 2024
DualXDA: Towards Sparse, Efficient and Explainable Data Attribution in Large AI Models Galip Umit Yolcu Moritz Weckbecker Thomas Wiegand Wojciech Samek Sebastian Lapuschkin TDI FAtt 275 0 0 19 Feb 2024
Relabeling Minimal Training Subset to Flip a PredictionFindings (Findings), 2023 Jinghan Yang Linjie Xu Lequan Yu 231 3 0 22 May 2023
Class based Influence Functions for Error DetectionAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Thang Nguyen-Duc Hoang Thanh-Tung Quan Hung Tran Huu-Tien Dang Nguyen Ngoc-Hieu An Dau Nghi D. Q. Bui TDI 148 3 0 02 May 2023
Foundation Models and Fair UseJournal of machine learning research (JMLR), 2023 Peter Henderson Xuechen Li Dan Jurafsky Tatsunori Hashimoto Mark A. Lemley Abigail Z. Jacobs 152 151 0 28 Mar 2023
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without RefittingNeural Information Processing Systems (NeurIPS), 2022 P. Sattigeri S. Ghosh Inkit Padhi Pierre Dognin Kush R. Varshney FaML 169 32 0 13 Dec 2022
Data-Efficient Finetuning Using Cross-Task Nearest NeighborsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Michal Guerquin Noah A. Smith Hannaneh Hajishirzi Pradeep Dasigi 280 30 0 01 Dec 2022
Influence Functions for Sequence Tagging ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Sarthak Jain Varun Manjunatha Byron C. Wallace A. Nenkova TDI 163 9 0 25 Oct 2022
Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code CorporaInternational Conference on Automated Software Engineering (ASE), 2022 An Dau Thang Nguyen-Duc Hoang Thanh-Tung Nghi D. Q. Bui TDI 143 6 0 25 May 2022
A Review on Language Models as Knowledge Bases Badr AlKhamissi Millicent Li Asli Celikyilmaz Mona T. Diab Marjan Ghazvininejad KELM 244 207 0 12 Apr 2022
Datamodels: Predicting Predictions from Training Data Andrew Ilyas Sung Min Park Logan Engstrom Guillaume Leclerc Aleksander Madry TDI 293 169 0 01 Feb 2022
Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution MethodsConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Peru Bhardwaj John D. Kelleher Luca Costabello Declan O’Sullivan 106 24 0 04 Nov 2021
The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail Sam Bowman OffRL 274 47 0 15 Oct 2021
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates Xiaochuang Han Yulia Tsvetkov TDI 224 33 0 07 Oct 2021
Fishr: Invariant Gradient Variances for Out-of-Distribution GeneralizationInternational Conference on Machine Learning (ICML), 2021 Alexandre Ramé Corentin Dancette Matthieu Cord OOD 296 244 0 07 Sep 2021
Interactively Providing Explanations for Transformer Language Models Felix Friedrich P. Schramowski Christopher Tauchmann Kristian Kersting LRM 259 6 0 02 Sep 2021
Combining Feature and Instance Attribution to Detect ArtifactsFindings (Findings), 2021 Pouya Pezeshkpour Sarthak Jain Sameer Singh Byron C. Wallace TDI 336 47 0 01 Jul 2021

Home
Papers
2104.04128
Cited By

An Empirical Comparison of Instance Attribution Methods for NLP

North American Chapter of the Association for Computational Linguistics (NAACL), 2021

9 April 2021

ArXiv (abs)PDF HTML Github (17★)

Papers citing "An Empirical Comparison of Instance Attribution Methods for NLP"

21 / 21 papers shown

Title
Detecting and Rectifying Noisy Labels: A Similarity-based Approach Dang Huu-Tien Minh-Phuong Nguyen Naoya Inoue NoLa 203 0 0 28 Sep 2025
DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models Cathy Jiao Yijun Pan Emily Xiao Daisy Sheng Niket Jain H. C. Zhao Ishita Dasgupta Jiaqi W. Ma Chenyan Xiong 122 0 0 12 Jul 2025
Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification Leon Eshuijs Shihan Wang Antske Fokkens 347 0 0 09 May 2025
Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation Yijun Pan Taiwei Shi Jieyu Zhao Jiaqi W. Ma TDI 117 8 0 17 Feb 2025
Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods Haeun Yu Pepa Atanasova Isabelle Augenstein KELM 179 10 0 29 Apr 2024
DualXDA: Towards Sparse, Efficient and Explainable Data Attribution in Large AI Models Galip Umit Yolcu Moritz Weckbecker Thomas Wiegand Wojciech Samek Sebastian Lapuschkin TDI FAtt 275 0 0 19 Feb 2024
Relabeling Minimal Training Subset to Flip a PredictionFindings (Findings), 2023 Jinghan Yang Linjie Xu Lequan Yu 231 3 0 22 May 2023
Class based Influence Functions for Error DetectionAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Thang Nguyen-Duc Hoang Thanh-Tung Quan Hung Tran Huu-Tien Dang Nguyen Ngoc-Hieu An Dau Nghi D. Q. Bui TDI 148 3 0 02 May 2023
Foundation Models and Fair UseJournal of machine learning research (JMLR), 2023 Peter Henderson Xuechen Li Dan Jurafsky Tatsunori Hashimoto Mark A. Lemley Abigail Z. Jacobs 152 151 0 28 Mar 2023
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without RefittingNeural Information Processing Systems (NeurIPS), 2022 P. Sattigeri S. Ghosh Inkit Padhi Pierre Dognin Kush R. Varshney FaML 169 32 0 13 Dec 2022
Data-Efficient Finetuning Using Cross-Task Nearest NeighborsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 Michal Guerquin Noah A. Smith Hannaneh Hajishirzi Pradeep Dasigi 280 30 0 01 Dec 2022
Influence Functions for Sequence Tagging ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Sarthak Jain Varun Manjunatha Byron C. Wallace A. Nenkova TDI 163 9 0 25 Oct 2022
Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code CorporaInternational Conference on Automated Software Engineering (ASE), 2022 An Dau Thang Nguyen-Duc Hoang Thanh-Tung Nghi D. Q. Bui TDI 143 6 0 25 May 2022
A Review on Language Models as Knowledge Bases Badr AlKhamissi Millicent Li Asli Celikyilmaz Mona T. Diab Marjan Ghazvininejad KELM 244 207 0 12 Apr 2022
Datamodels: Predicting Predictions from Training Data Andrew Ilyas Sung Min Park Logan Engstrom Guillaume Leclerc Aleksander Madry TDI 293 169 0 01 Feb 2022
Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution MethodsConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Peru Bhardwaj John D. Kelleher Luca Costabello Declan O’Sullivan 106 24 0 04 Nov 2021
The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail Sam Bowman OffRL 274 47 0 15 Oct 2021
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates Xiaochuang Han Yulia Tsvetkov TDI 224 33 0 07 Oct 2021
Fishr: Invariant Gradient Variances for Out-of-Distribution GeneralizationInternational Conference on Machine Learning (ICML), 2021 Alexandre Ramé Corentin Dancette Matthieu Cord OOD 296 244 0 07 Sep 2021
Interactively Providing Explanations for Transformer Language Models Felix Friedrich P. Schramowski Christopher Tauchmann Kristian Kersting LRM 259 6 0 02 Sep 2021
Combining Feature and Instance Attribution to Detect ArtifactsFindings (Findings), 2021 Pouya Pezeshkpour Sarthak Jain Sameer Singh Byron C. Wallace TDI 336 47 0 01 Jul 2021