From post

копировать удалить добавить публикацию в буфер
Запись сообщества
посмотреть историю данной записи
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Can We Really Trust Explanations? Evaluating the Stability of Feature Attribution Explanation Methods via Adversarial Attack.

Z. Yang, Y. Zhang, Z. Jiang, Y. Ju, J. Zhao, и K. Liu. CCL, том 13603 из Lecture Notes in Computer Science, стр. 281-297. Springer, (2022)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed.

Yiming Chen

Yiming Ma

Yiming Deng

Yiming Zhang

Yiming Wu

Другие публикации лиц с тем же именем

The Logic Traps in Evaluating Post-hoc Interpretations.Y. Ju, Y. Zhang, Z. Yang, Z. Jiang, K. Liu, и J. Zhao. CoRR, (2021)CMQA: A Dataset of Conditional Question Answering with Multiple-Span Answers.Y. Ju, W. Wang, Y. Zhang, S. Zheng, K. Liu, и J. Zhao. COLING, стр. 1697-1707. International Committee on Computational Linguistics, (2022)Generating Hierarchical Explanations on Text Classification Without Connecting Rules.Y. Ju, Y. Zhang, K. Liu, и J. Zhao. CoRR, (2022)Unsupervised Text Style Transfer with Deep Generative Models.Z. Jiang, Y. Zhang, Y. Ju, и K. Liu. CoRR, (2023)KLoB: a Benchmark for Assessing Knowledge Locating Methods in Language Models.Y. Ju, и Z. Zhang. CoRR, (2023)Explanation Guided Knowledge Distillation for Pre-trained Language Model Compression.Z. Yang, Y. Zhang, D. Sui, Y. Ju, J. Zhao, и K. Liu. ACM Trans. Asian Low Resour. Lang. Inf. Process., 23 (2): 32:1-32:19 (февраля 2024)Logic Traps in Evaluating Attribution Scores.Y. Ju, Y. Zhang, Z. Yang, Z. Jiang, K. Liu, и J. Zhao. ACL (1), стр. 5911-5922. Association for Computational Linguistics, (2022)Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations.Y. Ju, Y. Zhang, Z. Tian, K. Liu, X. Cao, W. Zhao, J. Li, и J. Zhao. EMNLP (1), стр. 3641-3652. Association for Computational Linguistics, (2021)A Hierarchical Explanation Generation Method Based on Feature Interaction Detection.Y. Ju, Y. Zhang, K. Liu, и J. Zhao. ACL (Findings), стр. 12600-12611. Association for Computational Linguistics, (2023)Can We Really Trust Explanations? Evaluating the Stability of Feature Attribution Explanation Methods via Adversarial Attack.Z. Yang, Y. Zhang, Z. Jiang, Y. Ju, J. Zhao, и K. Liu. CCL, том 13603 из Lecture Notes in Computer Science, стр. 281-297. Springer, (2022)

BibSonomy

Disambiguation