Library

GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers

Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Topic ModelingNatural Language Processing TechniquesExplainable Artificial Intelligence (XAI)
View graphSource

Paper

The full text of this publication is not hosted on 44B due to licensing.

Read it at OpenAlex

Similar papers

GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in TransformersAli Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh et al.2022 · North American Chapter of the Association for Computational Linguistics · 60 citations In Library
An Attribution Method for Siamese EncodersLucas Möller, Dmitry Nikolaev, Sebastian Padó2023 · arXiv (Cornell University) · 10 citations In Library
Quantifying the Overlap: Attribution Maps and Linguistic Heuristics in Encoder-Decoder Machine Translation ModelsAria Nourbakhsh, Salima Lamsiyah, Christoph Schommer2025 · International conference Recent advances in natural language processing · 1 citation In Library
DecompX: Explaining Transformers Decisions by Propagating Token DecompositionAli Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh et al.2023 In Library
An Attribution Method for Siamese EncodersLucas Moeller, Dmitry Nikolaev, Sebastian Padó2023 In Library
Every Component is a Lookup: Token Attribution and Composition from a Single DecompositionPo-Kai Chen, Niki van Stein, A. Plaat2026 · 0 citations In Library
On Identifiability in TransformersGino Brunner, Yang Liu, Damián Pascual et al.2020 · International Conference on Learning Representations In Library
Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer NetworkJiayi Ji, Yunpeng Luo, Xiaoshuai Sun et al.2021 · Proceedings of the AAAI Conference on Artificial Intelligence In Library
Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer NetworkJiayi Ji, Yunpeng Luo, Xiaoshuai Sun et al.2020 · arXiv (Cornell University) · 210 citations In Library
Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target PropagationLasse M. Jantsch, Dong-Jae Koh, Seonghyeon Lee et al.2026 · 0 citations In Library
© 2026 NYSGPT2525 LLC