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

6 May 2022

Ali Modarressi

Mohsen Fayyaz

Yadollah Yaghoobzadeh

Mohammad Taher Pilehvar

ViT

ArXiv PDF HTML

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

27 / 27 papers shown

Title
Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation Chiara Manna Afra Alishahi Frédéric Blain Eva Vanmassenhove 27 0 0 13 May 2025
From Text to Graph: Leveraging Graph Neural Networks for Enhanced Explainability in NLP Fabio Yáñez-Romero Andrés Montoyo Armando Suárez Yoan Gutiérrez Ruslan Mitkov 51 0 0 02 Apr 2025
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence Mohsen Fayyaz Ali Modarressi Hinrich Schuetze Nanyun Peng 62 1 0 06 Mar 2025
A Close Look at Decomposition-based XAI-Methods for Transformer Language Models L. Arras Bruno Puri Patrick Kahardipraja Sebastian Lapuschkin Wojciech Samek 46 1 0 21 Feb 2025
Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers Tobias Leemann Alina Fastowski Felix Pfeiffer Gjergji Kasneci 62 5 0 10 Jan 2025
How Language Models Prioritize Contextual Grammatical Cues? Hamidreza Amirzadeh A. Alishahi Hosein Mohebbi 26 0 0 04 Oct 2024
Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models Sepehr Kamahi Yadollah Yaghoobzadeh 53 0 0 21 Aug 2024
Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI Adrian Jaques Böck D. Slijepcevic Matthias Zeppelzauer 44 0 0 25 Jul 2024
Explanation Regularisation through the Lens of Attributions Pedro Ferreira Wilker Aziz Ivan Titov 46 1 0 23 Jul 2024
Evaluating Human Alignment and Model Faithfulness of LLM Rationale Mohsen Fayyaz Fan Yin Jiao Sun Nanyun Peng 65 3 0 28 Jun 2024
InternalInspector $I^2$ : Robust Confidence Estimation in LLMs through Internal States Mohammad Beigi Ying Shen Runing Yang Zihao Lin Qifan Wang Ankith Mohan Jianfeng He Ming Jin Chang-Tien Lu Lifu Huang HILM 36 4 0 17 Jun 2024
An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records Joakim Edin Maria Maistro Lars Maaløe Lasse Borgholt Jakob Drachmann Havtorn Tuukka Ruotsalo FAtt 40 2 0 13 Jun 2024
Unveiling and Manipulating Prompt Influence in Large Language Models Zijian Feng Hanzhang Zhou Zixiao Zhu Junlang Qian Kezhi Mao 45 2 0 20 May 2024
Isotropy, Clusters, and Classifiers Timothee Mickus Stig-Arne Gronroos Joseph Attieh 38 0 0 05 Feb 2024
From Understanding to Utilization: A Survey on Explainability for Large Language Models Haoyan Luo Lucia Specia 56 20 0 23 Jan 2024
Better Explain Transformers by Illuminating Important Information Linxin Song Yan Cui Ao Luo Freddy Lecue Irene Z Li FAtt 30 1 0 18 Jan 2024
A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia Giovanni Monea Maxime Peyrard Martin Josifoski Vishrav Chaudhary Jason Eisner Emre Kiciman Hamid Palangi Barun Patra Robert West KELM 51 12 0 04 Dec 2023
Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers Hosein Mohebbi Grzegorz Chrupała Willem H. Zuidema A. Alishahi 36 12 0 15 Oct 2023
Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings Timothee Mickus Raúl Vázquez 25 2 0 10 Oct 2023
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition Ali Modarressi Mohsen Fayyaz Ehsan Aghazadeh Yadollah Yaghoobzadeh Mohammad Taher Pilehvar 33 26 0 05 Jun 2023
Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection Vyoma Raman Eve Fleisig Dan Klein 27 0 0 24 May 2023
Computational modeling of semantic change Nina Tahmasebi Haim Dubossarsky 34 6 0 13 Apr 2023
Inseq: An Interpretability Toolkit for Sequence Generation Models Gabriele Sarti Nils Feldhus Ludwig Sickert Oskar van der Wal Malvina Nissim Arianna Bisazza 32 64 0 27 Feb 2023
Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps Goro Kobayashi Tatsuki Kuribayashi Sho Yokoi Kentaro Inui 33 14 0 01 Feb 2023
Quantifying Context Mixing in Transformers Hosein Mohebbi Willem H. Zuidema Grzegorz Chrupała A. Alishahi 168 24 0 30 Jan 2023
Measuring the Mixing of Contextual Information in the Transformer Javier Ferrando Gerard I. Gállego Marta R. Costa-jussá 31 50 0 08 Mar 2022
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models Goro Kobayashi Tatsuki Kuribayashi Sho Yokoi Kentaro Inui 160 46 0 15 Sep 2021