DecompX: Explaining Transformers Decisions by Propagating Token Decomposition

5 June 2023

Papers citing "DecompX: Explaining Transformers Decisions by Propagating Token Decomposition"

10 / 10 papers shown

Title
Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers Tobias Leemann Alina Fastowski Felix Pfeiffer Gjergji Kasneci 51 4 0 10 Jan 2025
Interpreting token compositionality in LLMs: A robustness analysis Nura Aljaafari Danilo S. Carvalho André Freitas 25 0 0 16 Oct 2024
Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models Sepehr Kamahi Yadollah Yaghoobzadeh 32 0 0 21 Aug 2024
Explanation Regularisation through the Lens of Attributions Pedro Ferreira Wilker Aziz Ivan Titov 33 1 0 23 Jul 2024
Evaluating Human Alignment and Model Faithfulness of LLM Rationale Mohsen Fayyaz Fan Yin Jiao Sun Nanyun Peng 48 3 0 28 Jun 2024
Computational modeling of semantic change Nina Tahmasebi Haim Dubossarsky 26 6 0 13 Apr 2023
Quantifying Context Mixing in Transformers Hosein Mohebbi Willem H. Zuidema Grzegorz Chrupała A. Alishahi 164 24 0 30 Jan 2023
Towards Faithful Model Explanation in NLP: A Survey Qing Lyu Marianna Apidianaki Chris Callison-Burch XAI 104 107 0 22 Sep 2022
"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification Jasmijn Bastings Sebastian Ebert Polina Zablotskaia Anders Sandholm Katja Filippova 110 75 0 14 Nov 2021
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models Goro Kobayashi Tatsuki Kuribayashi Sho Yokoi Kentaro Inui 158 46 0 15 Sep 2021