Measuring the Mixing of Contextual Information in the Transformer

8 March 2022

Papers citing "Measuring the Mixing of Contextual Information in the Transformer"

10 / 10 papers shown

Title
Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models Sepehr Kamahi Yadollah Yaghoobzadeh 30 0 0 21 Aug 2024
Evaluating Human Alignment and Model Faithfulness of LLM Rationale Mohsen Fayyaz Fan Yin Jiao Sun Nanyun Peng 35 3 0 28 Jun 2024
Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers Hosein Mohebbi Grzegorz Chrupała Willem H. Zuidema A. Alishahi 15 11 0 15 Oct 2023
Explaining How Transformers Use Context to Build Predictions Javier Ferrando Gerard I. Gállego Ioannis Tsiamas Marta R. Costa-jussá 8 31 0 21 May 2023
Computational modeling of semantic change Nina Tahmasebi Haim Dubossarsky 26 6 0 13 Apr 2023
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer Javier Ferrando Gerard I. Gállego Belen Alastruey Carlos Escolano Marta R. Costa-jussá 12 44 0 23 May 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 102 75 0 14 Nov 2021
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining Andreas Madsen Nicholas Meade Vaibhav Adlakha Siva Reddy 96 35 0 15 Oct 2021
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models Goro Kobayashi Tatsuki Kuribayashi Sho Yokoi Kentaro Inui 153 45 0 15 Sep 2021
All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality William Timkey Marten van Schijndel 213 110 0 09 Sep 2021