Quantifying Context Mixing in Transformers

30 January 2023

Papers citing "Quantifying Context Mixing in Transformers"

8 / 8 papers shown

Title
SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation Dennis Fucci Marco Gaido Beatrice Savoldi Matteo Negri Mauro Cettolo L. Bentivogli 36 1 0 03 Nov 2024
Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models Sepehr Kamahi Yadollah Yaghoobzadeh 30 0 0 21 Aug 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 44 12 0 04 Dec 2023
Causal interventions expose implicit situation models for commonsense language understanding Takateru Yamakoshi James L. McClelland A. Goldberg Robert D. Hawkins 9 5 0 06 Jun 2023
The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective Satyapriya Krishna Tessa Han Alex Gu Steven Wu S. Jabbari Himabindu Lakkaraju 148 181 0 03 Feb 2022
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
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference Timo Schick Hinrich Schütze 248 1,382 0 21 Jan 2020