All Roads Lead to Rome? Exploring the Invariance of Transformers'
Representations

All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations

23 May 2023

Qipeng Guo

Shauli Ravfogel

Mrinmaya Sachan

Bernhard Schölkopf

Papers citing "All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations"

7 / 7 papers shown

Title
On Affine Homotopy between Language Encoders Robin SM Chan Reda Boumasmoud Anej Svete Yuxin Ren Qipeng Guo ... Shauli Ravfogel Mrinmaya Sachan Bernhard Schölkopf Mennatallah El-Assady Ryan Cotterell 38 3 0 04 Jun 2024
Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch Xin-Chun Li Wen-Shu Fan Bowen Tao Le Gan De-Chuan Zhan 19 2 0 21 May 2024
Merging Text Transformer Models from Different Initializations Neha Verma Maha Elbayad MoMe 53 7 0 01 Mar 2024
Understanding the Inner Workings of Language Models Through Representation Dissimilarity Davis Brown Charles Godfrey N. Konz Jonathan Tu Henry Kvinge 32 7 0 23 Oct 2023
Git Re-Basin: Merging Models modulo Permutation Symmetries Samuel K. Ainsworth J. Hayase S. Srinivasa MoMe 243 313 0 11 Sep 2022
Training language models to follow instructions with human feedback Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright ... Amanda Askell Peter Welinder Paul Christiano Jan Leike Ryan J. Lowe OSLM ALM 308 11,909 0 04 Mar 2022
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding Alex Jinpeng Wang Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 294 6,950 0 20 Apr 2018