ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2406.12060
  4. Cited By
Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to
  Address Shortcut Shifts in Natural Language Understanding

Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding

17 June 2024
Ukyo Honda
Tatsushi Oka
Peinan Zhang
Masato Mita
ArXivPDFHTML

Papers citing "Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding"

4 / 4 papers shown
Title
Debiasing Masks: A New Framework for Shortcut Mitigation in NLU
Debiasing Masks: A New Framework for Shortcut Mitigation in NLU
Johannes Mario Meissner
Saku Sugawara
Akiko Aizawa
AAML
31
16
0
28 Oct 2022
Less is Better: Recovering Intended-Feature Subspace to Robustify NLU
  Models
Less is Better: Recovering Intended-Feature Subspace to Robustify NLU Models
Ting Wu
Tao Gui
32
5
0
16 Sep 2022
Competency Problems: On Finding and Removing Artifacts in Language Data
Competency Problems: On Finding and Removing Artifacts in Language Data
Matt Gardner
William Merrill
Jesse Dodge
Matthew E. Peters
Alexis Ross
Sameer Singh
Noah A. Smith
161
107
0
17 Apr 2021
Are We Modeling the Task or the Annotator? An Investigation of Annotator
  Bias in Natural Language Understanding Datasets
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets
Mor Geva
Yoav Goldberg
Jonathan Berant
235
319
0
21 Aug 2019
1