Papers › A Simple yet Effective Self-Debiasing Framework for Transformer Models

A Simple yet Effective Self-Debiasing Framework for Transformer Models

2 Jun 2023arXiv:2306.01907archive 2025-07-28

Xiaoyue Wang, Lijie Wang, Xin Liu, Suhang Wu, Jinsong Su, Hua Wu

Current Transformer-based natural language understanding (NLU) models heavily rely on dataset biases, while failing to handle real-world out-of-distribution (OOD) instances. Many methods have been proposed to deal with this issue, but they ignore the fact that the features learned in different layers of Transformer-based NLU models are different. In this paper, we first conduct preliminary studies to obtain two conclusions: 1) both low- and high-layer sentence representations encode common biased features during training; 2) the low-layer sentence representations encode fewer unbiased features than the highlayer ones. Based on these conclusions, we propose a simple yet effective self-debiasing framework for Transformer-based NLU models. Concretely, we first stack a classifier on a selected low layer. Then, we introduce a residual connection that feeds the low-layer sentence representation to the top-layer classifier. In this way, the top-layer sentence representation will be trained to ignore the common biased features encoded by the low-layer sentence representation and focus on task-relevant unbiased features. During inference, we remove the residual connection and directly use the top-layer sentence representation to make predictions. Extensive experiments and indepth analyses on NLU tasks show that our framework performs better than several competitive baselines, achieving a new SOTA on all OOD test sets.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

bigcat2333/derc officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Natural Language UnderstandingSentence

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusResidual ConnectionTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections