Papers › Debiasing Methods in Natural Language Understanding Make Bias More Accessible

Debiasing Methods in Natural Language Understanding Make Bias More Accessible

9 Sep 2021EMNLP 2021 11arXiv:2109.04095archive 2025-07-28

Michael Mendelson, Yonatan Belinkov

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring models into making unbiased predictions. An underlying assumption behind such methods is that this also leads to the discovery of more robust features in the model's inner representations. We propose a general probing-based framework that allows for post-hoc interpretation of biases in language models, and use an information-theoretic approach to measure the extractability of certain biases from the model's representations. We experiment with several NLU datasets and known biases, and show that, counter-intuitively, the more a language model is pushed towards a debiased regime, the more bias is actually encoded in its inner representations.

PaperPDFConference PDFCode

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

Code

technion-cs-nlp/bias-probing officialmentioned in papermentioned on GitHubpytorch report
mzakizadeh/Gender-Encoding-Patterns mentioned on GitHubpytorch 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

Language ModelingLanguage ModellingNatural Language Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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