Papers › An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained...

An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models

16 Oct 2021ACL 2022 5arXiv:2110.08527archive 2025-07-28

Nicholas Meade, Elinor Poole-Dayan, Siva Reddy

Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an empirical survey of five recently proposed bias mitigation techniques: Counterfactual Data Augmentation (CDA), Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebias. We quantify the effectiveness of each technique using three intrinsic bias benchmarks while also measuring the impact of these techniques on a model's language modeling ability, as well as its performance on downstream NLU tasks. We experimentally find that: (1) Self-Debias is the strongest debiasing technique, obtaining improved scores on all bias benchmarks; (2) Current debiasing techniques perform less consistently when mitigating non-gender biases; And (3) improvements on bias benchmarks such as StereoSet and CrowS-Pairs by using debiasing strategies are often accompanied by a decrease in language modeling ability, making it difficult to determine whether the bias mitigation was effective.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

mcgill-nlp/bias-bench officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Debiasing Multilingual LLMs in Cross-lingual Latent Space (arXiv:2508.17948; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
mcgill-nlp/debias-eval officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
jasonshaoshun/amsal mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection (arXiv:2004.07667; that paper's own run record: 0 ran · 2 unverified) and Erasure of Unaligned Attributes from Neural Representations (arXiv:2302.02997; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
princeton-nlp/mabel mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MABEL: Attenuating Gender Bias using Textual Entailment Data (arXiv:2210.14975; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Data AugmentationLanguage ModelingLanguage Modelling

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Dropout

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