MétaCan
Menu
Back to cohort
Record W3206487987 · doi:10.18653/v1/2022.acl-long.132

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

2022· article· en· W3206487987 on OpenAlexafffund
Nicholas Meade, Elinor Poole-Dayan, Siva Reddy

Bibliographic record

VenueProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2022
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsMcGill University
FundersInstitut de Valorisation des DonnéesNatural Sciences and Engineering Research Council of CanadaCanadian Institute for Advanced Research
KeywordsDebiasingCounterfactual thinkingComputer scienceDropout (neural networks)Machine learningArtificial intelligencePsychologySocial psychology

Abstract

fetched live from OpenAlex

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.1

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.019
metaresearch head score (Gemma)0.078
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.019
Threshold uncertainty score0.099

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0190.078
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0010.001
Scholarly communication0.0020.004
Open science0.0020.002
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.017
GPT teacher head0.296
Teacher spread0.279 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations109
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)Same topicTopic ModelingFrench-language works237,207