MétaCan
Menu
Back to cohort

Protecting marginalized communities by mitigating discrimination in toxic language detection

2021· article· en· W4200325561 on OpenAlexaff
Farshid Faal, Ketra Schmitt, Jia Yuan Yu

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicHate Speech and Cyberbullying Detection
Canadian institutionsConcordia University
Fundersnot available
KeywordsGeneralizability theoryComputer scienceLanguage identificationLanguage modelClassifier (UML)Artificial intelligenceMachine learningIdentification (biology)Natural language processingNatural languagePsychology

Abstract

fetched live from OpenAlex

As the harms of online toxic language become more apparent, countering online toxic behavior is an essential application of natural language processing. The first step in managing toxic language risk is identification, but algorithmic approaches have themselves demonstrated bias. Texts containing some demographic identity terms such as gay or Black are more likely to be labeled as toxic in existing toxic language detection datasets. In many machine learning models introduced for toxic language detection, non-toxic comments containing minority and marginalized community-specific identity terms were given unreasonably high toxicity scores. To address the challenge of bias in toxic language detection, we propose a two-step training approach. A pretrained language model with a multitask learning objective will mitigate biases in the toxicity classifier prediction. Experiments demonstrate that jointly training the pretrained language model with a multitask objective can effectively mitigate the impacts of unintended biases and is more robust to model bias towards commonly-attacked identity groups presented in datasets without significantly hurting the model’s generalizability.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.369
Threshold uncertainty score0.384

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.014
GPT teacher head0.241
Teacher spread0.228 · 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 teacher head, 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

Citations1
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicHate Speech and Cyberbullying DetectionFrench-language works237,207