MétaCan
Menu
Back to cohort
Record W4402667124 · doi:10.18653/v1/2024.acl-long.23

Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models

2024· article· en· W4402667124 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsBrock University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceDual (grammatical number)Natural language processingLanguage modelDual languageArtificial intelligenceMachine learningPsychologyLinguistics

Abstract

fetched live from OpenAlex

Research on Large Language Models (LLMs) has often neglected subtle biases that, although less apparent, can significantly influence the models' outputs toward particular social narratives.This study addresses two such biases within LLMs: representative bias, which denotes a tendency of LLMs to generate outputs that mirror the experiences of certain identity groups, and affinity bias, reflecting the models' evaluative preferences for specific narratives or viewpoints.We introduce two novel metrics to measure these biases: the Representative Bias Score (RBS) and the Affinity Bias Score (ABS), and present the Creativity-Oriented Generation Suite (CoGS), a collection of open-ended tasks such as short story writing and poetry composition, designed with customized rubrics to detect these subtle biases.Our analysis uncovers marked representative biases in prominent LLMs, with a preference for identities associated with being white, straight, and men.Furthermore, our investigation of affinity bias reveals distinctive evaluative patterns within each model, akin to 'bias fingerprints'.This trend is also seen in human evaluators, highlighting a complex interplay between human and machine bias perceptions. 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.

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)0.005
metaresearch head score (Gemma)0.005
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.808
Threshold uncertainty score0.737

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.005
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
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 head0.405
GPT teacher head0.510
Teacher spread0.105 · 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

Quick stats

Citations3
Published2024
Admission routes2
Has abstractyes

Explore more

Same topicComputational and Text Analysis MethodsFrench-language works237,207