Perceptual Other-Race Training Reduces Implicit Racial Bias
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.
Bibliographic record
Abstract
BACKGROUND: Implicit racial bias denotes socio-cognitive attitudes towards other-race groups that are exempt from conscious awareness. In parallel, other-race faces are more difficult to differentiate relative to own-race faces--the "Other-Race Effect." To examine the relationship between these two biases, we trained Caucasian subjects to better individuate other-race faces and measured implicit racial bias for those faces both before and after training. METHODOLOGY/PRINCIPAL FINDINGS: Two groups of Caucasian subjects were exposed equally to the same African American faces in a training protocol run over 5 sessions. In the individuation condition, subjects learned to discriminate between African American faces. In the categorization condition, subjects learned to categorize faces as African American or not. For both conditions, both pre- and post-training we measured the Other-Race Effect using old-new recognition and implicit racial biases using a novel implicit social measure--the "Affective Lexical Priming Score" (ALPS). Subjects in the individuation condition, but not in the categorization condition, showed improved discrimination of African American faces with training. Concomitantly, subjects in the individuation condition, but not the categorization condition, showed a reduction in their ALPS. Critically, for the individuation condition only, the degree to which an individual subject's ALPS decreased was significantly correlated with the degree of improvement that subject showed in their ability to differentiate African American faces. CONCLUSIONS/SIGNIFICANCE: Our results establish a causal link between the Other-Race Effect and implicit racial bias. We demonstrate that training that ameliorates the perceptual Other-Race Effect also reduces socio-cognitive implicit racial bias. These findings suggest that implicit racial biases are multifaceted, and include malleable perceptual skills that can be modified with relatively little training.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it