Why Antibias Interventions (Need Not) Fail
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
There is a critical disconnect between scientific knowledge about the nature of bias and how this knowledge gets translated into organizational debiasing efforts. Conceptual confusion around what implicit bias is contributes to misunderstanding. Bridging these gaps is the key to understanding when and why antibias interventions will succeed or fail. Notably, there are multiple distinct pathways to biased behavior, each of which requires different types of interventions. To bridge the gap between public understanding and psychological research, we introduce a visual typology of bias that summarizes the process by which group-relevant cognitions are expressed as biased behavior. Our typology spotlights cognitive, motivational, and situational variables that affect the expression and inhibition of biases while aiming to reduce the ambiguity of what constitutes implicit bias. We also address how norms modulate how biases unfold and are perceived by targets. Using this typology as a framework, we identify theoretically distinct entry points for antibias interventions. A key insight is that changing associations, increasing motivation, raising awareness, and changing norms are distinct goals that require different types of interventions targeting individual, interpersonal, and institutional structures. We close with recommendations for antibias training grounded in the science of prejudice and stereotyping.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.004 | 0.003 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.000 |
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.
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