OOF-AII-487868
Common Biases of Vector Embeddings
Researchers from Boston University and Microsoft Research, New England demonstrated gender bias in the most common techniques used to embed words for natural language processing (NLP).
- Event date
- 2016-07-21
- Country
- United States of America
- Severity
- Low
- Evidence state
- Single-source
Assessment status
Generated from available public incident evidence using OOF® governance methodology. It is not an official investigation, legal determination, regulatory finding, certification, or OOF® Approved Assessment.
View source record from AI Incident Database (Responsible AI Collaborative)
Assessment confidence dimensions
- Source corroboration
- Single-source
- Extraction completeness
- High
- Methodological assignment confidence
- Limited
Measures source-group corroboration only; it does not establish factual truth.
Measures populated source fields after deterministic normalization; it does not measure correctness.
Measures automated assignment support; substantive correctness requires authorized human review.
Known facts from the incident record
- The incident record identifies the event date as 2016-07-21.
- The incident record identifies the location as United States of America.
Reported claims
- Researchers from Boston University and Microsoft Research, New England demonstrated gender bias in the most common techniques used to embed words for natural language processing (NLP).
Material unknowns
- Independent corroboration is not established in the available incident record.
Primary governance problem
The incident appears to expose a governance problem involving models, demonstrated. Available reporting supports preliminary methodological interpretation, not a finding of fault or non-compliance.
Architecture intelligence
PGA™ — Prediction Governance Architecture
Primary architecture
The reported models, demonstrated concern falls within the governed questions represented by PGA™ — Prediction Governance Architecture.
Governance focus: How should models, demonstrated be governed in the conditions described by the available incident evidence?
Deeper methodology is withheld because the available evidence does not justify a Parent Standard or Core Module.
Preliminary governance questions
- How should models, demonstrated be governed in the conditions described by the available incident evidence?
- What operational authority and controls applied to Microsoft Research, Boston University at the relevant time?
- What evidence would establish how Word Embedding Models produced or enabled the reported outcome?
- What additional independent evidence is required to resolve the material evidence gaps?
Evidence gaps and limitations
- Only one independent source group is represented; corroboration is not established.
- AI technology is not specified in the source record.