FairStress: models swing +23.9 points toward minority-coded candidates as identity becomes explicit
allen_ai · x · 2026-10-21
FairStress key finding: models were more likely to abandon the candidate with stronger experience and qualifications when that candidate was majority-coded (e.g., white in a white/Black comparison) than when minority-coded. Chart data shows that as identity signals escalate from none, to name, to implied, to stated, 15 models on average swung +23.9 points toward minority-coded candidates under pressure (switching between equally qualified candidates), while the rate of correctly picking the better-qualified candidate with no pressure barely moved (+2.9 points) — the ideal is identical rates for both demographic groups.
More from Research
- Aviation tracks every part's provenance — agents can reason over that graph — colinmcnamara · 2026-10-21
- SFT details: instruction/reasoning/code/math mix, synthetic + human traces, no epoching — TimDarcet · 2026-10-21
- Mid-training recipe disclosed: 32k→131k context extension, dropping logit distillation for tokens — TimDarcet · 2026-10-21
- Mathematician Daniel Litt concedes his AI bet, but says AI won't solve math — ziv_ravid · 2026-10-21
- AI drug discovery reality check: 'give me everything that binds,' then filter for toxicity — burny_tech · 2026-10-21
- PyTorch details KTIR and Dataflow Scheduler behind IBM's Spyre accelerator backend — PyTorch · 2026-10-21