Public KG record
FairStress
Recorded overview
KG-recorded benchmark related to FairStress; detailed English notes are not yet available.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: 300个场景，覆盖29个领域
- Benchmarks: 身份信息与前缀组合扩展为超过1300万测试案例
- Benchmarks: 300个现实的双候选人决策场景，覆盖29个领域
- Benchmarks: 300个场景扩展为超过1300万个测试案例
- Capabilities: 比较身份信息和论据支持对象变化时的模型行为
- Use cases: 评估LLM在招聘、医疗、贷款、教育、住房等决策中的公平性
Evidence coverage
The KG currently records 6 known information dimensions and has 10 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- FairStress-Core — part of
- Claude Code — evaluated on
- Gemma — evaluated on
- GPT family — evaluated on
- Llama — evaluated on