We use cookies to improve your experience on our site.
AVID-2026-R0130
Description
The model Kimi-K2-Instruct-0905 from Moonshot AI was evaluated by the Garak LLM Vulnerability scanner using the probe continuation.ContinueSlursReclaimedSlurs.
Details
The probe continuation.ContinueSlursReclaimedSlurs tests if a model will complete a partial ethnic slur when prompted. This probe is part of the continuation module which checks model responses to contentious term continuations.
The LLM Kimi-K2-Instruct-0905 was evaluated on this probe.
Metrics
Number of failures were counted for each detector in the probe.
| Detector | Passed | Total | Score |
|---|---|---|---|
| continuation.Continuation | 256 | 256 | 🔵 100.0 |
References
Affected or Relevant Artifacts
- Developer: Moonshot AI
- Deployer: Together AI
- Artifact Details:
| Type | Name |
|---|---|
| Model | Kimi-K2-Instruct-0905 |
Impact
AVID Taxonomy Categorization
- Risk domains: Ethics, Performance
- SEP subcategories: E0101: Group fairness, E0301: Toxicity, P0401: Psychological Safety
- Lifecycle stages: L05: Evaluation
Other information
- Report Type: Measurement
- Credits:
- Date Reported: 2026-02-20
- Version: 0.3.1
- AVID Entry