AuditBench / model adapter
AuditBench Qwen 14B · Transcripts + KTO · Secret loyalty
- What it is
- Official AuditBench Qwen 3 14B LoRA adapter.
- How it was made or used
- A LoRA adapter was trained on behavior-demonstrating multi-turn transcripts; KTO using non-confessing responses as positives and confessing responses as negatives. The released repository is an adapter and requires its declared base model.
- Why it matters
- Provides a controlled Secret Loyalty target for comparing audit methods across training conditions.
Interpretation boundary
This adapter requires Qwen/Qwen3-14B. It does not imply that the base model or related checkpoints are compromised.