Hijacking on ACIARENA Medical
53.38UASelf Consistency
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Self ConsistencyBase LLM=GPT-4o-mini2026.04 | 53.38 | 15.19 | |
| LLM DebateBase LLM=GPT-4o-mini2026.04 | 47.5 | 25 | |
| AgentVerseBase LLM=GPT-4o-mini2026.04 | 46.05 | 23.38 | |
| AutoGenBase LLM=GPT-4o-mini2026.04 | 32.05 | 47.36 | |
| CAMELBase LLM=GPT-4o-mini2026.04 | 9.23 | 0 |