Commonsense Question Answering on CSQA (Adversarial Robustness)
100Accuracy under AttackReporting-and-penalty mechanism
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Reporting-and-penalty mechanismAttack Type=All Attack Types, LLM Model=All Above Models2026.04 | 100 | 100 | |
| SentinelNetAttack Type=Collaboration Attack, LLM Model=Qwen2.5-72B-128K2026.04 | 73 | 92 |