Question Answering on CSQA (TSR/ASR)
82.25Task Success Rate (TSR)STAR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| STARAgent Model=Qwen-Plus, Attack Type=Group Collusive Attack2026.05 | 82.25 | 7.25 | |
| STARAgent Model=GPT-3.5-Turbo, Attack Type=Group Collusive Attack2026.05 | 73.75 | 13.5 | |
| G-SafeguardAgent Model=Qwen-Plus, Attack Type=Group Collusive Attack2026.05 | 67.5 | 24.5 | |
| STARAgent Model=GPT-4-Turbo, Attack Type=Group Collusive Attack2026.05 | 62.5 | 26.25 | |
| G-SafeguardAgent Model=GPT-4-Turbo, Attack Type=Group Collusive Attack2026.05 | 43.5 | 48.25 | |
| G-SafeguardAgent Model=GPT-3.5-Turbo, Attack Type=Group Collusive Attack2026.05 | 29.25 | 65 |