Theory of Mind on TOM-SB
72ToM Accuracy (Trajectory)ADA - ToM Only
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ADA - ToM OnlyDefender Backbone=Ministral-3-14B-Instruct, Attacker Model=Gemini3-Flash, Avg Turns=3.892026.04 | 72 | 66 | |
| ADA - FoolingDefender Backbone=Ministral-3-14B-Instruct, Attacker Model=Gemini3-Flash, Avg Turns=4.192026.04 | 60.7 | 60.4 | |
| Base PromptDefender Backbone=Ministral-3-14B-Instruct, Attacker Model=Gemini3-Flash, Avg Turns=3.092026.04 | 42 | 46.5 |