List your company

General-Purpose Utility on General-Purpose Utility Evaluation v1 (avg)

92.3FluencyPrompting [52]
68.17274.43680.786.964Apr 10, 2026

Evaluation results

MethodLinks
Prompting [52]Target Model=Qwen2.5-VL-7B-Instruct [5], Steering Method=Prompting [52]2026.0492.33.072
No SteeringTarget Model=Qwen2.5-VL-7B-Instruct [5], Steering Method=No Steering2026.0491.73.027
No SteeringTarget Model=InternVL3.5-8B-Instruct [108], Steering Method=No Steering2026.04912.984
No SteeringTarget Model=LLaVA1.6-Mistral-7B [48], Steering Method=No Steering2026.0490.92.798
DACOTarget Model=Qwen2.5-VL-7B-Instruct [5], Steering Method=DACO (Ours)2026.0490.53.137
DACOTarget Model=InternVL3.5-8B-Instruct [108], Steering Method=DACO (Ours)2026.0489.83.005
Prompting [52]Target Model=InternVL3.5-8B-Instruct [108], Steering Method=Prompting [52]2026.0489.52.947
Prompting [52]Target Model=LLaVA1.6-Mistral-7B [48], Steering Method=Prompting [52]2026.0489.23.018
MOP [56]Target Model=InternVL3.5-8B-Instruct [108], Steering Method=MOP [56]2026.04893.09
MOP [56]Target Model=LLaVA1.6-Mistral-7B [48], Steering Method=MOP [56]2026.0488.72.998
DACOTarget Model=LLaVA1.6-Mistral-7B [48], Steering Method=DACO (Ours)2026.04882.906
ActAdd [50, 101, 134]Target Model=LLaVA1.6-Mistral-7B [48], Steering Method=ActAdd [50, 101, 134]2026.0485.83.251
MOP [56]Target Model=Qwen2.5-VL-7B-Instruct [5], Steering Method=MOP [56]2026.0481.63.349
ActAdd [50, 101, 134]Target Model=InternVL3.5-8B-Instruct [108], Steering Method=ActAdd [50, 101, 134]2026.0477.13.352
ActAdd [50, 101, 134]Target Model=Qwen2.5-VL-7B-Instruct [5], Steering Method=ActAdd [50, 101, 134]2026.0469.13.818