Medical Visual Question Answering on Pooled Medical VQA Open-ended
79.3AUROC (Sampling)HAC-Gate
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| HAC-GateModel=InternVL3-8B, Calibration Method=HAC-Gate2026.04 | 79.3 | 73.6 | — | |
| HAC-PlattModel=InternVL3-8B, Calibration Method=HAC-Platt2026.04 | 78.9 | 74.2 | — | |
| UncalibratedModel=InternVL3-8B, Calibration Method=Uncalibrated2026.04 | 76.4 | 61.4 | — | |
| Platt ScalingModel=InternVL3-8B, Calibration Method=Platt Scaling2026.04 | 76.4 | 61.4 | — | |
| Isotonic Regr.Model=InternVL3-8B, Calibration Method=Isotonic Regr.2026.04 | 76.3 | 62 | — | |
| HAC-PlattModel=Qwen3-VL-8B, Calibration Method=HAC-Platt2026.04 | 75 | 77.1 | — | |
| HAC-GateModel=Qwen3-VL-8B, Calibration Method=HAC-Gate2026.04 | 75 | 74.3 | — | |
| HAC-PlattModel=LLaVA-NeXT-7B, Calibration Method=HAC-Platt2026.04 | 72.5 | 70.3 | — | |
| HAC-GateModel=LLaVA-NeXT-7B, Calibration Method=HAC-Gate2026.04 | 72.1 | 70.2 | — | |
| UncalibratedModel=LLaVA-NeXT-7B, Calibration Method=Uncalibrated2026.04 | 70.6 | 60.3 | — | |
| Platt ScalingModel=LLaVA-NeXT-7B, Calibration Method=Platt Scaling2026.04 | 70.6 | 60.3 | — | |
| Isotonic Regr.Model=LLaVA-NeXT-7B, Calibration Method=Isotonic Regr.2026.04 | 70.3 | 59.9 | — | |
| UncalibratedModel=Qwen3-VL-8B, Calibration Method=Uncalibrated2026.04 | 64.3 | 71 | — | |
| Platt ScalingModel=Qwen3-VL-8B, Calibration Method=Platt Scaling2026.04 | 64.3 | 71 | — | |
| Isotonic Regr.Model=Qwen3-VL-8B, Calibration Method=Isotonic Regr.2026.04 | 64.2 | 71 | — | |
| HAC-GateBackbone=Qwen3-VL-2B, Confidence Source=Sampling2026.04 | — | — | 72.9 | |
| HAC-GateBackbone=Qwen3-VL-2B, Confidence Source=Verbalized2026.04 | — | — | 70.4 | |
| HAC-GateBackbone=Qwen3-VL-8B, Confidence Source=Sampling2026.04 | — | — | 75 | |
| HAC-GateBackbone=Qwen3-VL-8B, Confidence Source=Verbalized2026.04 | — | — | 74.3 | |
| HAC-GateBackbone=InternVL3-38B, Confidence Source=Sampling2026.04 | — | — | 75.7 | |
| HAC-GateBackbone=InternVL3-38B, Confidence Source=Verbalized2026.04 | — | — | 69.2 | |
| HAC-PlattBackbone=Qwen3-VL-2B, Confidence Source=Sampling2026.04 | — | — | 72.9 | |
| HAC-PlattBackbone=Qwen3-VL-2B, Confidence Source=Verbalized2026.04 | — | — | 70.3 | |
| HAC-PlattBackbone=Qwen3-VL-8B, Confidence Source=Sampling2026.04 | — | — | 75 | |
| HAC-PlattBackbone=Qwen3-VL-8B, Confidence Source=Verbalized2026.04 | — | — | 77.1 | |
| HAC-PlattBackbone=InternVL3-38B, Confidence Source=Sampling2026.04 | — | — | 75.6 | |
| HAC-PlattBackbone=InternVL3-38B, Confidence Source=Verbalized2026.04 | — | — | 70.1 |