Automated Evaluation Framework Alignment on AI-Generated Explorable Explanations Biased Data 1.0
0.178Functional PCCVLM (Baseline 1)
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| VLM (Baseline 1)Framework=VLM (Baseline 1), Model=GPT-4o-mini2026.06 | 0.178 | 0.674 | -0.019 | 0.001 | 0.242 | |
| FSM-basedFramework=FSM-based2026.06 | 0.065 | -0.148 | 0.21 | 0.125 | 0.079 | |
| Unit test (Baseline 2)Framework=Unit test (Baseline 2), Tool=Playwright2026.06 | -0.189 | -0.298 | -0.09 | 0.029 | -0.162 |