Human Evaluation of Explanations on HealthVer
2.15Helpfulness (MAR)PromptBaseline
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PromptBaselineBase Model=Qwen2.5-14B-Instruct, Prompting Strategy=PromptBaseline2025.05 | 2.15 | 2.033 | 2.117 | 2.167 | 2.033 | |
| CLUE-Span+SteeringBase Model=Qwen2.5-14B-Instruct, Prompting Strategy=CLUE-Span+Steering2025.05 | 1.967 | 2.017 | 1.983 | 1.9 | 2.033 | |
| CLUE-SpanBase Model=Qwen2.5-14B-Instruct, Prompting Strategy=CLUE-Span2025.05 | 1.867 | 1.817 | 1.833 | 1.8 | 1.917 | |
| CLUEBackbone=Qwen2.5-14B-Instruct2025.05 | 0.772 | 0.751 | 0.784 | 0.727 | 0.667 | |
| PromptBaselineBackbone=Qwen2.5-14B-Instruct2025.05 | 0.25 | 0.27 | 0.242 | 0.266 | 0.336 |