Explanation Quality Evaluation on LIAR-RAW (test)
1.53ChatGPT Meaningfulness ScoreOracle
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Oracle2025.11 | 1.53 | 4.5 | 4.77 | 4.77 | 1.47 | 3.61 | 3.89 | 3.86 | |
| S-EGS_LLaMA2Backbone=LLaMA-22025.11 | 1.65 | 4.79 | 4.86 | 4.88 | 1.75 | 3.76 | 3.92 | 3.96 | |
| L-Defense_ChatGPTBackbone=ChatGPT2025.11 | 1.77 | 4.4 | 4.6 | 4.53 | 1.97 | 3.68 | 3.52 | 3.56 | |
| L-Defense_LLaMA2Backbone=LLaMA-22025.11 | 1.87 | 4.5 | 4.67 | 4.67 | 2.12 | 3.48 | 3.37 | 3.49 | |
| w/o EGSBackbone=LLaMA-22025.11 | 1.89 | 4.76 | 4.78 | 4.5 | 2.35 | 3.48 | 3.36 | 2.62 | |
| ChatGPT_c,vBackbone=ChatGPT2025.11 | 2.07 | 4.43 | 4.67 | 4.73 | 2.22 | 3.22 | 3.38 | 3.57 | |
| ChatGPT_cBackbone=ChatGPT2025.11 | 2.33 | 4.17 | 4.43 | 4.63 | 2.68 | 2.68 | 2.84 | 3.27 |