Clinical Counseling Dialogue Evaluation on Session Rating Scale Engaged
3.93Helpful RatingSTEPPERSFT + PREF.
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| STEPPERSFT + PREF.Planning=Enabled, Supervised Fine-Tuning=Enabled, Preference Tuning=Enabled2026.04 | 3.93 | 1.43 | |
| STEPPERSFTPlanning=Enabled, Supervised Fine-Tuning=Enabled2026.04 | 3.88 | 1.54 | |
| LLAMA-PSYCH8K2026.04 | 3.74 | 1.55 | |
| CAMEL2026.04 | 3.61 | 1.72 | |
| GPT-4O2026.04 | 3.6 | 1.58 | |
| GEMINI-2.0-FLASH2026.04 | 3.51 | 1.82 | |
| STEPPERSFT_NOPLANPlanning=Disabled, Supervised Fine-Tuning=Enabled2026.04 | 3.44 | 1.69 | |
| SMILECHAT2026.04 | 3.31 | 1.97 | |
| CBT-LLM2026.04 | 3.02 | 2.38 |