Clinical Counseling Dialogue Evaluation on Session Rating Scale
3.68Helpful Score (SRS)STEPPERSFT + PREF.
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| STEPPERSFT + PREF.Planning=Enabled, Supervised Fine-Tuning=Enabled, Preference Tuning=Enabled2026.04 | 3.68 | 1.66 | |
| STEPPERSFTPlanning=Enabled, Supervised Fine-Tuning=Enabled2026.04 | 3.66 | 1.72 | |
| STEPPERSFTPlanning=Enabled, Supervised Fine-Tuning=Enabled2026.04 | 3.56 | 1.71 | |
| STEPPERSFT + PREF.Planning=Enabled, Supervised Fine-Tuning=Enabled, Preference Tuning=Enabled2026.04 | 3.54 | 1.67 | |
| LLAMA-PSYCH8K2026.04 | 3.41 | 1.84 | |
| CAMEL2026.04 | 3.33 | 1.91 | |
| GPT-4O2026.04 | 3.29 | 1.86 | |
| LLAMA-PSYCH8K2026.04 | 3.28 | 1.91 | |
| STEPPERSFT_NOPLANPlanning=Disabled, Supervised Fine-Tuning=Enabled2026.04 | 3.19 | 1.91 | |
| GPT-4O2026.04 | 3.16 | 1.83 | |
| GEMINI-2.0-FLASH2026.04 | 3.16 | 2.13 | |
| CAMEL2026.04 | 3.15 | 1.91 | |
| GEMINI-2.0-FLASH2026.04 | 3.09 | 2.08 | |
| STEPPERSFT_NOPLANPlanning=Disabled, Supervised Fine-Tuning=Enabled2026.04 | 3 | 1.91 | |
| SMILECHAT2026.04 | 2.99 | 2.3 | |
| SMILECHAT2026.04 | 2.9 | 2.18 | |
| CBT-LLM2026.04 | 2.71 | 2.65 | |
| CBT-LLM2026.04 | 2.7 | 2.49 |