Research map / Reinforcement learning / RL from feedback
Facilitating Early Maladaptive Schema–Guided Polite and Empathetic Psychotherapeutic Support: An LLM-Driven MoE-RL-Based Dialogue System
Priyanshu Priya, Asif Ekbal
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| MATE (LLM + MoE-RL with experts and composite reward) versus Phi-3-FT | Phi-3-mini · HOPE | SSSC: 0.671 -> 0.726 | Improved |
| MATE versus Phi-3-FT | Phi-3-mini · PSYCON | SSSC: 0.671 -> 0.819 | Improved |
| MATE versus Phi-3-FT | Phi-3-mini · HOPE | BLEU-3: 7.03 -> 8.95 | Improved |
| MATE versus Phi-3-FT | Phi-3-mini · PSYCON | Perplexity: 2.41 -> 1.09 | Improved |
| MATE versus Phi-3-FT human evaluation | Phi-3-mini · HOPE (human eval) | Fluency: 3.91 -> 4.62 | Improved |
| MATE versus ProCoT (ChatGPT) | ChatGPT · PSYCON | D-3: 3.46 -> 8.31 | Improved |
| MATE versus e-Therapist | e-Therapist · HOPE | EESC: 0.549 -> 0.683 | Improved |
Closest papers by meaning
- RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents (ICLR 2026 · similarity 0.86)
- TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots (NeurIPS 2026 · similarity 0.86)
- Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care (ICML 2025 · similarity 0.85)
- STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling (AAAI 2025 · similarity 0.85)
- Reinforce Trustworthiness in Multimodal Emotional Support System (AAAI 2026 · similarity 0.85)
- EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
