notesum.ai
Published at October 30Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval
cs.AI
Released Date: October 30, 2024
Authors: Le Huang1, Hengzhi Lan1, Zijun Sun2, Chuan Shi1, Ting Bai1
Aff.: 1Beijing University of Posts and Telecommunications; 2Yunic.AI

| Agent Types | Methods | BFI | MBTI | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Acc(Dim) | Acc(Full) | MSE | MAE | Acc(Dim) | Acc(Full) | MSE | MAE | ||
| ChatGLM-6B | Ordinary RAG | 0.6242 | 0.1250 | 0.1849 | 0.3728 | 0.6694 | 0.2188 | 0.1526 | 0.3610 |
| Emotional RAG | 0.6369 | 0.0938 | 0.1720 | 0.3625 | 0.6694 | 0.2812 | 0.1539 | 0.3655 | |
| Qwen-72B | Ordinary RAG | 0.6815 | 0.0938 | 0.1433 | 0.3024 | 0.7438 | 0.3438 | 0.1230 | 0.2920 |
| Emotional RAG | 0.7261 | 0.2500 | 0.1269 | 0.2878 | 0.7934 | 0.4688 | 0.1156 | 0.2900 | |
| GPT-3.5 | Ordinary RAG | 0.7006 | 0.1875 | 0.1496 | 0.3121 | 0.7851 | 0.5000 | 0.1221 | 0.2965 |
| Emotional RAG | 0.7006 | 0.1875 | 0.1475 | 0.3082 | 0.7851 | 0.4375 | 0.1236 | 0.2927 | |