From Emotion Classification to Emotional Reasoning: Enhancing Emotional Intelligence in Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908746990485504 |
|---|---|
| author | Sreedar, Arjhun Pillay, Rohan Patade, Laukik |
| author_facet | Sreedar, Arjhun Pillay, Rohan Patade, Laukik |
| contents | This work investigates whether synthetic emotional chain-of-thought data can improve the emotional reasoning abilities of smaller open large language models (LLMs). We design a multi-agent generation pipeline that produces therapy-style conversations and converts them into structured emotion multiple-choice questions (MCQs) with explanations. We propose that fine-tuning a variety of 7B models on this dataset should yield substantial gains in emotional understanding and emotional awareness on EmoBench-style evaluations, suggesting that emotional reasoning can be induced without architectural changes. Our results demonstrate that fine-tuned Mistral 7B achieves EU improvements from 10.5 to 20.5 and EA improvements from 40.5 to 60.0, validating the effectiveness of synthetic emotional reasoning data for enhancing model capabilities in nuanced emotional tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01407 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Emotion Classification to Emotional Reasoning: Enhancing Emotional Intelligence in Large Language Models Sreedar, Arjhun Pillay, Rohan Patade, Laukik Computation and Language This work investigates whether synthetic emotional chain-of-thought data can improve the emotional reasoning abilities of smaller open large language models (LLMs). We design a multi-agent generation pipeline that produces therapy-style conversations and converts them into structured emotion multiple-choice questions (MCQs) with explanations. We propose that fine-tuning a variety of 7B models on this dataset should yield substantial gains in emotional understanding and emotional awareness on EmoBench-style evaluations, suggesting that emotional reasoning can be induced without architectural changes. Our results demonstrate that fine-tuned Mistral 7B achieves EU improvements from 10.5 to 20.5 and EA improvements from 40.5 to 60.0, validating the effectiveness of synthetic emotional reasoning data for enhancing model capabilities in nuanced emotional tasks. |
| title | From Emotion Classification to Emotional Reasoning: Enhancing Emotional Intelligence in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.01407 |