Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.00552 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912968146419712 |
|---|---|
| author | Zhang, Shiya Zhan, Yuhan Su, Ruixi Sun, Ruihan Song, Ziyi Chen, Zhaohan Zhang, Xiaofan |
| author_facet | Zhang, Shiya Zhan, Yuhan Su, Ruixi Sun, Ruihan Song, Ziyi Chen, Zhaohan Zhang, Xiaofan |
| contents | Evaluating persona-aligned empathy in LLM-based dialogue agents remains challenging. User states are latent, feedback is sparse and difficult to verify in situ, and seemingly supportive turns can still accumulate into trajectories that drift from persona-specific needs. We introduce EMPA, a process-oriented framework that evaluates persona-aligned support as sustained intervention rather than isolated replies. EMPA distills real interactions into controllable, psychologically grounded scenarios, couples them with an open-ended multi-agent sandbox that exposes strategic adaptation and failure modes, and scores trajectories in a latent psychological space by directional alignment, cumulative impact, and stability. The resulting signals and metrics support reproducible comparison and optimization of long-horizon empathic behavior, and they extend to other agent settings shaped by latent dynamics and weak, hard-to-verify feedback. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00552 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EMPA: Evaluating Persona-Aligned Empathy as a Process Zhang, Shiya Zhan, Yuhan Su, Ruixi Sun, Ruihan Song, Ziyi Chen, Zhaohan Zhang, Xiaofan Artificial Intelligence Evaluating persona-aligned empathy in LLM-based dialogue agents remains challenging. User states are latent, feedback is sparse and difficult to verify in situ, and seemingly supportive turns can still accumulate into trajectories that drift from persona-specific needs. We introduce EMPA, a process-oriented framework that evaluates persona-aligned support as sustained intervention rather than isolated replies. EMPA distills real interactions into controllable, psychologically grounded scenarios, couples them with an open-ended multi-agent sandbox that exposes strategic adaptation and failure modes, and scores trajectories in a latent psychological space by directional alignment, cumulative impact, and stability. The resulting signals and metrics support reproducible comparison and optimization of long-horizon empathic behavior, and they extend to other agent settings shaped by latent dynamics and weak, hard-to-verify feedback. |
| title | EMPA: Evaluating Persona-Aligned Empathy as a Process |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.00552 |