Papers by Sophia Xiao Pu
ChatAnime: Towards User-Centered Emotional Support in LLM-based Virtual Character Chat (2026.acl-long)
Copied to clipboard
| Challenge: | Existing research focuses on character consistency in fictional or game-based scenarios . ESRP framework is designed to align role-playing with real-world user scenarios based on emotional needs. |
| Approach: | They propose a framework to align role-playing with real-world user scenarios and emotional needs. |
| Outcome: | The proposed framework aligns role-playing with real-world user scenarios and emotional needs. |
Dynamic Evaluation for Oversensitivity in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks rely on static datasets that degrade over time as models evolve, leading to data contamination and diminished evaluative power. |
| Approach: | They construct a framework that generates model-specific challenging datasets and aggregates them across diverse LLM families. |
| Outcome: | The framework captures emerging defensive patterns and aligns with each model’s unique behavior. |