Papers by Xuhai Xu

2 papers
Substance over Style: Evaluating Proactive Conversational Coaching Agents (2025.acl-long)

Copied to clipboard

Challenge: Recent NLP research has focused on single-turn tasks with well-defined objectives or evaluation criteria.
Approach: They describe five multi-turn coaching agents that exhibit distinct conversational styles and evaluate them through a user study.
Outcome: The authors compare user feedback with third-person evaluations from health experts and an LM to find that stylistic components in absence of core functionality are viewed negatively.
Can AI Relate: Testing Large Language Model Response for Mental Health Support (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) are already being piloted for clinical use in hospitals . recent failures of the Tessa chatbot have led to doubts about their reliability in high-stakes settings.
Approach: They propose safety guidelines for the potential deployment of large language models for mental health response.
Outcome: The proposed framework measures equity in empathy and adherence of LLM responses to motivational interviewing theory.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations