Papers by Honghui Xu

2 papers
Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for few-shot text classification suffer from overfitting due to the lack of matching between the few amount of samples and complicated models.
Approach: They propose a method to improve model generalization ability to a new task by leveraging a meta-learner via gradient similarity method.
Outcome: The proposed method improves few-shot text classification performance on several benchmarks.
DemMA: Dementia Multi-Turn Dialogue Agent with Expert-Guided Reasoning and Action Simulation (2026.findings-acl)

Copied to clipboard

Challenge: Simulating dementia patients with large language models is challenging due to the need to model cognitive impairment, emotional dynamics, and nonverbal behaviors over long conversations.
Approach: They propose an expert-guided dementia dialogue agent for multi-turn patient simulation . they introduce a framework that trains a single LLM to jointly generate reasoning traces, patient utterances, and aligned behavioral actions .
Outcome: The proposed model outperforms baselines in persona fidelity, clinical validity, and educational effectiveness.

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