← Search

Chao-Chung Wu

2 accepted papers

2025

Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning

NeurIPS 2025poster

Maintaining consistent model performance across domains is a fundamental challenge in machine learning. While recent work has explored using LLM-generated data for fine-tuning, its impact on cross-domain generalization remains poorly understood. This paper presents a systematic analysis revealing th…

Cited by 0SourceScholar
2024

I Need Help! Evaluating LLM’s Ability to Ask for Users’ Support: A Case Study on Text-to-SQL Generation

EMNLP 2024main

This study explores the proactive ability of LLMs to seek user support. We propose metrics to evaluate the trade-off between performance improvements and user burden, and investigate whether LLMs can determine when to request help under varying information availability. Our experiments show that wit…