Papers by Debin Xiao
A Simple yet Efficient Prompt Compression Method for Text Classification Data Annotation Using LLM (2025.coling-industry)
Copied to clipboard
| Challenge: | Existing methods to improve the accuracy of large language models (LLMs) are often impractical due to high costs and time consumption. |
| Approach: | They propose a method that uses keyword extraction to reduce prompt tokens in text annotation tasks. |
| Outcome: | The proposed method reduces prompt tokens while maintaining high accuracy. |
Emotion Cause Extraction on Social Media without Human Annotation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have focused on extracting emotion causes from news articles, but lack of fine-grained annotations has limited the ECE task. |
| Approach: | They propose a new ECE framework that extracts emotion causes from social media data without relying on human annotations. |
| Outcome: | The proposed framework achieves high extraction performance and generalizability without relying on human annotations. |