Papers by Xudong Zhao
A Chinese Dataset for Evaluating the Safeguards in Large Language Models (2024.findings-acl)
Copied to clipboard
Yuxia Wang, Zenan Zhai, Haonan Li, Xudong Han, Shom Lin, Zhenxuan Zhang, Angela Zhao, Preslav Nakov, Timothy Baldwin
| Challenge: | a recent study has shown that large language models can produce harmful responses, exposing users to unexpected risks. |
| Approach: | They propose a dataset for the safety evaluation of Chinese LLMs in Mandarin Chinese . they extend the dataset to better identify false negative and false positive examples . |
| Outcome: | The proposed dataset is for the safety evaluation of Chinese LLMs, and is based on a Chinese dataset. |
Learning Temporally-Aware Sample Weights for Preference Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for preference optimization rely on static functions of instantaneous model states and ignore temporal learning dynamics. |
| Approach: | They propose a framework that meta-learns adaptive weights using three temporal features: reward margin evolution, learning volatility, and reference deviation. |
| Outcome: | The proposed framework achieves statistically significant improvements over baselines on models ranging from 7B to 70B parameters. |
MuMath: Multi-perspective Data Augmentation for Mathematical Reasoning in Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) that integrate with external Python interpreters are not able to demonstrate the calculation process, which compromises user-friendliness and understanding of problem-solving steps. |
| Approach: | They propose to use LLaMA-2 to refine LLti-perspective augmentation methods to improve performance. |
| Outcome: | The proposed model achieves 88.3% on GSM8K and 34.5% on MATH. |
FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extraction (2024.lrec-main)
Copied to clipboard
| Challenge: | Document-level Relation Extraction (DocRE) aims to identify relation labels between entities within a document. |
| Approach: | They propose to fuse constituency and dependency syntax into DocRE to exploit the rich syntax information in the document. |
| Outcome: | The proposed method is able to identify relation labels between entities within a document and is scalable. |