News

2 Papers Accepted at NAACL 2025

Previously known as The North American Chapter of the Association for Computational Linguistics (NAACL), the renamed 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, still abbreviated as NAACL, seeks to promote cooperation and information exchange among related scientific and professional societies, encourages and facilitates ACL membership by people and institutions in the Americas, and provides a source of information on regional activities for the ACL Executive Committee.

Congratulations to the following scientists from A*STAR Centre for Frontier AI Research (A*STAR CFAR) on having their papers accepted: 

  • Dr Joey Zhou, Deputy Director, A*STAR CFAR and Principal Scientist
  • Dr Zhang Jie, Scientist

List of accepted papers:

1.Identifying and Mitigating Social Bias Knowledge in Language Models
Ruizhe Chen, Yichen Li, Jianfei Yang, Yang Feng, Joey Tianyi Zhou, Jian Wu, Zuozhu Liu

This paper introduces a novel debiasing framework that first identifies the encoding locations of biases within language models and then applies the Fairness-Stamp (FAST).
2.On the Vulnerability of Text Sanitisation
Meng Tong, Kejiang Chen, Xiaojian Yuan, Jiayang Liu, Weiming Zhang, Nenghai Yu, Jie Zhang

This paper evaluates the effectiveness of text sanitisation by implementing theoretically optimal reconstruction attacks and deriving ASR bounds as benchmarks. Additionally, it proposes practical attacks that improve ASR by 46.4% over the state-of-the-art, highlighting overlooked risks in privacy protection.

Find out more about NAACL 2025.