arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing

2026-02-19 至 2026-02-19 共收录 2
2602.15866 2026-02-19 cs.CL cs.AI cs.CR cs.CY cs.HC

NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey

社交媒体中自然语言处理隐私风险识别(NLP-PRISM):一项调查

Dhiman Goswami, Jai Kruthunz Naveen Kumar, Sanchari Das

机构 * George Mason University(乔治·马歇尔大学)

AI总结 本文提出NLP-PRISM框架,系统评估社交媒体中NLP处理的隐私风险,揭示模型隐私保护与效用之间的权衡,并呼吁加强隐私保护措施。

Journal ref In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.15038 2026-02-19 cs.CL cs.AI

Indic-TunedLens: Interpreting Multilingual Models in Indian Languages

Indic-TunedLens:解读印度语言多语言模型

Mihir Panchal, Deeksha Varshney, Mamta, Asif Ekbal

机构 * Dwarkadas Jivanlal Sanghvi College of Engineering(达沃拉斯·吉文拉尔工程学院) Indian Institute of Technology Jodhpur(印度理工学院乔浦尔分校) King’s College London(伦敦国王学院) Indian Institute of Technology Patna(印度理工学院帕特纳分校)

AI总结 Indic-TunedLens通过学习共享仿射变换,为印度语言提供更准确的模型表示解码,提升多语言模型的可解释性。

Comments 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL) Thirteenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏