arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

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

2026-02-05 至 2026-02-05 共收录 2
2602.04750 2026-02-05 cs.CL cs.AI

Exploiting contextual information to improve stance detection in informal political discourse with LLMs

利用上下文信息提升LLMs在非正式政治 discourse中的立场检测

Arman Engin Sucu, Yixiang Zhou, Mario A. Nascimento, Tony Mullen

机构 * Khoury College of Computer Sciences Northeastern University(科里学院计算机科学系东北大学)

AI总结 本研究通过引入用户资料上下文信息,利用LLMs提升非正式政治讨论中立场检测的准确性,实验表明上下文提示可使准确率提升17.5%-38.5%。

Comments 14 pages, 7 figures

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.20106 2026-02-05 cs.LG cs.AI

Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors

基于偏好向量的自适应有益有害对齐

Ren-Wei Liang, Chin-Ting Hsu, Chan-Hung Yu, Saransh Agrawal, Shih-Cheng Huang, Chieh-Yen Lin, Shang-Tse Chen, Kuan-Hao Huang, Shao-Hua Sun

机构 * National Taiwan University(国立台湾大学) Texas A&M University(德克萨斯A&M大学) Appier AI Research(Appier人工智能研究院) Graduate Institute of Communication Engineering, National Taiwan University(国立台湾大学通信工程研究所)

AI总结 本文提出偏好向量框架,通过模块化方法实现细粒度的用户可控偏好调整,提升大语言模型的有益性和无害性平衡。

Comments Accepted at The 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), Rabat, Morocco

详情

展开后加载摘要…

URL PDF HTML 收藏