Chenxi Lin — accepted AI-conference papers

2026

AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveys

Chenxi Lin, Weikang Yuan, Zhuoren Jiang, Biao Huang, Ruitao Zhang, Jianan Ge +2

AAAI 2026technical

Understanding human attitudes, preferences, and behaviors through social surveys is essential for academic research and policymaking. Yet traditional surveys face persistent challenges, including fixed-question formats, high costs, limited adaptability, and difficulties ensuring cross-cultural equiv

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Recurrent Alignment with Hard Attention for Hierarchical Text Rating

Chenxi Lin, Ren Jiayu, Guoxiu He, Zhuoren Jiang, Haiyan Yu, Xiaomin Zhu

EMNLP 2024main

While large language models (LLMs) excel at understanding and generating plain text, they are not tailored to handle hierarchical text structures or directly predict task-specific properties such as text rating. In fact, selectively and repeatedly grasping the hierarchical structure of large-scale t…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗