Weiqin Wang's photo

Weiqin Wang (็Ž‹ไผŸ้’ฆ)

Master's student
College of Computer Science and Software Engineering, Shenzhen University

Email: here1swqw@gmail.com

Weiqin Wang is currently a master's student at the College of Computer Science and Software Engineering, Shenzhen University (admitted through the 2025 recommended exemption program), advised by Assistant Professor Yile Wang. His research interests include artificial intelligence, natural language processing, and large language models.

Publications ๐Ÿ“„

(* equal contribution, # corresponding author)

Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs. [arxiv] [code] [bib]
     Feiyang Li, Shengjing Liu, Qi Zhan, Sijie Cheng, Weiqing Wang, Hongwen Chen, Yuxuan Yang, Wen Wang, Yile Wang, and Hui Huang.
     arXiv Preprint, 2026

DySem: Uncovering Dynamic Semantic Components of Large Language Models for Calculating Semantic Textual Similarity. [pdf] [code] [bib]
     Kaijie Zheng*, Weiqin Wang*, Yile Wang, and Hui Huang.
     To appear in Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment. [pdf] [code] [bib]
     Ziyang Chen, Zhenxuan Huang, Yile Wang, Weiqin Wang, Lu Yin, and Hui Huang.
     In Findings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2026

Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning. [pdf] [code] [bib]
     Weiqin Wang, Yile Wang, Kehao Chen, and Hui Huang.
     In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026

AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models. [pdf] [code] [bib]
     Zhanyu Shen, Sijie Cheng, Zhicheng Guo, Weiqin Wang, Yile Wang, and Hui Huang.
     In Findings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2026

Ranked Voting based Self-Consistency of Large Language Models. [pdf] [code] [bib]
     Weiqin Wang, Yile Wang, and Hui Huang.
     In Findings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2025


Award ๐Ÿ†


Academic & Professional Services


Education ๐ŸŽ“



( last updated on Apr. 23, 2026 )