Houquan Zhou

Houquan Zhou

周厚全

PhD student at HLT@SUDA, co-advised by Prof. Zhenghua Li and Prof. Min Zhang.

My current focus is on how AI can enable new forms of gameplay, particularly AI-native games. This direction builds on my broader research in language intelligence, including text error correction—spelling and grammatical error correction—and the evaluation and application of large language models. Earlier, I worked on constituency parsing, dependency parsing, and part-of-speech tagging.

Projects

青椒模拟器 — A Little Simulator Powered by LLMs
I am interested in building LLM-powered applications. Here is a little simulator that Spico197 and I made: 🫑青椒模拟器. Feel free to play and give us feedback! Thanks to Kimi for API credits, and Warrier for the connection.
Media: ScienceNet游戏茶馆
Wortou.AI — Exploring AI-Native Games
I co-founded Wortou.AI, a cross-disciplinary team spanning research, engineering, and design. Together, we explore how large language models can become native game mechanics—not merely content generators. Our projects span AI-driven narratives, multi-agent competition, and playable AI algorithms, supported by the platforms and open-source tools we build along the way.
Neuralchemy — A Card Game for Model Experiments
I also made Neuralchemy, an exploratory demo about turning model training into a card-table experiment. It is a small probe into what interactive ML education and playful model-building might feel like: buy cards, upgrade compute, build a model from your hand, and let the browser really train it before the server checks the result. Good runs earn research points; odd runs become very serious lab notes.

Publications

(* denotes equal contributions)

LLM Application

  • 2026
  • WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

    Zijian Li, Xin Guan, Bo Zhang, Shen Huang, Houquan Zhou, Shaopeng Lai, Ming Yan, Yong Jiang, Pengjun Xie, Fei Huang, Jun Zhang, Jingren Zhou

    ICLR 2026

    arXiv cited 39

Text Error Correction

  • 2025
  • A Training-free LLM-based Approach to General Chinese Character Error Correction

    Houquan Zhou, Bo Zhang, Zhenghua Li, Ming Yan, Min Zhang

    ACL 2025

    paper arXiv code cited 7
  • Mixture of Small and Large Models for Chinese Spelling Check

    Ziheng Qiao, Houquan Zhou, Zhenghua Li

    ACL 2025

    paper arXiv code cited 6
  • DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check

    Ziheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang

    ACL 2025

    paper arXiv code cited 2
  • 2024
  • A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models

    Houquan Zhou, Zhenghua Li, Bo Zhang, Chen Li, Shaopeng Lai, Ji Zhang, Fei Huang, Min Zhang

    EMNLP 2024

    paper arXiv bib code cited 8
  • 2023
  • Improving Seq2Seq Grammatical Error Correction via Decoding Interventions

    Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang

    EMNLP (Findings) 2023

    paper arXiv code cited 18
  • CCL23-Eval Task 7 Track 1 System Report: Suda & Alibaba Team Text Error Correction System

    Haochen Jiang, Yumeng Liu, Houquan Zhou, Ziheng Qiao, Bo Zhang, Chen Li, Zhenghua Li, Min Zhang

    CCL 2023

    paper bib cited 1

Parsing & Tagging

  • 2023
  • How Well Do Large Language Models Understand Syntax? An Evaluation by Asking Natural Language Questions

    Houquan Zhou, Yang Hou, Zhenghua Li, Xuebin Wang, Zhefeng Wang, Xinyu Duan, Min Zhang

    arXiv 2023 (preprint)

    arXiv code cited 12
  • 2022
  • Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

    Houquan Zhou*, Yang Li*, Zhenghua Li, Min Zhang

    ACL (Findings) 2022

    paper arXiv bib code cited 4
  • An In-depth Study on Internal Structure of Chinese Words

    Chen Gong, Saihao Huang, Houquan Zhou, Zhenghua Li, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan

    ACL-IJCNLP 2021

    paper arXiv bib code cited 3
  • A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing

    Yang Hou, Houquan Zhou, Zhenghua Li, Yu Zhang, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan

    CoNLL 2021

    paper bib code cited 5
  • 2020
  • Fast and Accurate Neural CRF Constituency Parsing

    Yu Zhang*, Houquan Zhou*, Zhenghua Li

    IJCAI 2020

    paper arXiv bib code cited 105
  • Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?

    Houquan Zhou*, Yu Zhang*, Zhenghua Li, Min Zhang

    NLPCC 2020 — Best Paper Award

    arXiv code cited 29

Competitions

Education

Experience