§ 01About简介PROFILE个人简介

I am a first-year M.S. student in Data Science (Artificial Intelligence) at the University of Macau, advised by Prof. Derek F. Wong in the NLP2CT Lab.

My research focuses on LLM evaluation, LLM-as-a-Judge, rubric-based evaluation, and machine learning. I am particularly interested in evaluating judges on long-horizon agent trajectories and building reliable reward models for complex tasks. I plan to pursue a Ph.D. and continue research in academia.

I am deeply grateful to my mentor, Shudong Liu, who introduced me to research and has supported me immensely along the way. I am also sincerely grateful to my advisor, Prof. Derek F. Wong, for his guidance and support in my research. I will keep working hard to live up to the guidance and help I have received from my labmates, professors, and friends in the lab.

I am looking to pursue a Ph.D. and continue my research in academia. Please feel free to reach out via email.

我是澳门大学数据科学(人工智能应用方向)研究生一年级学生, 在 NLP2CT 实验室, 导师为 Derek F. Wong 教授。

我的研究兴趣包括大语言模型评测、LLM-as-a-Judge、基于评分标准(rubric)的评测及机器学习。 我尤其关注长程智能体轨迹中的判官评测,以及复杂任务中的可靠奖励模型,并希望继续攻读博士学位、在学术界深耕。

我由衷感谢我的 mentor 刘树东, 是他领我进入学术之门,并一路给予我莫大的帮助。我也衷心感谢导师 Derek F. Wong 教授在科研中给予我的指导与支持。 我会继续努力,不辜负实验室师兄、教授与同伴对我的指导和帮助。

我希望继续攻读博士学位,在学术界深耕。欢迎通过邮件与我联系。

§ 02Research Overview研究方向THEMATIC PILLARS研究主题

I.

LLM Reliability & Safety Evaluation大模型可靠性与安全评测

Building rigorous benchmarks to evaluate LLM judges, scoring rubrics, and the reliability of model-generated assessments.

构建严谨的评测基准,衡量 LLM 判官、评分标准及模型生成评价的可靠性。

II.

Trustworthy Agents & Deep Research可信智能体与深度研究

Studying error detection, evidence tracing, and recovery in long-horizon agents and deep research, towards reliable agent training and multi-agent collaboration.

关注长程智能体与深度研究系统的错误检测、证据回溯和自主纠错,探索可靠的智能体训练与多智能体协作。

III.

Reward Modeling & Reward Hacking奖励模型与奖励投机

Evaluating reward-model reliability and robustness, and investigating how agents exploit reward signals and how to detect and mitigate such behavior.

评测奖励模型的判断能力与鲁棒性,研究智能体如何利用奖励机制的漏洞,以及如何识别和缓解这些行为。

I also maintain an active interest in agent hardness, agent skills, and AI watermarking, and closely follow the latest research developments in these emerging areas.

同时对 agent hardness、智能体技能(agent skills)与 AI 水印等前沿方向保持积极兴趣,并持续跟踪相关领域的最新研究进展。

§ 03News动态RECENT近况

  • 2026-10 Submitted LongJudgeBench and CIFE to the October 2026 ACL Rolling Review (ARR). LongJudgeBench 与 CIFE 已投稿至 2026 年 10 月 ACL Rolling Review(ARR)。
  • 2026-08 DeepResearch RewardBench: Evaluating Reward Models for Deep Research Reports was accepted to Findings of EMNLP 2026. DeepResearch RewardBench: Evaluating Reward Models for Deep Research Reports 被 EMNLP 2026 Findings 接收。
  • 2026-05 Submitted DeepResearch RewardBench: Evaluating Reward Models for Deep Research Reports to EMNLP. 向 EMNLP 投稿 DeepResearch RewardBench —— 面向深度研究报告的奖励模型评测基准。
  • 2025-08 Started the M.S. program in Data Science (Artificial Intelligence) at the University of Macau and joined the NLP2CT Lab. 开始在澳门大学攻读数据科学(人工智能应用方向)硕士学位,并加入 NLP2CT 实验室。
  • 2025-07 Graduated from Guangdong University of Foreign Studies with an Honours Degree and the Outstanding Graduate Award. 毕业于广东外语外贸大学,获荣誉学位及优秀毕业生称号。

§ 04Education教育经历DEGREES学位

University of Macau澳门大学 2025.08 – 2027.07
M.S. in Data Science (Artificial Intelligence) · Macau SAR, China 数据科学理学硕士(人工智能应用方向)· 中国澳门

GPA: 3.62/4.0 · Advisor:导师: Prof. Derek F. Wong

Guangdong University of Foreign Studies广东外语外贸大学 2021.09 – 2025.07
B.Eng. in Computer Science and Technology · Guangzhou, China 计算机科学与技术工学学士 · 中国广州

GPA: 3.75/4.0 · Outstanding Graduate & Honours Degree优秀毕业生、荣誉学位

§ 05Experience经历ROLES职务

Research Assistant — NLP2CT Lab, University of Macau 研究助理 —— NLP2CT 实验室,澳门大学 2025 – Present
  • DeepResearch RewardBench (co-first author) — built the first reward-model benchmark for long-form deep-research reports: an end-to-end pipeline over 19 agent/LLM families yielding preference datasets of 331 tasks / 866 reports, evaluation of 17 models (7B–235B), and a few-shot judge-error classifier reaching ~87% agreement with humans. Accepted to Findings of EMNLP 2026.
  • CIFE (co-first author) — developed a glossary-grounded, item-level metric for cultural fidelity in literary machine translation. It grades each cultural item with an evidence-checked LLM judgment and was evaluated on English translations of Journey to the West and a Telugu Ramayana; submitted to October 2026 ACL Rolling Review.
  • LongJudgeBench (first author) — built a benchmark of 590 natural agent trajectories and 262 constructed error cases to measure LLM judges' error detection, localization, and evidence attribution; submitted to October 2026 ACL Rolling Review.
  • DeepResearch RewardBench(共同第一作者)—— 构建首个面向长篇深度研究报告的奖励模型评测基准:聚合 19 个智能体/大模型家族的端到端数据流水线,产出 331 任务 / 866 份报告的偏好数据集,系统评测 17 个模型(7B–235B),并提炼出与人工一致率约 87% 的 few-shot 错误分类器。已被 EMNLP 2026 Findings 接收。
  • CIFE(共同第一作者)—— 提出基于术语表、逐项评估文学机器翻译文化忠实度的方法;LLM 判官对每个文化特定项评分并提供可核验的译文证据,在《西游记》英文译本和泰卢固语《罗摩衍那》上进行评测;已投稿至 2026 年 10 月 ACL Rolling Review。
  • LongJudgeBench(第一作者)—— 构建包含 590 条自然智能体轨迹和 262 个构造错误案例的基准,评测 LLM 判官的错误检出、定位与证据归因能力;已投稿至 2026 年 10 月 ACL Rolling Review。

§ 06Selected Projects代表项目WORK项目

LongJudgeBench Submitted · ARR Oct 2026已投稿 · 2026 年 10 月 ARR

Benchmarks three LLM-judge capabilities on agent trajectories: error detection, localization, and attribution of supporting execution evidence. It contains 590 natural trajectories and 262 constructed error cases across five error families; evaluation of 10 judges revealed a substantial evidence-attribution gap.

评测 LLM 判官在智能体轨迹中的三项能力:错误检出、错误定位和支持证据归因。数据集包含 590 条自然轨迹及覆盖五类错误的 262 个构造案例;对 10 个判官的评测发现,证据归因仍存在明显短板。

LLM-as-a-Judge · Agent Evaluation · Evidence Grounding

CIFE Submitted · ARR Oct 2026已投稿 · 2026 年 10 月 ARR

CIFE (Glossary-Grounded, Item-Level Evaluation of Cultural Fidelity in Literary Machine Translation) evaluates cultural items individually. An LLM assigns strategy-constrained severity scores and quotes translation evidence that is automatically checked; evaluated on Journey to the West and a Telugu Ramayana.

CIFE(基于术语表的文学机器翻译文化忠实度逐项评估)逐项评测译文中的文化特定项。LLM 根据翻译策略判定错误严重程度并引用可自动核验的译文证据;评测对象包括《西游记》英文译本和泰卢固语《罗摩衍那》。

LLM-as-a-Judge · Cultural Fidelity · Machine Translation Evaluation

DeepResearch RewardBench accepted已接收

A benchmark for evaluating how well reward models score long-form deep-research reports, probing their reliability as judges. Accepted to Findings of EMNLP 2026.

一个评测奖励模型对长文本深度研究报告打分能力的基准,考察其作为评判者的可靠性。已被 EMNLP 2026 Findings 接收。

Python · PyTorch · vLLM · Reward Models

§ 07Publications论文PAPERS发表

* denotes equal contribution / co-first authorship.* 表示同等贡献 / 共同第一作者。

  1. ACL Rolling Review · October 2026ACL Rolling Review · 2026 年 10 月 2026
    LongJudgeBench: Benchmarking LLM Judges on Agent Trajectory Error Localization and Evidence Attribution Yuting Zhong (first author).钟玉婷(第一作者)。 Submitted to ACL Rolling Review (ARR), October 2026.已投稿至 ACL Rolling Review (ARR),2026 年 10 月。
  2. DeepResearch RewardBench data collection, scoring, filtering, and evaluation framework
    Findings of EMNLP 2026EMNLP 2026 Findings 2026
    DeepResearch RewardBench: Evaluating Reward Models for Deep Research Reports Shudong Liu*, Yuting Zhong*, Guanhua Chen, Xinyi Yang, Junnan Liu, Lidia S. Chao, Jiaheng Liu, and Derek F. Wong. To appear in Findings of EMNLP 2026.将发表于 EMNLP 2026 Findings。
    Paper论文 Code · coming soon代码 · 待公开
  3. ACL Rolling Review · October 2026ACL Rolling Review · 2026 年 10 月 2026
    CIFE: Glossary-Grounded, Item-Level Evaluation of Cultural Fidelity in Literary Machine Translation Bhaskar Ganesh Devalla*, Yuting Zhong*, Dejing Zhou, Junchao Wu, Shudong Liu, Lidia S. Chao, and Derek F. Wong. Submitted to ACL Rolling Review (ARR), October 2026.已投稿至 ACL Rolling Review (ARR),2026 年 10 月。

§ 08Honors & Awards荣誉奖项AWARDS荣誉

  • Provincial Second Prize, Chinese Mathematics Competition for College Students.全国大学生数学竞赛 省级二等奖。
  • Outstanding Graduate Award, Guangdong University of Foreign Studies.广东外语外贸大学 优秀毕业生。
  • University Comprehensive Scholarship (multiple times).大学综合奖学金(多次)。
  • “Merit Student” & “Outstanding Class Cadre” honors (multiple times).校级“三好学生”、“优秀班干部”等荣誉(多次)。

§ 09Technical Skills技术能力TOOLBOX工具

Programming编程语言
Python, C/C++
ML & AI机器学习与 AI
PyTorch, TensorFlow, LLM evaluation & application, NLP, prompt / few-shot methods
Data Science数据科学
Statistical testing (Wilcoxon, Spearman), TF-IDF, feature engineering, graph algorithms
Tools工具
Linux, Git, LaTeX

§ 10Relevant Coursework相关课程STUDY课程

Graduate (UM):研究生(澳大): Applied Natural Language Processing, Deep Learning, Practical Machine Learning, Principles of Artificial Intelligence 应用自然语言处理、深度学习、实用机器学习、人工智能原理

Undergraduate:本科: Algorithm Design, C++ Programming, Natural Language Processing, Big Data Processing 算法设计、C++ 程序设计、自然语言处理、大数据处理技术

Visitors访客分布

Global reach全球访问
Live world map of website visitors Live visitor map实时访客地图
Top countries国家排行
Live visitor counts by country

New countries appear automatically after their first genuine visit.新的国家会在首次真实访问后自动出现。

Locations are estimated from privacy-preserving IP geolocation. Click either panel for the complete distribution. 访问地区由隐私保护的 IP 地理定位估算;点击地图或排行可查看完整分布。

© 2026 Yuting Zhong (yutingzhong, 钟玉婷) · University of Macau · zyt2312.github.io © 2026 钟玉婷 (Yuting Zhong, yutingzhong) · 澳门大学 · zyt2312.github.io

Last updated August 2026 · Built with plain HTML & CSS. 最后更新于 2026 年 8 月 · 使用纯 HTML 与 CSS 构建。