About Me
I am a Senior Research Software Engineer at the General AI Group in Microsoft Research Asia, specializing in artificial intelligence, large language models, natural language processing, and agent systems. I hold a Master's degree in Computer Science from Tsinghua University (2019) and a Bachelor's degree in Computer Science from Beijing Normal University (2016).
My work primarily focuses on developing next-generation LLM-powered agent systems. This includes enhancing reasoning, planning, and task-solving capabilities to improve AI's effectiveness and generalizability in real-world applications. I also served as volunteer reviewer for top-tier conferences and journals, including NeurIPS, ICLR, ICML, ACL ARR (ACL, EMNLP, NAACL), ICASSP, INTERSPEECH, etc.
Beyond my professional work, I have a wide range of interests. You can explore more about my daily life in the gallery tab.
If you are interested in LLM Reasoning or Agent Foundation research and want to do an internship at MSRA, feel free to contact me!
Contact me: Shaoguang.Mao@microsoft.com, dawnmsg941107@gmail.com
Publications
Natural Language Processing
Large Language Model
Agent
Reasoning
Speech Processing
Machine Learning
(#: students I mentored)
2024
-
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark.
Qihao Zhao, Yangyu Huang, Tengchao Lv, Lei Cui, Qinzheng Sun, Shaoguang Mao, Xin Zhang, Ying Xin, Qiufeng Yin, Scarlett Li, Furu Wei
arXiv preprint arXiv:2412.15194, 2024. [code] [HF Dataset] -
1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs.
Jinheng Wang, Hansong Zhou, Ting Song, Shaoguang Mao, Shuming Ma, Hongyu Wang, Yan Xia, Furu Wei.
arXiv preprint arXiv:2410.16144, 2024. [code] -
One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks.
Fangru Lin #, Shaoguang Mao, Emanuele La Malfa, Valentin Hofmann, Adrian de Wynter, Jing Yao, Si-Qing Chen, Michael Wooldridge, Furu Wei.
arXiv preprint arXiv:2410.11005, 2024. -
Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models.
Wenshan Wu, Shaoguang Mao, Yadong Zhang #, Yan Xia, Li Dong, Lei Cui, Furu Wei.
NeurIPS Poster, 2024. -
CERD: A Comprehensive Chinese Rhetoric Dataset for Rhetorical Understanding and Generation in Essays.
Nuowei Liu, Xinhao Chen, Hongyi Wu #, Changzhi Sun, Man Lan, Yuanbin Wu, Xiaopeng Bai, Shaoguang Mao, Yan Xia.
EMNLP Findings, 2024. -
Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method.
Xinshu Shen #, Hongyi Wu #, Yadong Zhang #, Man Lan, Xiaopeng Bai, Shaoguang Mao, Yuanbin Wu, Xinlin Zhuang, Li Cai.
EMNLP Findings, 2024. -
Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning.
Yadong Zhang #, Shaoguang Mao, Wenshan Wu, Yan Xia, Tao Ge, Man Lan, Furu Wei
arXiv preprint arXiv:2407.06112. -
Meta Reasoning for Large Language Models.
Peizhong Gao #, Ao Xie #, Shaoguang Mao, Wenshan Wu, Yan Xia, Haipeng Mi, Furu Wei
arXiv preprint arXiv:2406.11698. -
Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction.
Dingyao Yu, Yang An #, Wei Ye, Xiongfeng Xiao, Shaoguang Mao, Tao Ge, Shikun Zhang.
Findings of ACL, 2024. -
LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models.
Yadong Zhang #, Shaoguang Mao, Tao Ge, Xun Wang, Adrian de Wynter, Yan Xia, Wenshan Wu, Ting Song, Man Lan, Furu Wei.
Conference on Language Modeling, 2024. -
Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration.
Zhenhailong Wang #, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji.
NAACL Main Conference, 2024. -
Low-code LLM: Graphical User Interface over Large Language Models.
Yuzhe Cai #, Shaoguang Mao, Wenshan Wu, Zehua Wang, Yaobo Liang, Tao Ge, Chenfei Wu, WangYou WangYou, Ting Song, Yan Xia, Nan Duan, Furu Wei.
NAACL System Demonstrations, 2024. -
TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs.
Yaobo Liang, Chenfei Wu, Ting Song, Wenshan Wu, Yan Xia, Yu Liu, Yang Ou, Shuai Lu, Lei Ji, Shaoguang Mao, Yun Wang, Linjun Shou, Ming Gong, Nan Duan.
Intelligent Computing, 2024. -
K-Level Reasoning with Large Language Models.
Yadong Zhang #, Shaoguang Mao, Tao Ge, Xun Wang, Yan Xia, Man Lan, Furu Wei.
arXiv preprint arXiv:2402.01521. -
Empirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition: Taking TOEFL Independent Writing Task for Example.
Wei Xia, Shaoguang Mao, Chanjin Zheng.
arXiv preprint arXiv:2401.03401.
2023
-
Extensible Prompts for Language Models on Zero-shot Language Style Customization.
Tao Ge, Hu Jing, Li Dong, Shaoguang Mao, Yan Xia, Xun Wang, Si-Qing Chen, Furu Wei.
NeurIPS Poster, 2023. -
ALYMPICS: LLM Agents Meet Game Theory.
Shaoguang Mao, Yuzhe Cai #, Yan Xia, Wenshan Wu, Xun Wang, Fengyi Wang, Tao Ge, Furu Wei.
arXiv preprint arXiv:2311.03220. -
A Multi-Task Dataset for Assessing Discourse Coherence in Chinese Essays: Structure, Theme, and Logic Analysis.
Hongyi Wu, Xinshu Shen, Man Lan, Shaoguang Mao, Xiaopeng Bai, Yuanbin Wu.
EMNLP Main Conference, 2023. -
Enhancing Detailed Feedback to Chinese Writing Learners Using a Soft-Label Driven Approach and Tag-Aware Ranking Model.
Yuzhe Cai #, Shaoguang Mao, Chenshuo Wang, Tao Ge, Wenshan Wu, Yan Xia, Chanjin Zheng, Qiang Guan.
NLPCC, 2023. -
Assessing Phrase Break of ESL Speech with Pre-trained Language Models and Large Language Models.
Zhiyi Wang #, Shaoguang Mao, Wenshan Wu, Yan Xia, Yan Deng, Jonathan Tien.
Interspeech, 2023. -
End-to-End Word-Level Pronunciation Assessment with MASK Pre-training.
Yukang Liang, Kaitao Song, Shaoguang Mao, Huiqiang Jiang, Luna Qiu, Yuqing Yang, Dongsheng Li, Linli Xu, Lili Qiu.
Interspeech, 2023. -
Smart Word Suggestions for Writing Assistance.
Chenshuo Wang #, Shaoguang Mao, Tao Ge, Wenshan Wu, Xun Wang, Yan Xia, Jonathan Tien, Dongyan Zhao.
Findings of ACL, 2023. -
EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation.
Wang You #, Wenshan Wu, Yaobo Liang, Shaoguang Mao, Chenfei Wu, Maosong Cao, Yuzhe Cai, Yiduo Guo, Yan Xia, Furu Wei, Nan Duan.
arXiv preprint arXiv:2310.08185.
2022
-
A Universal Ordinal Regression for Assessing Phoneme-Level Pronunciation.
Shaoguang Mao, Frank Soong, Yan Xia, Jonathan Tien.
ICASSP, 2022. -
An Approach to Mispronunciation Detection and Diagnosis with Acoustic, Phonetic and Linguistic (APL) Embeddings.
Wenxuan Ye #, Shaoguang Mao, Frank Soong, Wenshan Wu, Yan Xia, Jonathan Tien, Zhiyong Wu.
ICASSP, 2022. -
Ordinal Regression via Binary Preference vs Simple Regression: Statistical and Experimental Perspectives.
Bin Su #, Shaoguang Mao, Frank Soong, Zhiyong Wu.
arXiv preprint arXiv:2207.02454.
2021
-
Improving Pronunciation Assessment via Ordinal Regression with Anchored Reference Samples.
Bin Su #, Shaoguang Mao, Frank Soong, Yan Xia, Jonathan Tien, Zhiyong Wu.
ICASSP, 2021.
2019
-
NN-based Ordinal Regression for Assessing Fluency of ESL Speech.
Shaoguang Mao, Zhiyong Wu, Jingshuai Jiang, Peiyun Liu, Frank K Soong.
ICASSP, 2019.
2018
-
Automatic Lexical Stress and Pitch Accent Detection for L2 English Speech Using Multi-Distribution Deep Neural Networks.
Kun Li, Shaoguang Mao, Xv Li, Zhiyong Wu, Helen Meng.
Speech Communication, 2018. -
Unsupervised Discovery of Non-native Phonetic Patterns in L2 English Speech for Mispronunciation Detection and Diagnosis.
Xu Li, Shaoguang Mao, Xixin Wu, Kun Li, Xunying Liu, Helen Meng.
Interspeech, 2018. -
Integrating Articulatory Features into Acoustic-Phonemic Model for Mispronunciation Detection and Diagnosis in L2 English Speech.
Shaoguang Mao, Zhiyong Wu, Xu Li, Runnan Li, Xixin Wu, Helen Meng.
ICME, 2018. -
Applying Multitask Learning to Acoustic-Phonemic Model for Mispronunciation Detection and Diagnosis in L2 English Speech.
Shaoguang Mao, Zhiyong Wu, Runnan Li, Xu Li, Helen Meng, Lianhong Cai.
ICASSP, 2018. -
Unsupervised Discovery of an Extended Phoneme Set in L2 English Speech for Mispronunciation Detection and Diagnosis.
Shaoguang Mao, Xu Li, Kun Li, Zhiyong Wu, Xunying Liu, Helen Meng.
ICASSP, 2018.