Curriculum Vitae
Education, platforms and tools, research impact, awards, teaching, research experience, talks, and academic service, in the order of the CV. For the full publication record, see Publications.
Education
- Ph.D. in Informatics (Complex Networks and Systems), Indiana University Bloomington, USA. Advisors: Prof. Jisun An and Prof. Haewoon Kwak
- Ph.D. in Computer Science, Singapore Management University, Singapore. Advisors: Prof. Jisun An and Prof. Haewoon Kwak
- M.Sc. in Information Systems, Nanyang Technological University, Singapore. Advisor: Prof. Jin-Cheon Na · Thesis: Public Opinion Trend Analysis on Nuclear Energy via Aspect-based Sentiment Analysis Methods
- B.Sc. in Computer Science & Technology, Central South University, China. Advisor: Prof. Zuping Zhang
Platforms & Tools
- AgentSims: Agentic Simulations — agentsims.agentsnet.org LLM-driven multi-agent simulation framework with persistent state and replayable histories for reproducible academic research on collective behavior. Designed to support industry scenario analysis, strategy evaluation, and risk assessment through configurable agent environments.
- Founders-Sim: Market Competition Simulation — founders-sim.agentsnet.org Rule-based simulation of startups vying for users in a synthetic population of 80,000 groups (100,000 people each). Social ties spread word of products, but only advertising or referrals can start free trials, after which some pay. The site replays a recorded 1,000-week run.
- Cytolume: GPU-Accelerated Million-Cell Visualization — muyuhuatang.github.io/Cytolume WebGL2 visualization library for large single-cell embeddings: UMAP, t-SNE, and PCA layouts in 2D and 3D, lasso selection, Human Reference Atlas anatomy beside the cell map, and figure export with data provenance. Successor to Human Reference Atlas cell-embedding notebooks built with Prof. Katy Börner's group in 2024. A Python package serves the viewer from AnnData objects, locally or in Jupyter.
Publications
- 10 peer-reviewed conference papers and 12 preprints — the full list, with links and filters, is on the Publications page. Google Scholar: 649 citations · h-index 6 (as of Oct 2026)
Research Impact
Cited by 42 papers that each have 100+ citations, including Llama 2 (Meta; 18,593 citations) and Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena (NeurIPS 2023; 12,204 citations). Citation counts from Semantic Scholar (Oct 2026); each citation below was verified in the citing work's reference list.
Selected Media Coverage
- Multi-LLM Agent Simulation Reproduces Hate Speech Cascades with 97% Hostile Stance Accuracy. The Neural Feed. Jun 18, 2026. Covers Simulating Hate Speech Cascades with Multi-LLM Agents (arXiv 2026).
- Network-of-Thought (NoT) moves LLM reasoning from linear chains and trees to complex directed graphs, significantly improving multi-hop QA. SeriesFusion.ai. SeriesFusion Editorial Board. Mar 24, 2026. Covers Reasoning Topology Matters: Network-of-Thought for Complex Reasoning Tasks (arXiv 2026).
- How Can We Tell if LLMs Actually Think Like Humans? XCHOICE Offers a Mechanism-Based Answer. CORe Inc., AI Research. Masato Okuwaki. Jan 22, 2026. Covers XChoice (AACL-IJCNLP Findings 2026).
- 7 Papers & Radios (weekly selection), featuring Chain of Explanation among the week's 10 selected NLP papers. Synced (机器之心); syndicated by The Paper and Tencent News. ArXiv Weekly Radiostation. Sep 18, 2022. Covers Chain of Explanation (WWW 2023 Companion).
Cited in Nature- and PNAS-Family Journals
- Evaluating LLMs' divergent thinking capabilities for scientific idea generation with minimal context. Nature Communications. Kai Ruan et al. Mar 2026. Cites ChatGPT Rates Natural Language Explanation Quality like Humans (LREC-COLING 2024).
- Perils and opportunities in using large language models in psychological research. PNAS Nexus. Suhaib Abdurahman et al. Jul 2024. Cites Is ChatGPT Better than Human Annotators? (WWW 2023 Companion).
- ChatGPT outperforms crowd workers for text-annotation tasks. Proceedings of the National Academy of Sciences (PNAS). Fabrizio Gilardi, Meysam Alizadeh, and Maël Kubli. Jul 2023. Cites Is ChatGPT Better than Human Annotators? (WWW 2023 Companion).
Cited in Other Nature Portfolio Journals
- Fallibility, persuadability, and correctability of large language models under sustained conversational misinformation pressure. Scientific Reports. Jordan Rodriguez et al. Sep 2026. Cites Vulnerability of LLMs' Stated Belief? (ACL Findings 2026).
- A Blue Start: A large-scale pairwise and higher-order social network dataset. Scientific Data. Alyssa Hasegawa Smith et al. Mar 2026. Cites The Rise of Bluesky (arXiv 2025).
- LLMs outperform outsourced human coders on complex textual analysis. Scientific Reports. Vicente J. Bermejo et al. Nov 2025. Cites Is ChatGPT Better than Human Annotators? (WWW 2023 Companion).
- Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligence. Humanities and Social Sciences Communications. Andres Karjus. Feb 2025. Cites Is ChatGPT Better than Human Annotators? (WWW 2023 Companion).
- Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI. npj Digital Medicine. Mahyar Abbasian et al. Mar 2024. Cites Chain of Explanation (WWW 2023 Companion).
- Evolving linguistic divergence on polarizing social media. Humanities and Social Sciences Communications. Andres Karjus and Christine Cuskley. Mar 2024. Cites Is ChatGPT Better than Human Annotators? (WWW 2023 Companion).
Cited by Researchers at Frontier AI Labs
- Kurt Thomas et al. (Google and Google DeepMind). May 2025. Cites Is ChatGPT Better than Human Annotators?
- Ruibo Liu et al. (Google DeepMind). Oct 2024. Cites Is ChatGPT Better than Human Annotators?
- Yifan Wang et al. (Meta). Sep 2024. Cites Is ChatGPT Better than Human Annotators?
- Vinodkumar Prabhakaran et al. (Google Research). Jun 2024. Cites Is ChatGPT Better than Human Annotators?
- Lora Aroyo et al. (Google Research). Dec 2023. Cites Is ChatGPT Better than Human Annotators?
- Hugo Touvron et al. (Meta). Jul 2023. Cites Is ChatGPT Better than Human Annotators?
- Christopher M. Homan et al. (Google Research). Jun 2023. Cites Is ChatGPT Better than Human Annotators?
Cited in Government and Policy Reports
- Validating Large Language Model Annotations. Federal Reserve Board, Finance and Economics Discussion Series 2026-020 (staff working paper). Anne Lundgaard Hansen. Mar 2026. Cites Is ChatGPT Better than Human Annotators? (WWW 2023 Companion).
- The Role of Artificial Intelligence in Scientific Research: A Science for Policy, European Perspective. European Commission, Joint Research Centre (JRC), Science for Policy report. Erasmo Purificato et al. Oct 2025. Cites Is ChatGPT Better than Human Annotators? (WWW 2023 Companion).
- Technical report on the state of the art of political disinformation in social networks and the press. HYBRIDS Deliverable D3.2, Horizon Europe Marie Skłodowska-Curie Doctoral Network. HYBRIDS doctoral researchers. Apr 2024. Cites Chain of Explanation (WWW 2023 Companion).
- ChatGPT: research evidence-based controversies, regulations and solutions. Good In Tech Research Network (Institut Mines-Télécom and Sciences Po), report. Kay Yip and Christine Balagué. Sep 2023. Cites Is ChatGPT Better than Human Annotators? (WWW 2023 Companion).
Awards & Honors
- Google PhD Fellowship – Institutional Nominee, nominated by Indiana University Bloomington (IUB).
- Graduate Student Travel Fellowship, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington (IUB), to present a poster at IEEE VIS 2026 (Boston).
- Travel Fund, Midwest Speech and Language Days (MSLD) 2026.
- Full Ph.D. Scholarship, Indiana University Bloomington (IUB).
- Full Ph.D. Scholarship, Singapore Management University (SMU).
- Outstanding Student Leader, Central South University.
- Second Prize, Information Security Competition, Central South University.
- Merit Award, East China Division, China College Student Cloud Computing Competition.
- Second Prize, U.S. Mathematical Modeling Competition.
- Third Prize, Shenghua Cup, Central South University.
- Second Prize, Hunan Province E-Commerce Challenge.
- Shanhe Yingcai Scholarship (Second Class).
- First-Class Scholarship (University Level), Central South University.
Research Organization
- Workshop Proposal, Delegation, Oversight, and Evaluation of AI Across the Research Lifecycle, ACM CHI Conference on Human Factors in Computing Systems (CHI 2027). Fan Huang, Kai-Cheng Yang, Munjung Kim.
- Workshop Proposal, What Do LLMs Believe? Belief Representation and Human-AI Alignment, International Conference on Learning Representations (ICLR 2027). Fan Huang, Byunghwee Lee, Haewoon Kwak, Jisun An.
Teaching — Indiana University Bloomington, Luddy School of Informatics, Computing, and Engineering
- Teaching Assistant, INFO-I 201 Mathematical Foundations of Informatics.
- Lecture Presentation — Vision Language Models (VLM), INFO-I 590 Foundation and Application for Large Language Models.
- Lecture Presentation — Retrieval Augmented Generation (RAG), INFO-I 590 Foundation and Application for Large Language Models.
- Teaching Assistant, INFO-I 590 Foundation and Application for Large Language Models.
- Teaching Assistant, INFO-I 590 Foundation and Application for Large Language Models.
- Teaching Assistant, INFO-I 590 Foundation and Application for Large Language Models.
Research Advising
- Master's Student: Sathvik Bandaru (co-advising)
- Undergraduate Student: Jack Waren (co-advising)
Research Experience
- Research Assistant, Indiana University Bloomington. Advisors: Prof. Jisun An and Prof. Haewoon Kwak · Collaborators: Prof. Yong-Yeol Ahn, Prof. Filippo Menczer, and Prof. Filippo Radicchi
- Quantitative Research Intern, Core Research Team, QuantLab Financial, Houston.
- Research Summer Internship, Indiana University Bloomington, supervised by Prof. Katy Börner.
- Research Assistant, Singapore Management University.
Presentations — Talks
- Poster presentation at InfoVis (Boston): “LLM Belief Atlas”.
- Invited talk, CNS Research Showcase, Prof. Katy Börner's lab, Indiana University Bloomington: “Cytolume: Interactive Exploration of Million-Level Cell-Embedding Maps in the Browser”.
- Invited research discussion, Squoosh, Inc.: “Evaluating LLM-Generated Preference Distributions”.
- Invited research talk, Prof. Michael Färber's lab, TU Dresden: “Trustworthiness of LLM Reasoning Capabilities”.
- Parallel talk at IC2S2 (Burlington, Vermont): “Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability”.
- Invited talk, Prof. Han Xue's lab, Donghua University, Shanghai: “LLM Moral Reasoning Trajectory Analysis”.
- Invited talk, Prof. Thai Le's lab, Indiana University Bloomington: “AI-Assisted Research”.
- Presentation at MSLD (UIUC): “Vulnerability of LLMs' Stated Belief? LLMs Belief Resistance Check Through Strategic Persuasive Conversation Interventions”.
- Oral presentation at MSLD (Ann Arbor, Michigan, USA): “ChatGPT Rates Like Human: Towards a Better Alignment of Text Explanation Quality Assessments”.
- Poster presentation at The Web Conference (WWW) (Austin, Texas, USA): “Is ChatGPT Better than Human Annotators?” & “Chain of Explanation”.
- YY Group, CNetS, Indiana University Bloomington: “Natural Language Explanation: From XAI to Human-AI Interaction”.
Presentations — Workshops
- Participant, Summer Institute of Computational Social Science (SICSS), NUS, Singapore.
- Co-organizer, Workshop “Introduction to NLP”, IEEE NTU Student Branch, NTU, Singapore.
Academic Service — Chairs
- Session Chair, EMNLP: Virtual Program Session (Topic: Interpretability and Analysis of Models for NLP).
- Session Chair, IC2S2: Science of Science (AI) Parallel Talk Session.
Academic Service — Program Committee Member
- WISE 2026 · PC
- IC2S2 2026 · PC
- WWW 2026 Web4Good · PC
- 7th CySoc @ ICWSM 2026 · PC
- 6th CySoc @ ICWSM 2025 · PC
- WebSci 2025 · PC
Academic Service — Conference Reviewer
- ICRA 2027 · Reviewer
- ICLR 2027 · Reviewer
- NeurIPS 2026 · Reviewer
- KDD 2026 · Reviewer
- COLM 2026 · Reviewer
- IUI 2026 · Reviewer
- ACL Rolling Review (ARR) 2026 · Reviewer
- ICWSM 2026 · Reviewer
- IMX 2025 · Reviewer
- ACL Rolling Review (ARR) 2025 · Reviewer
- CHI 2025 · Reviewer
- ICWSM 2025 · Reviewer
- IDC 2025 · Reviewer
- WSDM 2022 · Reviewer
Academic Service — Journal Reviewer
- PeerJ Computer Science
- Online Social Networks and Media
- Information Processing & Management
Organized Activities / Volunteer
- SODA Lab Research Talk: “Multimodal NLP Research Insights”, Dr. Henry Wei Han, Organizer.
- CNetS @ Luddy School Gathering Event, Organizer.
- ISSI, Student Volunteer.
Campus Leadership and Activities
- Founder, LLM Innovators Hub @ CNetS, Indiana University. Organize LLM research and application sharing sessions within CNetS.
- Member, IEEE NTU Student Branch, Nanyang Technological University. Co-organized the workshop “Introduction to NLP”.
- Academic Affairs Representative, Computer Science Class 1401, Central South University.
- Director, University Student Union Office, Central South University.
- Class Monitor, Microelectronics Class 1401, Central South University.
Research Committee
- Jisun AnAssistant Professor, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington
- Haewoon KwakAssociate Professor, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington
- Thai LeAssistant Professor, Computer Science, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington
- Filippo RadicchiProfessor, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington
Research Rotation Advisors
- Filippo MenczerLuddy Distinguished Professor of Informatics and Computer Science, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington
- Yong-Yeol (YY) AhnQuantitative Foundation Distinguished Professor of Data Science, School of Data Science, University of Virginia