Publications

Simulating Hate Speech Cascades with Multi-LLM Agents: Empirical Grounding, Modeling Fidelity, and Intervention Strategies

Fan Huang

Preprint · 2026 · arXiv

Online harm LLMs & responsible AI

ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning

Fan Huang

Preprint · 2026 · arXiv

Reasoning & interpretability LLMs & responsible AI

CogBias: Measuring and Mitigating Cognitive Bias in Large Language Models

Fan Huang, Songheng Zhang, Haewoon Kwak, Jisun An

Preprint · 2026 · arXiv

Bias & fairness LLMs & responsible AI

Can LLMs Predict Academic Collaboration? Topology Heuristics vs. LLM-Based Link Prediction on Real Co-authorship Networks

Fan Huang, Munjung Kim

Preprint · 2026 · arXiv

Networks LLMs & responsible AI

Reasoning Topology Matters: Network-of-Thought for Complex Reasoning Tasks

Fan Huang

Preprint · 2026 · arXiv

Reasoning & interpretability Networks

Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based ExplainabilityFeatured

Fan Huang, Haewoon Kwak, Jisun An

IC2S2 2026 (Parallel Talk) · 2026 · arXiv

arXiv:2603.16017 GitHub: LLM-Morality

Reasoning & interpretability LLMs & responsible AI

Vulnerability of LLMs' Stated Belief? LLMs Belief Resistance Check Through Strategic Persuasive Conversation InterventionsFeatured

Fan Huang, Haewoon Kwak, Jisun An

ACL 2026 Findings · 2026 ACL

arXiv:2601.13590 GitHub: LLM-Stated-Belief

Beliefs & opinions LLMs & responsible AI

LLMs as Implicit Probabilistic World Models: Distributional Stability, Convergence, and Scale Discordance

Fan Huang, Minsuk Kim

OpenReview · 2026

OpenReview PDF

Reasoning & interpretability LLMs & responsible AI

XChoice: Explainable Evaluation of AI-Human Alignment in LLM-based Constrained Choice Decision Making

Weihong Qi, Fan Huang, Rasika Muralidharan, Jisun An, Haewoon Kwak

IC2S2 2026 (Poster) · 2026 · arXiv

Human–AI alignment LLMs & responsible AI

Is DeepSeek a New Voice Among LLMs in Public Opinion Simulation?

Weihong Qi, Fan Huang, Jisun An, Haewoon Kwak

ICDM 2025 · 2025 ICDM

Beliefs & opinions LLMs & responsible AI

Dif: A Framework for Benchmarking and Verifying Implicit Bias in LLMs

Lake Yin, Fan Huang

Preprint · 2025 · arXiv

Bias & fairness LLMs & responsible AI

The Rise of Bluesky

Ozgur Can Seckin, Filipi Nascimento Silva, Bao Tran Truong, Sangyeon Kim, Fan Huang, Nick Liu, Alessandro Flammini, Filippo Menczer

Preprint · 2025 · arXiv

User behavior Networks

Token-Ensemble Text Generation: On Attacking the Automatic AI-Generated Text Detection

Fan Huang, Haewoon Kwak, Jisun An

Preprint · 2024 · arXiv

NLP & generation LLMs & responsible AI

ChatGPT Rates Like Human: Towards a Better Alignment of Text Explanation Quality AssessmentsFeatured

Fan Huang, Haewoon Kwak, Kunwoo Park, Jisun An

LREC-COLING 2024 · 2024 LREC-COLING

NLP & generation Human–AI alignment

YouNICon: YouTube's CommuNIty of Conspiracy Videos

Shaoyi Liaw, Fan Huang, Fabricio Benevenuto, Haewoon Kwak, Jisun An

ICWSM 2023 · 2023 ICWSM

Online harm User behavior

Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate SpeechFeatured

Fan Huang, Haewoon Kwak, Jisun An

The Web Conference (WWW) 2023 · 2023 WWW

arXiv:2302.07736

Online harm NLP & generation

Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate SpeechFeatured

Fan Huang, Haewoon Kwak, Jisun An

The Web Conference (WWW) 2023 · 2023 WWW

Online harm NLP & generation

Highlight Timestamp Detection Model for Comedy Videos via Multimodal Sentiment Analysis

Fan Huang

Preprint · 2021 · arXiv

arXiv:2106.00451

NLP & generation

Network Activities Recognition and Analysis Based on Supervised Machine Learning Classification Methods Using J48 and Naïve Bayes Algorithm

Fan Huang

Preprint · 2021 · arXiv

arXiv:2105.13698

Networks