About me
Hello! I’m Chaewan Chun (Chae).
I’m a Ph.D. candidate in Informatics at The Pennsylvania State University, advised by Dr. Dongwon Lee. My research focuses on multimodal misinformation detection, especially fact-checking in spoken, conversational audio. I build datasets and methods that aim for positive social impact by improving information integrity.
Before my Ph.D., I completed dual B.S. degrees in Computer Science (Magna Cum Laude) and Mathematics (Cum Laude), along with a minor in Statistics, at Penn State as a Schreyer Honors College scholar.
Interests: Machine Learning; Generative AI; Large Language Models; Computer Vision; Speech & Audio Processing; Multimodal Learning; Information Retrieval
Updates
· Two papers accepted to SALMA at EMNLP 2026
· Selected for the Future Leaders of AI doctoral consortium at the ACM AI Leadership Summit; will attend in Atlanta, Georgia
· Two papers accepted to EMNLP 2026: one in main, one in Findings
· Completed a Ph.D. Research Scientist Internship at the Air Force Research Laboratory (AFRL)
· Selected for an oral presentation at ACL 2026 in San Diego
· Paper accepted at ACL 2026
· Paper accepted in Patterns
· Penn State team selected as a global Top 10 finalist in the Amazon Nova AI Challenge
Earlier updates
· Paper accepted in IEEE TPAMI
· Passed the Ph.D. Comprehensive Exam
· Attended the Grace Hopper Celebration 2025 in Chicago
· Presented the MAD poster at SBP-BRiMS 2025 at Carnegie Mellon University
· Paper accepted at SBP-BRiMS 2025
· Presented a poster at the MASC-SLL Symposium
Publications
2026
Context-Aware Multimodal Claim Verification in Spoken Dialogues
The 2nd Speech and Audio Language Models Workshop (SALMA), EMNLP, 2026
Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts
The 2nd Speech and Audio Language Models Workshop (SALMA), EMNLP, 2026
TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio (PDF)
Findings of the Association for Computational Linguistics: EMNLP 2026
AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries? (PDF)
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)
When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms (PDF)
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL), Oral Presentation, 2026
Mapping the Flow of Painterly Gesture (PDF)
Patterns, vol. 7, no. 3, article 101516, 2026
Computational Investigation of Abstraction in Claude Monet's Water Lilies Through Brushstroke Analysis (PDF)
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 48, no. 6, pp. 7129–7146, 2026
2025
MAD: A Benchmark for Multi-Turn Audio Dialogue Fact-Checking (PDF)
International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS), Working paper, 2025
2022
Robust Image Classification Based on Pixel Importance (PDF)
Schreyer Honors Thesis, Penn State University, 2022