1. ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty (Findings of ACL 2025)
2. TILFA: A unified framework for text, image, and layout fusion in argument mining (The 10th Workshop on Argument Mining 2023)
3. Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty? (ACL 2025, short paper)
4. The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning (TMLR 2025)
5. AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation (ACL 2024)
6. KnowComp Submission for WMT23 Sign Language Translation Task (WMT 2023)
7. Glyph Features Matter: A Multimodal Solution for EvaHan in LT4HALA2022 (LT4HALA 2022)
8. CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration? (Under Review)
9. CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents (Under Review)
10. AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (Under Review)
11. SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding (Under Review)
12. Prospect Theory Fails for LLMs: Revealing Instability of Decision-Making under Epistemic Uncertainty (Under Review)
Research Experience
Involved in multiple research projects, including but not limited to: ComparisonQA, TILFA, Revisiting Epistemic Markers in Confidence Estimation, The Curse of CoT, AbsInstruct, etc.
Education
Received Bachelor’s degree in Computer Science and Technology from Harbin Institute of Technology (Shenzhen) in 2024, where she conducted research under the guidance of Prof. Baotian Hu; currently a second-year Ph.D. student at Hong Kong University of Science and Technology, supervised by Prof. Yangqiu Song.
Background
Research interests: Natural Language Processing, Trustworthy AI, Confidence Calibration, Multimodal Learning. Currently a Ph.D. student in Computer Science and Engineering at Hong Kong University of Science and Technology, supervised by Prof. Yangqiu Song.