One paper accepted for JURIX 2025 (Short Paper): 'Reinforcement Learning with Argument-Structured Reward for Court Decision Abstractive Summarization.'
One paper accepted for NeurIPS 2025 (Main Track): 'Language-Bias-Resilient Visual Question Answering via Adaptive Multi-Margin Collaborative Debiasing.'
Proposed a novel legal AI task, Legal Fact Prediction (LFP), and released a benchmark LFPBench. This work has been accepted for EMNLP 2025 Main Conference.
Developed a privacy-preserving database synthesis method for benchmarking scenarios, PrivBench. This work has been accepted for VLDB 2025.
Explored the spontaneous cooperation of LLM agents in competing environments. This work has been accepted for EMNLP 2024 Findings.
Research Experience
Currently working at Onizuka Lab, Graduate School of Information Science and Technology, Osaka University, collaborating with Prof. Makoto Onizuka and Prof. Chuan Xiao.
Education
Received Ph.D. in Informatics from Kyoto University in 2023, under the supervision of Prof. Masatoshi Yoshikawa and Prof. Yang Cao.
Background
Currently an Assistant Professor at the Graduate School of Information Science and Technology, Osaka University. Research interests lie at the intersection of computer science, law, and economics, with a particular focus on data market, data privacy, and computational law.
Miscellany
Personal interests not mentioned. Contact: zheng[at]ist[dot]osaka-u[dot]ac[dot]jp.