Conference Paper

Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering

JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audience

ToMBench: Benchmarking Theory of Mind in Large Language Models

A Pilot Study on Dialogue-Level Dependency Parsing for Chinese

Document and Word Representations Generated by Graph Convolutional Network and BERT for Short Text Classification