Leixian Shen — accepted AI-conference papers

2025

nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning

Tianqi Luo, Chuhan Huang, Leixian Shen, Boyan Li, Shuyu Shen, Wei Zeng +2

NeurIPS 2025poster

Text-to-Visualization (Text2VIS) enables users to create visualizations from natural language queries, making data insights more accessible. However, Text2VIS faces challenges in interpreting ambiguous queries, as users often express their visualization needs in imprecise language. To address this…

Cited by 0 Source ↗code ↗Scholar ↗

2024

ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering

Yifan Wu, Lutao Yan, Leixian Shen, Yunhai Wang, Nan Tang, Yuyu Luo

EMNLP 2024finding

Chart question answering (ChartQA) tasks play a critical role in interpreting and extracting insights from visualization charts. While recent advancements in multimodal large language models (MLLMs) like GPT-4o have shown promise in high-level ChartQA tasks, such as chart captioning, their effective…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗