Waitgpt: Monitoring and steering conversational llm agent in data analysis with on-the-fly code visualization

L Xie, C Zheng, H Xia, H Qu, C Zhu-Tian - Proceedings of the 37th …, 2024 - dl.acm.org
Large language models (LLMs) support data analysis through conversational user
interfaces, as exemplified in OpenAI's ChatGPT (formally known as Advanced Data Analysis …

[PDF][PDF] Spreadsheetllm: Encoding spreadsheets for large language models

Y Tian, J Zhao, H Dong, J Xiong… - arXiv preprint …, 2024 - readwise-assets.s3.amazonaws.com
Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts,
and varied formatting options, which pose significant challenges for large language models …

Chartx & chartvlm: A versatile benchmark and foundation model for complicated chart reasoning

R Xia, B Zhang, H Ye, X Yan, Q Liu, H Zhou… - arXiv preprint arXiv …, 2024 - arxiv.org
Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged
continuously. However, their capacity to query information depicted in visual charts and …

SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation

Z Ma, B Zhang, J Zhang, J Yu, X Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce SpreadsheetBench, a challenging spreadsheet manipulation benchmark
exclusively derived from real-world scenarios, designed to immerse current large language …

[PDF][PDF] CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing

X He, J Zou, Y Lin, M Zhou, S Han… - arXiv preprint arXiv …, 2024 - jiaruzouu.github.io
Abstract Large Language Models (LLMs) have revolutionized code generation ability by
converting natural language descriptions into executable code. However, generating …

Encoding Spreadsheets for Large Language Models

H Dong, J Zhao, Y Tian, J Xiong, M Zhou… - Proceedings of the …, 2024 - aclanthology.org
Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts,
and varied formatting options, which pose significant challenges for large language models …

LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution

Y Zhao, J Wang, L Xiang, X Zhang… - … on Visualization and …, 2024 - ieeexplore.ieee.org
Visual analytics requires analysts to constantly plan and execute analysis tasks based on
observations and generate visualizations and support analysis for gaining insights from …

CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing

X He, J Zou, Y Lin, M Zhou, S Han… - Proceedings of the …, 2024 - aclanthology.org
Abstract Large Language Models have revolutionized code generation ability by converting
natural language descriptions into executable code. However, generating complex code …

Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning

J Xing, Y He, M Zhou, H Dong, S Han, D Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
In this work, we propose Table-LLM-Specialist, or Table-Specialist for short, as a new self-
trained fine-tuning paradigm specifically designed for table tasks. Our insight is that for each …

Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents

J Li, N Huo, Y Gao, J Shi, Y Zhao, G Qu, Y Wu… - arXiv preprint arXiv …, 2024 - arxiv.org
Interactive Data Analysis, the collaboration between humans and LLM agents, enables real-
time data exploration for informed decision-making. The challenges and costs of collecting …