Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.23096 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908473385549824 |
|---|---|
| author | Peterka, Tom Mallick, Tanwi Yildiz, Orcun Lenz, David Quammen, Cory Geveci, Berk |
| author_facet | Peterka, Tom Mallick, Tanwi Yildiz, Orcun Lenz, David Quammen, Cory Geveci, Berk |
| contents | Large language models (LLMs) are rapidly increasing in capability, but they still struggle with highly specialized programming tasks such as scientific visualization. We present an LLM assistant, ChatVis, that aids the LLM to generate Python code for ParaView scientific visualization tasks, without the need for retraining or fine-tuning the LLM. ChatVis employs chain-of-thought prompt simplification, retrieval-augmented prompt generation using a vector database of documentation and code examples, and error checking with iterative prompt feedback to correct errors until a visualization is produced. An integral part of our approach is a benchmark suite of canonical visualization tasks, ParaView regression tests, and scientific use cases that includes comprehensive evaluation metrics. We evaluate our visualization assistant by comparing results with a variety of top-performing unassisted LLMs. We find that all the metrics are significantly improved with ChatVis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23096 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChatVis: Large Language Model Agent for Generating Scientific Visualizations Peterka, Tom Mallick, Tanwi Yildiz, Orcun Lenz, David Quammen, Cory Geveci, Berk Human-Computer Interaction Large language models (LLMs) are rapidly increasing in capability, but they still struggle with highly specialized programming tasks such as scientific visualization. We present an LLM assistant, ChatVis, that aids the LLM to generate Python code for ParaView scientific visualization tasks, without the need for retraining or fine-tuning the LLM. ChatVis employs chain-of-thought prompt simplification, retrieval-augmented prompt generation using a vector database of documentation and code examples, and error checking with iterative prompt feedback to correct errors until a visualization is produced. An integral part of our approach is a benchmark suite of canonical visualization tasks, ParaView regression tests, and scientific use cases that includes comprehensive evaluation metrics. We evaluate our visualization assistant by comparing results with a variety of top-performing unassisted LLMs. We find that all the metrics are significantly improved with ChatVis. |
| title | ChatVis: Large Language Model Agent for Generating Scientific Visualizations |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2507.23096 |