Abstract
VisuaLLM is a Python library that enables interactive visualization of common tasks in natural language generation with pretrained language models (using HuggingFace’s model API), with tight integration of benchmark datasets and fine-grained generation control. The system runs as a local generation backend server and features a web-based frontend, allowing simple interface configuration by minimal Python code. The currently implemented views include data visualization, next-token prediction with probability distributions, and decoding parameter control, with simple extension to additional tasks.- Anthology ID:
- 2023.inlg-demos.3
- Volume:
- Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czechia
- Editors:
- C. Maria Keet, Hung-Yi Lee, Sina Zarrieß
- Venues:
- INLG | SIGDIAL
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6–8
- Language:
- URL:
- https://aclanthology.org/2023.inlg-demos.3
- DOI:
- Cite (ACL):
- František Trebuňa and Ondrej Dusek. 2023. VisuaLLM: Easy Web-based Visualization for Neural Language Generation. In Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations, pages 6–8, Prague, Czechia. Association for Computational Linguistics.
- Cite (Informal):
- VisuaLLM: Easy Web-based Visualization for Neural Language Generation (Trebuňa & Dusek, INLG-SIGDIAL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2023.inlg-demos.3.pdf