Abstract
Pre-trained language models and other generative models have revolutionized NLP and beyond. However, these models tend to reproduce undesirable biases present in their training data. Also, they may overlook patterns that are important but challenging to capture. To address these limitations, researchers have introduced distributional control techniques. These techniques, not limited to language, allow controlling the prevalence (i.e. expectations) of any features of interest in the model’s outputs. Despite their potential, the widespread adoption of these techniques has been hindered by the difficulty in adapting the complex, disconnected code. Here, we present disco, an open-source Python library that brings these techniques to the broader public- Anthology ID:
- 2023.acl-demo.14
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Danushka Bollegala, Ruihong Huang, Alan Ritter
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 144–160
- Language:
- URL:
- https://aclanthology.org/2023.acl-demo.14
- DOI:
- 10.18653/v1/2023.acl-demo.14
- Award:
- Demo Track: Outstanding Paper Award
- Cite (ACL):
- Germán Kruszewski, Jos Rozen, and Marc Dymetman. 2023. disco: a toolkit for Distributional Control of Generative Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 144–160, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- disco: a toolkit for Distributional Control of Generative Models (Kruszewski et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.acl-demo.14.pdf