Modeling Disclosive Transparency in NLP Application Descriptions
Michael Saxon, Sharon Levy, Xinyi Wang, Alon Albalak, William Yang Wang
Abstract
Broader disclosive transparency—truth and clarity in communication regarding the function of AI systems—is widely considered desirable. Unfortunately, it is a nebulous concept, difficult to both define and quantify. This is problematic, as previous work has demonstrated possible trade-offs and negative consequences to disclosive transparency, such as a confusion effect, where “too much information” clouds a reader’s understanding of what a system description means. Disclosive transparency’s subjective nature has rendered deep study into these problems and their remedies difficult. To improve this state of affairs, We introduce neural language model-based probabilistic metrics to directly model disclosive transparency, and demonstrate that they correlate with user and expert opinions of system transparency, making them a valid objective proxy. Finally, we demonstrate the use of these metrics in a pilot study quantifying the relationships between transparency, confusion, and user perceptions in a corpus of real NLP system descriptions.- Anthology ID:
- 2021.emnlp-main.153
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2023–2037
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.153
- DOI:
- 10.18653/v1/2021.emnlp-main.153
- Cite (ACL):
- Michael Saxon, Sharon Levy, Xinyi Wang, Alon Albalak, and William Yang Wang. 2021. Modeling Disclosive Transparency in NLP Application Descriptions. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2023–2037, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Modeling Disclosive Transparency in NLP Application Descriptions (Saxon et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2021.emnlp-main.153.pdf
- Code
- michaelsaxon/disclosive-transparency