Assessing Political Inclination of Bangla Language Models

Thapa, Surendrabikram, Maratha, Ashwarya, Hasib, Khan Md, Nasim, Mehwish, and Naseem, Usman (2023) Assessing Political Inclination of Bangla Language Models. In: Proceedings of the 1st Workshop on Bangla Language Processing. pp. 152-162. From: BLP 2023: First Workshop on Bangla Language Processing, 7 December 2023, Singapore.

[img]
Preview
PDF (Published Version) - Published Version
Available under License Creative Commons Attribution.

Download (455kB) | Preview
View at Publisher Website: https://doi.org/10.18653/v1/2023.banglal...
 
45


Abstract

Natural language processing has advanced with AI-driven language models (LMs), that are applied widely from text generation to question answering. These models are pre-trained on a wide spectrum of data sources, enhancing accuracy and responsiveness. However, this process inadvertently entails the absorption of a diverse spectrum of viewpoints inherent within the training data. Exploring political leaning within LMs due to such viewpoints remains a less-explored domain. In the context of a low-resource language like Bangla, this area of research is nearly non-existent. To bridge this gap, we comprehensively analyze biases present in Bangla language models, specifically focusing on social and economic dimensions. Our findings reveal the inclinations of various LMs, which will provide insights into ethical considerations and limitations associated with deploying Bangla LMs.

Item ID: 82400
Item Type: Conference Item (Research - E1)
ISBN: 9798891760585
Copyright Information: Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
Date Deposited: 14 Mar 2024 02:11
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460208 Natural language processing @ 100%
SEO Codes: 22 INFORMATION AND COMMUNICATION SERVICES > 2204 Information systems, technologies and services > 220403 Artificial intelligence @ 100%
Downloads: Total: 45
Last 12 Months: 30
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page