Natural language processing for dialects of a language: A survey

A Joshi, R Dabre, D Kanojia, Z Li, H Zhan… - ACM Computing …, 2024 - dl.acm.org
State-of-the-art natural language processing (NLP) models are trained on massive training
corpora, and report a superlative performance on evaluation datasets. This survey delves …

ChatGPT promises and challenges in education: Computational and ethical perspectives

A Adel, A Ahsan, C Davison - Education Sciences, 2024 - search.proquest.com
This paper investigates the integration of ChatGPT into educational environments, focusing
on its potential to enhance personalized learning and the ethical concerns it raises. Through …

Language discrepancies in the performance of generative artificial intelligence models: an examination of infectious disease queries in English and Arabic

M Sallam, K Al-Mahzoum, O Alshuaib, H Alhajri… - BMC Infectious …, 2024 - Springer
Background Assessment of artificial intelligence (AI)-based models across languages is
crucial to ensure equitable access and accuracy of information in multilingual contexts. This …

GenAI Advertising: Risks of Personalizing Ads with LLMs

BJ Tang, K Sun, NT Curran, F Schaub… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advances in large language models have enabled the creation of highly effective
chatbots, which may serve as a platform for targeted advertising. This paper investigates the …

One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks

F Lin, S Mao, E La Malfa, V Hofmann… - arXiv preprint arXiv …, 2024 - arxiv.org
Language is not monolithic. While many benchmarks are used as proxies to systematically
estimate Large Language Models'(LLM) performance in real-life tasks, they tend to ignore …

Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese

RMK Freitag, TS de Gois - arXiv preprint arXiv:2410.10991, 2024 - arxiv.org
Different of biases are reproduced in LLM-generated responses, including dialectal biases.
A study based on prompt engineering was carried out to uncover how LLMs discriminate …

Human-Machine Interfaces for Subsea Telerobotics: From Soda-straw to Natural Language Interactions

A Abdullah, R Chen, D Blow, T Uthai, EJ Du… - arXiv preprint arXiv …, 2024 - arxiv.org
This review explores the evolution of human-machine interfaces (HMIs) for subsea
telerobotics, tracing back the transition from traditional first-person" soda-straw" consoles …

The Language of Weather: Social Media Reactions to Weather Accounting for Climatic and Linguistic Baselines

JC Young, R Arthur, HTP Williams - arXiv preprint arXiv:2407.07683, 2024 - arxiv.org
This study explores how different weather conditions influence public sentiment on social
media, focusing on Twitter data from the UK. By considering climate and linguistic baselines …

Evaluating AI-Generated Language as Models for Strategic Competence in English Language Teaching.

PA Nguyen - IAFOR Journal of Education, 2024 - ERIC
Strategic competence, the ability to use communication strategies (CS) to overcome
challenges and enhance communication effectiveness, is crucial in language learning …

Finding A Voice: Evaluating African American Dialect Generation for Chatbot Technology

SE Finch, ES Paek, S Kwon, I Choi, J Wells… - arXiv preprint arXiv …, 2025 - arxiv.org
As chatbots become increasingly integrated into everyday tasks, designing systems that
accommodate diverse user populations is crucial for fostering trust, engagement, and …