5 papers
TA-RAG: Tone Awareness as a Design Imperative for Retrieval-Augmented Generation
Yong-Bin Kang, Anthony McCosker
Retrieval-Augmented Generation (RAG) has become a robust architecture for grounding large language models (LLMs) in trusted knowledge. However, standard RAG systems exhibit a struc…
DysLexLens: A Low-Resource LLM Framework for Analysing Dyslexic Learners Insights from Online Forums
Dana Rezazadegan, Atie Kia, Phongpadid Nandavong +6
Dyslexic learners increasingly use artificial intelligence (AI) tools to support reading, writing, organisation, and study-related tasks. However, their lived experiences with thes…
TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication
Yong-Bin Kang, Anthony McCosker
Retrieval-augmented generation (RAG) successfully grounds large language model (LLM) outputs in trusted documents, but factual grounding alone is insufficient for sensitive peer-su…
Analysis of Terms of Service on Social Media Platforms: Consent Challenges and Assessment Metrics
Yong-Bin Kang, Anthony McCosker
Social media platforms typically obtain user consent through Terms of Service (ToS) presented at account creation, rather than through dedicated consent forms. This study investiga…
Missing the human touch? A computational stylometry analysis of GPT-4 translations of online Chinese literature
Xiaofang Yao, Yong-Bin Kang, Anthony McCosker
Existing research indicates that machine translations (MTs) of literary texts are often unsatisfactory. MTs are typically evaluated using automated metrics and subjective human rat…