The Dark Side of AI Transformers: Sentiment Polarization & the Loss of Business Neutrality by NLP Transformers

The use of Transfer Learning & Transformers has steadily improved accuracy and has significantly contributed in solving complex computation problems. However, this transformer led accuracy improvement in Applied AI Analytics specifically in sentiment analytics comes with the dark side. It is observed during experiments that a lot of these improvements in transformer led accuracy of one class of sentiment has been at the cost of polarization of another class of sentiment and the failing of neutrality. This lack of neutrality poses an acute problem in the Applied NLP space, which relies heavily on the computational outputs of sentiment analytics for reliable industry ready tasks.

New Methods & Metrics for LFQA tasks

Long-form question answering (LFQA) tasks require retrieving the documents pertinent to a query, using them to form a paragraph-length answer. Despite considerable progress in LFQA modeling, fundamental issues impede its progress: i) train/validation/test dataset overlap, ii) absence of automatic metrics and iii) generated answers not being "grounded" in retrieved documents. This work addresses every one these critical bottlenecks, contributing natural language inference/generation (NLI/NLG) methods and metrics that make significant strides to their alleviation.