English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The benefits and capabilities of pre-trained language models (LLMs) incurrent and future innovations are vital to any society. However, introducingand using LLMs comes with biases and discrimination, resulting in concernsabout equality, diversity and fairness, and must be addressed. Whileunderstanding and acknowledging bias in LLMs and developing mitigationstrategies are crucial, the generalised assumptions towards societal needs canresult in disadvantages towards under-represented societies and indigenouspopulations. Furthermore, the ongoing changes to actual and proposed amendmentsto regulations and laws worldwide also impact research capabilities in tacklingthe bias problem. This research presents a comprehensive survey synthesisingthe current trends and limitations in techniques used for identifying andmitigating bias in LLMs, where the overview of methods for tackling bias aregrouped into metrics, benchmark datasets, and mitigation strategies. Theimportance and novelty of this survey are that it explores the perspective ofunder-represented societies. We argue that current practices tackling the biasproblem cannot simply be 'plugged in' to address the needs of under-representedsocieties. We use examples from New Zealand to present requirements foradopting existing techniques to under-represented societies.

Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies