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 versatility of Large Language Models (LLMs) on natural languageunderstanding tasks has made them popular for research in social sciences. Inparticular, to properly understand the properties and innate personas of LLMs,researchers have performed studies that involve using prompts in the form ofquestions that ask LLMs of particular opinions. In this study, we take acautionary step back and examine whether the current format of promptingenables LLMs to provide responses in a consistent and robust manner. We firstconstruct a dataset that contains 693 questions encompassing 39 differentinstruments of persona measurement on 115 persona axes. Additionally, we designa set of prompts containing minor variations and examine LLM's capabilities togenerate accurate answers, as well as consistency variations to examine theirconsistency towards simple perturbations such as switching the option order.Our experiments on 15 different open-source LLMs reveal that even simpleperturbations are sufficient to significantly downgrade a model'squestion-answering ability, and that most LLMs have low negation consistency.Our results suggest that the currently widespread practice of prompting isinsufficient to accurately capture model perceptions, and we discuss potentialalternatives to improve such issues.

You don't need a personality test to know these models are unreliable:  Assessing the Reliability of Large Language Models on Psychometric  Instruments