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

Have Large Language Models (LLMs) developed a personality? The short answeris a resounding "We Don't Know!". In this paper, we show that we do not yethave the right tools to measure personality in language models. Personality isan important characteristic that influences behavior. As LLMs emulatehuman-like intelligence and performance in various tasks, a natural question toask is whether these models have developed a personality. Previous works haveevaluated machine personality through self-assessment personality tests, whichare a set of multiple-choice questions created to evaluate personality inhumans. A fundamental assumption here is that human personality tests canaccurately measure personality in machines. In this paper, we investigate theemergence of personality in five LLMs of different sizes ranging from 1.5B to30B. We propose the Option-Order Symmetry property as a necessary condition forthe reliability of these self-assessment tests. Under this condition, theanswer to self-assessment questions is invariant to the order in which theoptions are presented. We find that many LLMs personality test responses do notpreserve option-order symmetry. We take a deeper look at LLMs test responseswhere option-order symmetry is preserved to find that in these cases, LLMs donot take into account the situational statement being tested and produce theexact same answer irrespective of the situation being tested. We also identifythe existence of inherent biases in these LLMs which is the root cause of theaforementioned phenomenon and makes self-assessment tests unreliable. Theseobservations indicate that self-assessment tests are not the correct tools tomeasure personality in LLMs. Through this paper, we hope to draw attention tothe shortcomings of current literature in measuring personality in LLMs andcall for developing tools for machine personality measurement.

Have Large Language Models Developed a Personality?: Applicability of Self-Assessment Tests in Measuring Personality in LLMs