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

Recent work has aimed to capture nuances of human behavior by using LLMs tosimulate responses from particular demographics in settings like social scienceexperiments and public opinion surveys. However, there are currently noestablished ways to discuss or evaluate the quality of such LLM simulations.Moreover, there is growing concern that these LLM simulations are flattenedcaricatures of the personas that they aim to simulate, failing to capture themultidimensionality of people and perpetuating stereotypes. To bridge thesegaps, we present CoMPosT, a framework to characterize LLM simulations usingfour dimensions: Context, Model, Persona, and Topic. We use this framework tomeasure open-ended LLM simulations' susceptibility to caricature, defined viatwo criteria: individuation and exaggeration. We evaluate the level ofcaricature in scenarios from existing work on LLM simulations. We find that forGPT-4, simulations of certain demographics (political and marginalized groups)and topics (general, uncontroversial) are highly susceptible to caricature.

CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations