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

Large language models (LLMs) have been shown to perform well at a variety ofsyntactic, discourse, and reasoning tasks. While LLMs are increasingly deployedin many forms including conversational agents that interact with humans, welack a grounded benchmark to measure how well LLMs understand \textit{social}language. Here, we introduce a new theory-driven benchmark, SocKET, thatcontains 58 NLP tasks testing social knowledge which we group into fivecategories: humor & sarcasm, offensiveness, sentiment & emotion, andtrustworthiness. In tests on the benchmark, we demonstrate that current modelsattain only moderate performance but reveal significant potential for tasktransfer among different types and categories of tasks, which were predictedfrom theory. Through zero-shot evaluations, we show that pretrained modelsalready possess some innate but limited capabilities of social languageunderstanding and training on one category of tasks can improve zero-shottesting on others. Our benchmark provides a systematic way to analyze modelperformance on an important dimension of language and points to clear room forimprovement to build more socially-aware LLMs. The associated resources arereleased at https://github.com/minjechoi/SOCKET.

Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark