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

Being able to predict people's opinions on issues and behaviors in realisticscenarios can be helpful in various domains, such as politics and marketing.However, conducting large-scale surveys like the European Social Survey tosolicit people's opinions on individual issues can incur prohibitive costs.Leveraging prior research showing influence of core human values on individualdecisions and actions, we propose to use value-injected large language models(LLM) to predict opinions and behaviors. To this end, we present ValueInjection Method (VIM), a collection of two methods -- argument generation andquestion answering -- designed to inject targeted value distributions into LLMsvia fine-tuning. We then conduct a series of experiments on four tasks to testthe effectiveness of VIM and the possibility of using value-injected LLMs topredict opinions and behaviors of people. We find that LLMs value-injected withvariations of VIM substantially outperform the baselines. Also, the resultssuggest that opinions and behaviors can be better predicted usingvalue-injected LLMs than the baseline approaches.

From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models