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) are increasingly used for accessing informationon the web. Their truthfulness and factuality are thus of great interest. Tohelp users make the right decisions about the information they're getting, LLMsshould not only provide but also help users fact-check information. In thispaper, we conduct experiments with 80 crowdworkers in total to compare languagemodels with search engines (information retrieval systems) at facilitatingfact-checking by human users. We prompt LLMs to validate a given claim andprovide corresponding explanations. Users reading LLM explanations aresignificantly more efficient than using search engines with similar accuracy.However, they tend to over-rely the LLMs when the explanation is wrong. Toreduce over-reliance on LLMs, we ask LLMs to provide contrastive information -explain both why the claim is true and false, and then we present both sides ofthe explanation to users. This contrastive explanation mitigates users'over-reliance on LLMs, but cannot significantly outperform search engines.However, showing both search engine results and LLM explanations offers nocomplementary benefits as compared to search engines alone. Taken together,natural language explanations by LLMs may not be a reliable replacement forreading the retrieved passages yet, especially in high-stakes settings whereover-relying on wrong AI explanations could lead to critical consequences.

Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong