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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Large Language Models (LLMs) make natural interfaces to factual knowledge,but their usefulness is limited by their tendency to deliver inconsistentanswers to semantically equivalent questions. For example, a model mightpredict both "Anne Redpath passed away in Edinburgh." and "Anne Redpath's lifeended in London." In this work, we identify potential causes of inconsistencyand evaluate the effectiveness of two mitigation strategies: up-scaling andaugmenting the LM with a retrieval corpus. Our results on the LLaMA and Atlasmodels show that both strategies reduce inconsistency while retrievalaugmentation is considerably more efficient. We further consider anddisentangle the consistency contributions of different components of Atlas. Forall LMs evaluated we find that syntactical form and other evaluation taskartifacts impact consistency. Taken together, our results provide a betterunderstanding of the factors affecting the factual consistency of languagemodels.

The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models