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/

Zendy Plus

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

Zendy Tools

Zendy Open

Large Language Models (LLMs) might hallucinate facts, while curated KnowledgeGraph (KGs) are typically factually reliable especially with domain-specificknowledge. Measuring the alignment between KGs and LLMs can effectively probethe factualness and identify the knowledge blind spots of LLMs. However,verifying the LLMs over extensive KGs can be expensive. In this paper, wepresent KGLens, a Thompson-sampling-inspired framework aimed at effectively andefficiently measuring the alignment between KGs and LLMs. KGLens features agraph-guided question generator for converting KGs into natural language, alongwith a carefully designed importance sampling strategy based on parameterizedKG structure to expedite KG traversal. Our simulation experiment compares thebrute force method with KGLens under six different sampling methods,demonstrating that our approach achieves superior probing efficiency.Leveraging KGLens, we conducted in-depth analyses of the factual accuracy often LLMs across three large domain-specific KGs from Wikidata, composing over19K edges, 700 relations, and 21K entities. Human evaluation results indicatethat KGLens can assess LLMs with a level of accuracy nearly equivalent to thatof human annotators, achieving 95.7% of the accuracy rate.

KGLens: Towards Efficient and Effective Knowledge Probing of Large Language Models with Knowledge Graphs