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

Entity resolution, the task of identifying and merging records that refer tothe same real-world entity, is crucial in sectors like e-commerce, healthcare,and law enforcement. Large Language Models (LLMs) introduce an innovativeapproach to this task, capitalizing on their advanced linguistic capabilitiesand a ``pay-as-you-go'' model that provides significant advantages to thosewithout extensive data science expertise. However, current LLMs are costly dueto per-API request billing. Existing methods often either lack quality orbecome prohibitively expensive at scale. To address these problems, we proposean uncertainty reduction framework using LLMs to improve entity resolutionresults. We first initialize possible partitions of the entity cluster, referto the same entity, and define the uncertainty of the result. Then, we reducethe uncertainty by selecting a few valuable matching questions for LLMverification. Upon receiving the answers, we update the probabilitydistribution of the possible partitions. To further reduce costs, we design anefficient algorithm to judiciously select the most valuable matching pairs toquery. Additionally, we create error-tolerant techniques to handle LLM mistakesand a dynamic adjustment method to reach truly correct partitions. Experimentalresults show that our method is efficient and effective, offering promisingapplications in real-world tasks.

On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach