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

Incorporating factual knowledge in knowledge graph is regarded as a promisingapproach for mitigating the hallucination of large language models (LLMs).Existing methods usually only use the user's input to query the knowledgegraph, thus failing to address the factual hallucination generated by LLMsduring its reasoning process. To address this problem, this paper proposesKnowledge Graph-based Retrofitting (KGR), a new framework that incorporatesLLMs with KGs to mitigate factual hallucination during the reasoning process byretrofitting the initial draft responses of LLMs based on the factual knowledgestored in KGs. Specifically, KGR leverages LLMs to extract, select, validate,and retrofit factual statements within the model-generated responses, whichenables an autonomous knowledge verifying and refining procedure without anyadditional manual efforts. Experiments show that KGR can significantly improvethe performance of LLMs on factual QA benchmarks especially when involvingcomplex reasoning processes, which demonstrates the necessity and effectivenessof KGR in mitigating hallucination and enhancing the reliability of LLMs.

Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting