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 model (LLM) has achieved outstanding performance on variousdownstream tasks with its powerful natural language understanding and zero-shotcapability, but LLM still suffers from knowledge limitation. Especially inscenarios that require long logical chains or complex reasoning, thehallucination and knowledge limitation of LLM limit its performance in questionanswering (QA). In this paper, we propose a novel framework KnowledgeNavigatorto address these challenges by efficiently and accurately retrieving externalknowledge from knowledge graph and using it as a key factor to enhance LLMreasoning. Specifically, KnowledgeNavigator first mines and enhances thepotential constraints of the given question to guide the reasoning. Then itretrieves and filters external knowledge that supports answering throughiterative reasoning on knowledge graph with the guidance of LLM and thequestion. Finally, KnowledgeNavigator constructs the structured knowledge intoeffective prompts that are friendly to LLM to help its reasoning. We evaluateKnowledgeNavigator on multiple public KGQA benchmarks, the experiments show theframework has great effectiveness and generalization, outperforming previousknowledge graph enhanced LLM methods and is comparable to the fully supervisedmodels.

KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph