Highlight

Patent Response System Optimised for Faithfulness: Procedural Knowledge Embodiment with Knowledge Graph and Retrieval Augmented Generation

A proposed system for generating faithful and unbiased patent responses using a knowledge graph and retrieval augmented generation.

Based on

Patent Response System Optimised for Faithfulness: Procedural Knowledge Embodiment with Knowledge Graph and Retrieval Augmented Generation

By Jung-Mei Chu, Hao-Cheng Lo, Jieh Hsiang, Chun-Chieh Cho
Read original article →

The authors propose the Patent Response System Optimised for Faithfulness (PRO), which incorporates procedural knowledge and uses a tailored large language model to generate patent responses. PRO outperforms GPT-4 in terms of faithfulness, reducing unfaithfulness across six error types.

The system's effectiveness is demonstrated through experimental results.

Abstract

The authors propose the Patent Response System Optimised for Faithfulness (PRO), which incorporates procedural knowledge and uses a tailored large language model to generate patent responses. PRO outperforms GPT-4 in terms of faithfulness, reducing unfaithfulness across six error types. The system's effectiveness is demonstrated through experimental results.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

patent-response-systemfaithfulness-in-patent-responsesprocedural-knowledge-embodimentknowledge-graph-based-generationaugmented-generationKnowledge GraphsLarge Language ModelsRetrieval & RAGSemantic Interoperability
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources