@inproceedings{chu-etal-2024-patent,
title = "Patent Response System Optimised for Faithfulness: Procedural Knowledge Embodiment with Knowledge Graph and Retrieval Augmented Generation",
author = "Chu, Jung-Mei and
Lo, Hao-Cheng and
Hsiang, Jieh and
Cho, Chun-Chieh",
editor = "Li, Sha and
Li, Manling and
Zhang, Michael JQ and
Choi, Eunsol and
Geva, Mor and
Hase, Peter and
Ji, Heng",
booktitle = "Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.knowllm-1.12",
doi = "10.18653/v1/2024.knowllm-1.12",
pages = "146--155",
abstract = "A successful response to Office Action is crucial for an invention to obtain a patent. While previous attempts have applied generalised LLMs, such as GPT-4, in the response process, there remains significant room for improvement in generating faithful, unbiased, and practically valuable responses. To address this issue, we propose the Patent Response System Optimised for Faithfulness (PRO). PRO explicitly incorporates procedural knowledge used by patent agents during drafting arguments in response. This framework comprises several key components: (1) Our proposed PRLLM is a LLM tailored for patent responses, designed to have comprehensive patent domain-specific knowledge. (2) Our proposed PPNet encodes legal interpretations and relationships between technical components from judicial sources through a knowledge graph. (3) The augmented generation processes retrieve relevant information from both the patent text and PPNet to augment the PRLLM{'}s input and generate faithful responses. Results show that PRO significantly reduces unfaithfulness across six error types compared to several settings. For instance, PRO outperforms GPT-4 by an average of 39{\%} in terms of faithfulness. This demonstrates the effectiveness of our domain-specific approach in improving the quality of automated patent responses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2024-patent">
<titleInfo>
<title>Patent Response System Optimised for Faithfulness: Procedural Knowledge Embodiment with Knowledge Graph and Retrieval Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jung-Mei</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao-Cheng</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieh</namePart>
<namePart type="family">Hsiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chun-Chieh</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sha</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">JQ</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mor</namePart>
<namePart type="family">Geva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Hase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A successful response to Office Action is crucial for an invention to obtain a patent. While previous attempts have applied generalised LLMs, such as GPT-4, in the response process, there remains significant room for improvement in generating faithful, unbiased, and practically valuable responses. To address this issue, we propose the Patent Response System Optimised for Faithfulness (PRO). PRO explicitly incorporates procedural knowledge used by patent agents during drafting arguments in response. This framework comprises several key components: (1) Our proposed PRLLM is a LLM tailored for patent responses, designed to have comprehensive patent domain-specific knowledge. (2) Our proposed PPNet encodes legal interpretations and relationships between technical components from judicial sources through a knowledge graph. (3) The augmented generation processes retrieve relevant information from both the patent text and PPNet to augment the PRLLM’s input and generate faithful responses. Results show that PRO significantly reduces unfaithfulness across six error types compared to several settings. For instance, PRO outperforms GPT-4 by an average of 39% in terms of faithfulness. This demonstrates the effectiveness of our domain-specific approach in improving the quality of automated patent responses.</abstract>
<identifier type="citekey">chu-etal-2024-patent</identifier>
<identifier type="doi">10.18653/v1/2024.knowllm-1.12</identifier>
<location>
<url>https://aclanthology.org/2024.knowllm-1.12</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>146</start>
<end>155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Patent Response System Optimised for Faithfulness: Procedural Knowledge Embodiment with Knowledge Graph and Retrieval Augmented Generation
%A Chu, Jung-Mei
%A Lo, Hao-Cheng
%A Hsiang, Jieh
%A Cho, Chun-Chieh
%Y Li, Sha
%Y Li, Manling
%Y Zhang, Michael JQ
%Y Choi, Eunsol
%Y Geva, Mor
%Y Hase, Peter
%Y Ji, Heng
%S Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F chu-etal-2024-patent
%X A successful response to Office Action is crucial for an invention to obtain a patent. While previous attempts have applied generalised LLMs, such as GPT-4, in the response process, there remains significant room for improvement in generating faithful, unbiased, and practically valuable responses. To address this issue, we propose the Patent Response System Optimised for Faithfulness (PRO). PRO explicitly incorporates procedural knowledge used by patent agents during drafting arguments in response. This framework comprises several key components: (1) Our proposed PRLLM is a LLM tailored for patent responses, designed to have comprehensive patent domain-specific knowledge. (2) Our proposed PPNet encodes legal interpretations and relationships between technical components from judicial sources through a knowledge graph. (3) The augmented generation processes retrieve relevant information from both the patent text and PPNet to augment the PRLLM’s input and generate faithful responses. Results show that PRO significantly reduces unfaithfulness across six error types compared to several settings. For instance, PRO outperforms GPT-4 by an average of 39% in terms of faithfulness. This demonstrates the effectiveness of our domain-specific approach in improving the quality of automated patent responses.
%R 10.18653/v1/2024.knowllm-1.12
%U https://aclanthology.org/2024.knowllm-1.12
%U https://doi.org/10.18653/v1/2024.knowllm-1.12
%P 146-155
Markdown (Informal)
[Patent Response System Optimised for Faithfulness: Procedural Knowledge Embodiment with Knowledge Graph and Retrieval Augmented Generation](https://aclanthology.org/2024.knowllm-1.12) (Chu et al., KnowLLM-WS 2024)
ACL