@inproceedings{gao-etal-2024-beyond,
title = "Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph",
author = "Gao, Xiaochen and
Yao, Feng and
Zhao, Kewen and
He, Beilei and
Kumar, Animesh and
Krishnan, Vish and
Shang, Jingbo",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.285/",
doi = "10.18653/v1/2024.acl-long.285",
pages = "5218--5234",
abstract = "Model scaling is becoming the default choice for many language tasks due to the success of large language models (LLMs). However, it can fall short in specific scenarios where simple customized methods excel. In this paper, we delve into the patent approval prediction task and unveil that simple domain-specific graph methods outperform enlarging the model, using the intrinsic dependencies within the patent data. Specifically, we first extend the embedding-based state-of-the-art (SOTA) by scaling up its backbone model with various sizes of open-source LLMs, then explore prompt-based methods to harness proprietary LLMs' potential, but find the best results close to random guessing, underlining the ineffectiveness of model scaling-up. Hence, we propose a novel Fine-grained cLAim depeNdency (FLAN) Graph through meticulous patent data analyses, capturing the inherent dependencies across segments of the patent text. As it is model-agnostic, we apply cost-effective graph models to our FLAN Graph to obtain representations for approval prediction. Extensive experiments and detailed analyses prove that incorporating FLAN Graph via various graph models consistently outperforms all LLM baselines significantly. We hope that our observations and analyses in this paper can bring more attention to this challenging task and prompt further research into the limitations of LLMs."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2024-beyond">
<titleInfo>
<title>Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaochen</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kewen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beilei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Animesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vish</namePart>
<namePart type="family">Krishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Shang</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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</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>Model scaling is becoming the default choice for many language tasks due to the success of large language models (LLMs). However, it can fall short in specific scenarios where simple customized methods excel. In this paper, we delve into the patent approval prediction task and unveil that simple domain-specific graph methods outperform enlarging the model, using the intrinsic dependencies within the patent data. Specifically, we first extend the embedding-based state-of-the-art (SOTA) by scaling up its backbone model with various sizes of open-source LLMs, then explore prompt-based methods to harness proprietary LLMs’ potential, but find the best results close to random guessing, underlining the ineffectiveness of model scaling-up. Hence, we propose a novel Fine-grained cLAim depeNdency (FLAN) Graph through meticulous patent data analyses, capturing the inherent dependencies across segments of the patent text. As it is model-agnostic, we apply cost-effective graph models to our FLAN Graph to obtain representations for approval prediction. Extensive experiments and detailed analyses prove that incorporating FLAN Graph via various graph models consistently outperforms all LLM baselines significantly. We hope that our observations and analyses in this paper can bring more attention to this challenging task and prompt further research into the limitations of LLMs.</abstract>
<identifier type="citekey">gao-etal-2024-beyond</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.285</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.285/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>5218</start>
<end>5234</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph
%A Gao, Xiaochen
%A Yao, Feng
%A Zhao, Kewen
%A He, Beilei
%A Kumar, Animesh
%A Krishnan, Vish
%A Shang, Jingbo
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F gao-etal-2024-beyond
%X Model scaling is becoming the default choice for many language tasks due to the success of large language models (LLMs). However, it can fall short in specific scenarios where simple customized methods excel. In this paper, we delve into the patent approval prediction task and unveil that simple domain-specific graph methods outperform enlarging the model, using the intrinsic dependencies within the patent data. Specifically, we first extend the embedding-based state-of-the-art (SOTA) by scaling up its backbone model with various sizes of open-source LLMs, then explore prompt-based methods to harness proprietary LLMs’ potential, but find the best results close to random guessing, underlining the ineffectiveness of model scaling-up. Hence, we propose a novel Fine-grained cLAim depeNdency (FLAN) Graph through meticulous patent data analyses, capturing the inherent dependencies across segments of the patent text. As it is model-agnostic, we apply cost-effective graph models to our FLAN Graph to obtain representations for approval prediction. Extensive experiments and detailed analyses prove that incorporating FLAN Graph via various graph models consistently outperforms all LLM baselines significantly. We hope that our observations and analyses in this paper can bring more attention to this challenging task and prompt further research into the limitations of LLMs.
%R 10.18653/v1/2024.acl-long.285
%U https://aclanthology.org/2024.acl-long.285/
%U https://doi.org/10.18653/v1/2024.acl-long.285
%P 5218-5234
Markdown (Informal)
[Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph](https://aclanthology.org/2024.acl-long.285/) (Gao et al., ACL 2024)
ACL