@inproceedings{lin-jang-2025-concept,
title = "Concept-Based {RAG} Models: A High-Accuracy Fact Retrieval Approach",
author = "Lin, Cheng-Yu and
Jang, Jyh-Shing",
editor = "Chen, Chung-Chi and
Moreno-Sandoval, Antonio and
Huang, Jimin and
Xie, Qianqian and
Ananiadou, Sophia and
Chen, Hsin-Hsi",
booktitle = "Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.finnlp-1.8/",
pages = "96--100",
abstract = "This study introduces a concept-based methodology to optimize Retrieval-Augmented Generation (RAG) tasks by assessing dataset certainty using entropy-based metrics and concept extraction techniques. Unlike traditional methods focused on reducing LLM hallucinations or modifying data structures, this approach evaluates inherent knowledge uncertainty from an LLM perspective. By pre-processing documents with LLMs, the concept-based method significantly enhances precision in tasks demanding high accuracy, such as legal, finance, or formal document responses."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-jang-2025-concept">
<titleInfo>
<title>Concept-Based RAG Models: A High-Accuracy Fact Retrieval Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheng-Yu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyh-Shing</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Moreno-Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study introduces a concept-based methodology to optimize Retrieval-Augmented Generation (RAG) tasks by assessing dataset certainty using entropy-based metrics and concept extraction techniques. Unlike traditional methods focused on reducing LLM hallucinations or modifying data structures, this approach evaluates inherent knowledge uncertainty from an LLM perspective. By pre-processing documents with LLMs, the concept-based method significantly enhances precision in tasks demanding high accuracy, such as legal, finance, or formal document responses.</abstract>
<identifier type="citekey">lin-jang-2025-concept</identifier>
<location>
<url>https://aclanthology.org/2025.finnlp-1.8/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>96</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Concept-Based RAG Models: A High-Accuracy Fact Retrieval Approach
%A Lin, Cheng-Yu
%A Jang, Jyh-Shing
%Y Chen, Chung-Chi
%Y Moreno-Sandoval, Antonio
%Y Huang, Jimin
%Y Xie, Qianqian
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%S Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F lin-jang-2025-concept
%X This study introduces a concept-based methodology to optimize Retrieval-Augmented Generation (RAG) tasks by assessing dataset certainty using entropy-based metrics and concept extraction techniques. Unlike traditional methods focused on reducing LLM hallucinations or modifying data structures, this approach evaluates inherent knowledge uncertainty from an LLM perspective. By pre-processing documents with LLMs, the concept-based method significantly enhances precision in tasks demanding high accuracy, such as legal, finance, or formal document responses.
%U https://aclanthology.org/2025.finnlp-1.8/
%P 96-100
Markdown (Informal)
[Concept-Based RAG Models: A High-Accuracy Fact Retrieval Approach](https://aclanthology.org/2025.finnlp-1.8/) (Lin & Jang, FinNLP 2025)
ACL
- Cheng-Yu Lin and Jyh-Shing Jang. 2025. Concept-Based RAG Models: A High-Accuracy Fact Retrieval Approach. In Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal), pages 96–100, Abu Dhabi, UAE. Association for Computational Linguistics.