@inproceedings{malandri-etal-2025-fin,
title = "{RE}-{FIN}: Retrieval-based Enrichment for Financial data",
author = "Malandri, Lorenzo and
Mercorio, Fabio and
Mezzanzanica, Mario and
Pallucchini, Filippo",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven and
Darwish, Kareem and
Agarwal, Apoorv",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-industry.62/",
pages = "751--759",
abstract = "Enriching sentences with knowledge from qualitative sources benefits various NLP tasks and enhances the use of labeled data in model training. This is crucial for Financial Sentiment Analysis (FSA), where texts are often brief and contain implied information. We introduce RE-FIN (Retrieval-based Enrichment for FINancial data), an automated system designed to retrieve information from a knowledge base to enrich financial sentences, making them more knowledge-dense and explicit. RE-FIN generates propositions from the knowledge base and employs Retrieval-Augmented Generation (RAG) to augment the original text with relevant information. A large language model (LLM) rewrites the original sentence, incorporating this data. Since the LLM does not create new content, the risk of hallucinations is significantly reduced. The LLM generates multiple new sentences using different relevant information from the knowledge base; we developed an algorithm to select one that best preserves the meaning of the original sentence while avoiding excessive syntactic similarity. Results show that enhanced sentences present lower perplexity than the original ones and improve performances on FSA."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malandri-etal-2025-fin">
<titleInfo>
<title>RE-FIN: Retrieval-based Enrichment for Financial data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Malandri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Mercorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Mezzanzanica</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filippo</namePart>
<namePart type="family">Pallucchini</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 31st International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorv</namePart>
<namePart type="family">Agarwal</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>Enriching sentences with knowledge from qualitative sources benefits various NLP tasks and enhances the use of labeled data in model training. This is crucial for Financial Sentiment Analysis (FSA), where texts are often brief and contain implied information. We introduce RE-FIN (Retrieval-based Enrichment for FINancial data), an automated system designed to retrieve information from a knowledge base to enrich financial sentences, making them more knowledge-dense and explicit. RE-FIN generates propositions from the knowledge base and employs Retrieval-Augmented Generation (RAG) to augment the original text with relevant information. A large language model (LLM) rewrites the original sentence, incorporating this data. Since the LLM does not create new content, the risk of hallucinations is significantly reduced. The LLM generates multiple new sentences using different relevant information from the knowledge base; we developed an algorithm to select one that best preserves the meaning of the original sentence while avoiding excessive syntactic similarity. Results show that enhanced sentences present lower perplexity than the original ones and improve performances on FSA.</abstract>
<identifier type="citekey">malandri-etal-2025-fin</identifier>
<location>
<url>https://aclanthology.org/2025.coling-industry.62/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>751</start>
<end>759</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RE-FIN: Retrieval-based Enrichment for Financial data
%A Malandri, Lorenzo
%A Mercorio, Fabio
%A Mezzanzanica, Mario
%A Pallucchini, Filippo
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%Y Darwish, Kareem
%Y Agarwal, Apoorv
%S Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F malandri-etal-2025-fin
%X Enriching sentences with knowledge from qualitative sources benefits various NLP tasks and enhances the use of labeled data in model training. This is crucial for Financial Sentiment Analysis (FSA), where texts are often brief and contain implied information. We introduce RE-FIN (Retrieval-based Enrichment for FINancial data), an automated system designed to retrieve information from a knowledge base to enrich financial sentences, making them more knowledge-dense and explicit. RE-FIN generates propositions from the knowledge base and employs Retrieval-Augmented Generation (RAG) to augment the original text with relevant information. A large language model (LLM) rewrites the original sentence, incorporating this data. Since the LLM does not create new content, the risk of hallucinations is significantly reduced. The LLM generates multiple new sentences using different relevant information from the knowledge base; we developed an algorithm to select one that best preserves the meaning of the original sentence while avoiding excessive syntactic similarity. Results show that enhanced sentences present lower perplexity than the original ones and improve performances on FSA.
%U https://aclanthology.org/2025.coling-industry.62/
%P 751-759
Markdown (Informal)
[RE-FIN: Retrieval-based Enrichment for Financial data](https://aclanthology.org/2025.coling-industry.62/) (Malandri et al., COLING 2025)
ACL
- Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, and Filippo Pallucchini. 2025. RE-FIN: Retrieval-based Enrichment for Financial data. In Proceedings of the 31st International Conference on Computational Linguistics: Industry Track, pages 751–759, Abu Dhabi, UAE. Association for Computational Linguistics.