@inproceedings{padro-sauri-2024-fine,
title = "Fine-Tuning Open Access {LLM}s for High-Precision {NLU} in Goal-Driven Dialog Systems",
author = "Padr{\'o}, Llu{\'\i}s and
Saur{\'\i}, Roser",
editor = "Gaspari, Federico and
Moorkens, Joss and
Aldabe, Itziar and
Farwell, Aritz and
Altuna, Begona and
Piperidis, Stelios and
Rehm, Georg and
Rigau, German",
booktitle = "Proceedings of the Second International Workshop Towards Digital Language Equality (TDLE): Focusing on Sustainability @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.tdle-1.3",
pages = "33--42",
abstract = "This paper presents a set of experiments on fine-tuning LLMs to produce high-precision semantic representations for the NLU component of a dialog system front-end. The aim of this research is threefold: First, we want to explore the capabilities of LLMs on real, industry-based use cases that involve complex data and strict requirements on results. Since the LLM output should usable by the application back-end, the produced semantic representation must satisfy strict format and consistency requirements. Second, we want to evaluate the cost-benefit of open-source LLMs, that is, the feasibility of running this kind of models in machines affordable to small-medium enterprises (SMEs), in order to assess how far this organizations can go without depending on the large players controlling the market, and with a moderate use of computation resources. Finally, we also want to assess the language scalability of the LLMs in this kind of applications; specifically, whether a multilingual model is able to cast patterns learnt from one language to other ones {--}with special attention to underresourced languages{--}, thus reducing required training data and computation costs. This work was carried out within an R{\&}D context of assisting a real company in defining its NLU model strategy, and thus the results have a practical, industry-level focus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="padro-sauri-2024-fine">
<titleInfo>
<title>Fine-Tuning Open Access LLMs for High-Precision NLU in Goal-Driven Dialog Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Padró</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roser</namePart>
<namePart type="family">Saurí</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second International Workshop Towards Digital Language Equality (TDLE): Focusing on Sustainability @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Gaspari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joss</namePart>
<namePart type="family">Moorkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itziar</namePart>
<namePart type="family">Aldabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aritz</namePart>
<namePart type="family">Farwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Begona</namePart>
<namePart type="family">Altuna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a set of experiments on fine-tuning LLMs to produce high-precision semantic representations for the NLU component of a dialog system front-end. The aim of this research is threefold: First, we want to explore the capabilities of LLMs on real, industry-based use cases that involve complex data and strict requirements on results. Since the LLM output should usable by the application back-end, the produced semantic representation must satisfy strict format and consistency requirements. Second, we want to evaluate the cost-benefit of open-source LLMs, that is, the feasibility of running this kind of models in machines affordable to small-medium enterprises (SMEs), in order to assess how far this organizations can go without depending on the large players controlling the market, and with a moderate use of computation resources. Finally, we also want to assess the language scalability of the LLMs in this kind of applications; specifically, whether a multilingual model is able to cast patterns learnt from one language to other ones –with special attention to underresourced languages–, thus reducing required training data and computation costs. This work was carried out within an R&D context of assisting a real company in defining its NLU model strategy, and thus the results have a practical, industry-level focus.</abstract>
<identifier type="citekey">padro-sauri-2024-fine</identifier>
<location>
<url>https://aclanthology.org/2024.tdle-1.3</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>33</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Tuning Open Access LLMs for High-Precision NLU in Goal-Driven Dialog Systems
%A Padró, Lluís
%A Saurí, Roser
%Y Gaspari, Federico
%Y Moorkens, Joss
%Y Aldabe, Itziar
%Y Farwell, Aritz
%Y Altuna, Begona
%Y Piperidis, Stelios
%Y Rehm, Georg
%Y Rigau, German
%S Proceedings of the Second International Workshop Towards Digital Language Equality (TDLE): Focusing on Sustainability @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F padro-sauri-2024-fine
%X This paper presents a set of experiments on fine-tuning LLMs to produce high-precision semantic representations for the NLU component of a dialog system front-end. The aim of this research is threefold: First, we want to explore the capabilities of LLMs on real, industry-based use cases that involve complex data and strict requirements on results. Since the LLM output should usable by the application back-end, the produced semantic representation must satisfy strict format and consistency requirements. Second, we want to evaluate the cost-benefit of open-source LLMs, that is, the feasibility of running this kind of models in machines affordable to small-medium enterprises (SMEs), in order to assess how far this organizations can go without depending on the large players controlling the market, and with a moderate use of computation resources. Finally, we also want to assess the language scalability of the LLMs in this kind of applications; specifically, whether a multilingual model is able to cast patterns learnt from one language to other ones –with special attention to underresourced languages–, thus reducing required training data and computation costs. This work was carried out within an R&D context of assisting a real company in defining its NLU model strategy, and thus the results have a practical, industry-level focus.
%U https://aclanthology.org/2024.tdle-1.3
%P 33-42
Markdown (Informal)
[Fine-Tuning Open Access LLMs for High-Precision NLU in Goal-Driven Dialog Systems](https://aclanthology.org/2024.tdle-1.3) (Padró & Saurí, TDLE-WS 2024)
ACL