@inproceedings{siragusa-pirrone-2024-unipa,
title = "Unipa-{GPT}: A Framework to Assess Open-source Alternatives to Chat-{GPT} for {I}talian Chat-bots",
author = "Siragusa, Irene and
Pirrone, Roberto",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.100/",
pages = "929--939",
ISBN = "979-12-210-7060-6",
abstract = "This paper illustrates the implementation of Open Unipa-GPT, an open source version of the Unipa-GPT chatbot that leverages on open-source Large Language Models for embeddings and text generation. The system relies on a Retrieval Augmented Generation approach, thus mitigating hallucination errors in the generation phase. A detailed comparison between different models is reported to illustrate their performance as regards embedding generation, retrieval, and text generation. In the last case, models were tested in simple inference setup after a fine-tuning procedure. Experiments demonstrate that an open-source LLMs can be efficiently used for embedding generation, but noon of the models does reach the performances obtained by closed models, such as gpt-3.5-turbo in generating answers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siragusa-pirrone-2024-unipa">
<titleInfo>
<title>Unipa-GPT: A Framework to Assess Open-source Alternatives to Chat-GPT for Italian Chat-bots</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irene</namePart>
<namePart type="family">Siragusa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Pirrone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>This paper illustrates the implementation of Open Unipa-GPT, an open source version of the Unipa-GPT chatbot that leverages on open-source Large Language Models for embeddings and text generation. The system relies on a Retrieval Augmented Generation approach, thus mitigating hallucination errors in the generation phase. A detailed comparison between different models is reported to illustrate their performance as regards embedding generation, retrieval, and text generation. In the last case, models were tested in simple inference setup after a fine-tuning procedure. Experiments demonstrate that an open-source LLMs can be efficiently used for embedding generation, but noon of the models does reach the performances obtained by closed models, such as gpt-3.5-turbo in generating answers.</abstract>
<identifier type="citekey">siragusa-pirrone-2024-unipa</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.100/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>929</start>
<end>939</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unipa-GPT: A Framework to Assess Open-source Alternatives to Chat-GPT for Italian Chat-bots
%A Siragusa, Irene
%A Pirrone, Roberto
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F siragusa-pirrone-2024-unipa
%X This paper illustrates the implementation of Open Unipa-GPT, an open source version of the Unipa-GPT chatbot that leverages on open-source Large Language Models for embeddings and text generation. The system relies on a Retrieval Augmented Generation approach, thus mitigating hallucination errors in the generation phase. A detailed comparison between different models is reported to illustrate their performance as regards embedding generation, retrieval, and text generation. In the last case, models were tested in simple inference setup after a fine-tuning procedure. Experiments demonstrate that an open-source LLMs can be efficiently used for embedding generation, but noon of the models does reach the performances obtained by closed models, such as gpt-3.5-turbo in generating answers.
%U https://aclanthology.org/2024.clicit-1.100/
%P 929-939
Markdown (Informal)
[Unipa-GPT: A Framework to Assess Open-source Alternatives to Chat-GPT for Italian Chat-bots](https://aclanthology.org/2024.clicit-1.100/) (Siragusa & Pirrone, CLiC-it 2024)
ACL