@inproceedings{graciotti-etal-2024-latent,
title = "Latent vs Explicit Knowledge Representation: How {C}hat{GPT} Answers Questions about Low-Frequency Entities",
author = "Graciotti, Arianna and
Presutti, Valentina and
Tripodi, Rocco",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.888",
pages = "10172--10185",
abstract = "In this paper, we present an evaluation of two different approaches to the free-form Question Answering (QA) task. The main difference between the two approaches is that one is based on latent representations of knowledge, and the other uses explicit knowledge representation. For the evaluation, we developed DynaKnowledge, a new benchmark composed of questions concerning Wikipedia low-frequency entities. We wanted to ensure, on the one hand, that the questions are answerable and, on the other, that the models can provide information about very specific facts. The evaluation that we conducted highlights that the proposed benchmark is particularly challenging. The best model answers correctly only on 50{\%} of the questions. Analysing the results, we also found that ChatGPT shows low reliance on low-frequency entity questions, manifesting a popularity bias. On the other hand, a simpler model based on explicit knowledge is less affected by this bias. With this paper, we want to provide a living benchmark for open-form QA to test knowledge and latent representation models on a dynamic benchmark.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="graciotti-etal-2024-latent">
<titleInfo>
<title>Latent vs Explicit Knowledge Representation: How ChatGPT Answers Questions about Low-Frequency Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Graciotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentina</namePart>
<namePart type="family">Presutti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rocco</namePart>
<namePart type="family">Tripodi</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</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">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>In this paper, we present an evaluation of two different approaches to the free-form Question Answering (QA) task. The main difference between the two approaches is that one is based on latent representations of knowledge, and the other uses explicit knowledge representation. For the evaluation, we developed DynaKnowledge, a new benchmark composed of questions concerning Wikipedia low-frequency entities. We wanted to ensure, on the one hand, that the questions are answerable and, on the other, that the models can provide information about very specific facts. The evaluation that we conducted highlights that the proposed benchmark is particularly challenging. The best model answers correctly only on 50% of the questions. Analysing the results, we also found that ChatGPT shows low reliance on low-frequency entity questions, manifesting a popularity bias. On the other hand, a simpler model based on explicit knowledge is less affected by this bias. With this paper, we want to provide a living benchmark for open-form QA to test knowledge and latent representation models on a dynamic benchmark.</abstract>
<identifier type="citekey">graciotti-etal-2024-latent</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.888</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10172</start>
<end>10185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Latent vs Explicit Knowledge Representation: How ChatGPT Answers Questions about Low-Frequency Entities
%A Graciotti, Arianna
%A Presutti, Valentina
%A Tripodi, Rocco
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F graciotti-etal-2024-latent
%X In this paper, we present an evaluation of two different approaches to the free-form Question Answering (QA) task. The main difference between the two approaches is that one is based on latent representations of knowledge, and the other uses explicit knowledge representation. For the evaluation, we developed DynaKnowledge, a new benchmark composed of questions concerning Wikipedia low-frequency entities. We wanted to ensure, on the one hand, that the questions are answerable and, on the other, that the models can provide information about very specific facts. The evaluation that we conducted highlights that the proposed benchmark is particularly challenging. The best model answers correctly only on 50% of the questions. Analysing the results, we also found that ChatGPT shows low reliance on low-frequency entity questions, manifesting a popularity bias. On the other hand, a simpler model based on explicit knowledge is less affected by this bias. With this paper, we want to provide a living benchmark for open-form QA to test knowledge and latent representation models on a dynamic benchmark.
%U https://aclanthology.org/2024.lrec-main.888
%P 10172-10185
Markdown (Informal)
[Latent vs Explicit Knowledge Representation: How ChatGPT Answers Questions about Low-Frequency Entities](https://aclanthology.org/2024.lrec-main.888) (Graciotti et al., LREC-COLING 2024)
ACL