@inproceedings{xiao-etal-2024-analyzing,
title = "Analyzing Large Language Models{'} Capability in Location Prediction",
author = "Xiao, Zhaomin and
Huang, Yan and
Blanco, Eduardo",
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.85",
pages = "951--958",
abstract = "In this paper, we investigate and evaluate large language models{'} capability in location prediction. We present experimental results with four models{---}FLAN-T5, FLAN-UL2, FLAN-Alpaca, and ChatGPT{---}in various instruction finetuning and exemplar settings. We analyze whether taking into account the context{---}tweets published before and after the tweet mentioning a location{---}is beneficial. Additionally, we conduct an ablation study to explore whether instruction modification is beneficial. Lastly, our qualitative analysis sheds light on the errors made by the best-performing model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2024-analyzing">
<titleInfo>
<title>Analyzing Large Language Models’ Capability in Location Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaomin</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Blanco</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 investigate and evaluate large language models’ capability in location prediction. We present experimental results with four models—FLAN-T5, FLAN-UL2, FLAN-Alpaca, and ChatGPT—in various instruction finetuning and exemplar settings. We analyze whether taking into account the context—tweets published before and after the tweet mentioning a location—is beneficial. Additionally, we conduct an ablation study to explore whether instruction modification is beneficial. Lastly, our qualitative analysis sheds light on the errors made by the best-performing model.</abstract>
<identifier type="citekey">xiao-etal-2024-analyzing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.85</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>951</start>
<end>958</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing Large Language Models’ Capability in Location Prediction
%A Xiao, Zhaomin
%A Huang, Yan
%A Blanco, Eduardo
%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 xiao-etal-2024-analyzing
%X In this paper, we investigate and evaluate large language models’ capability in location prediction. We present experimental results with four models—FLAN-T5, FLAN-UL2, FLAN-Alpaca, and ChatGPT—in various instruction finetuning and exemplar settings. We analyze whether taking into account the context—tweets published before and after the tweet mentioning a location—is beneficial. Additionally, we conduct an ablation study to explore whether instruction modification is beneficial. Lastly, our qualitative analysis sheds light on the errors made by the best-performing model.
%U https://aclanthology.org/2024.lrec-main.85
%P 951-958
Markdown (Informal)
[Analyzing Large Language Models’ Capability in Location Prediction](https://aclanthology.org/2024.lrec-main.85) (Xiao et al., LREC-COLING 2024)
ACL