@inproceedings{rajan-sequiera-2024-legallens,
title = "{L}egal{L}ens 2024 Shared Task: Masala-chai Submission",
author = "Rajan, Khalid and
Sequiera, Royal",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goan{\textcommabelow{t}}{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preo{\textcommabelow{t}}iuc-Pietro, Daniel and
Spanakis, Gerasimos",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2024",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nllp-1.30",
pages = "346--354",
abstract = "In this paper, we present the masala-chai team{'}s participation in the LegalLens 2024 shared task and detail our approach to predicting legal entities and performing natural language inference (NLI) in the legal domain. We experimented with various transformer-based models, including BERT, RoBERTa, Llama 3.1, and GPT-4o. Our results show that state-of-the-art models like GPT-4o underperformed in NER and NLI tasks, even when using advanced techniques such as bootstrapping and prompt optimization. The best performance in NER (accuracy: 0.806, F1 macro: 0.701) was achieved with a fine-tuned RoBERTa model, while the highest NLI results (accuracy: 0.825, F1 macro: 0.833) came from a fine-tuned Llama 3.1 8B model. Notably, RoBERTa, despite having significantly fewer parameters than Llama 3.1 8B, delivered comparable results. We discuss key findings and insights from our experiments and provide our results and code for reproducibility and further analysis at https://github.com/rosequ/masala-chai",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajan-sequiera-2024-legallens">
<titleInfo>
<title>LegalLens 2024 Shared Task: Masala-chai Submission</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Rajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Royal</namePart>
<namePart type="family">Sequiera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goan\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present the masala-chai team’s participation in the LegalLens 2024 shared task and detail our approach to predicting legal entities and performing natural language inference (NLI) in the legal domain. We experimented with various transformer-based models, including BERT, RoBERTa, Llama 3.1, and GPT-4o. Our results show that state-of-the-art models like GPT-4o underperformed in NER and NLI tasks, even when using advanced techniques such as bootstrapping and prompt optimization. The best performance in NER (accuracy: 0.806, F1 macro: 0.701) was achieved with a fine-tuned RoBERTa model, while the highest NLI results (accuracy: 0.825, F1 macro: 0.833) came from a fine-tuned Llama 3.1 8B model. Notably, RoBERTa, despite having significantly fewer parameters than Llama 3.1 8B, delivered comparable results. We discuss key findings and insights from our experiments and provide our results and code for reproducibility and further analysis at https://github.com/rosequ/masala-chai</abstract>
<identifier type="citekey">rajan-sequiera-2024-legallens</identifier>
<location>
<url>https://aclanthology.org/2024.nllp-1.30</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>346</start>
<end>354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LegalLens 2024 Shared Task: Masala-chai Submission
%A Rajan, Khalid
%A Sequiera, Royal
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goan\textcommabelowtă, Cătălina
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%S Proceedings of the Natural Legal Language Processing Workshop 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F rajan-sequiera-2024-legallens
%X In this paper, we present the masala-chai team’s participation in the LegalLens 2024 shared task and detail our approach to predicting legal entities and performing natural language inference (NLI) in the legal domain. We experimented with various transformer-based models, including BERT, RoBERTa, Llama 3.1, and GPT-4o. Our results show that state-of-the-art models like GPT-4o underperformed in NER and NLI tasks, even when using advanced techniques such as bootstrapping and prompt optimization. The best performance in NER (accuracy: 0.806, F1 macro: 0.701) was achieved with a fine-tuned RoBERTa model, while the highest NLI results (accuracy: 0.825, F1 macro: 0.833) came from a fine-tuned Llama 3.1 8B model. Notably, RoBERTa, despite having significantly fewer parameters than Llama 3.1 8B, delivered comparable results. We discuss key findings and insights from our experiments and provide our results and code for reproducibility and further analysis at https://github.com/rosequ/masala-chai
%U https://aclanthology.org/2024.nllp-1.30
%P 346-354
Markdown (Informal)
[LegalLens 2024 Shared Task: Masala-chai Submission](https://aclanthology.org/2024.nllp-1.30) (Rajan & Sequiera, NLLP 2024)
ACL