@inproceedings{rajpoot-chukamphaeng-2024-team,
title = "Team {NP}{\_}{PROBLEM} at {S}em{E}val-2024 Task 7: Numerical Reasoning in Headline Generation with Preference Optimization",
author = "Rajpoot, Pawan and
Chukamphaeng, Nut",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.103/",
doi = "10.18653/v1/2024.semeval-1.103",
pages = "716--720",
abstract = "While large language models (LLMs) exhibit impressive linguistic abilities, their numerical reasoning skills within real-world contexts re- main under-explored. This paper describes our participation in a headline-generation challenge by Numeval at Semeval 2024, which focused on numerical reasoning. Our system achieved an overall top numerical accuracy of 73.49{\%} on the task. We explore the system`s design choices contributing to this result and analyze common error patterns. Our findings highlight the potential and ongoing challenges of integrat- ing numerical reasoning within large language model-based headline generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajpoot-chukamphaeng-2024-team">
<titleInfo>
<title>Team NP_PROBLEM at SemEval-2024 Task 7: Numerical Reasoning in Headline Generation with Preference Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Rajpoot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nut</namePart>
<namePart type="family">Chukamphaeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While large language models (LLMs) exhibit impressive linguistic abilities, their numerical reasoning skills within real-world contexts re- main under-explored. This paper describes our participation in a headline-generation challenge by Numeval at Semeval 2024, which focused on numerical reasoning. Our system achieved an overall top numerical accuracy of 73.49% on the task. We explore the system‘s design choices contributing to this result and analyze common error patterns. Our findings highlight the potential and ongoing challenges of integrat- ing numerical reasoning within large language model-based headline generation.</abstract>
<identifier type="citekey">rajpoot-chukamphaeng-2024-team</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.103</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.103/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>716</start>
<end>720</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team NP_PROBLEM at SemEval-2024 Task 7: Numerical Reasoning in Headline Generation with Preference Optimization
%A Rajpoot, Pawan
%A Chukamphaeng, Nut
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F rajpoot-chukamphaeng-2024-team
%X While large language models (LLMs) exhibit impressive linguistic abilities, their numerical reasoning skills within real-world contexts re- main under-explored. This paper describes our participation in a headline-generation challenge by Numeval at Semeval 2024, which focused on numerical reasoning. Our system achieved an overall top numerical accuracy of 73.49% on the task. We explore the system‘s design choices contributing to this result and analyze common error patterns. Our findings highlight the potential and ongoing challenges of integrat- ing numerical reasoning within large language model-based headline generation.
%R 10.18653/v1/2024.semeval-1.103
%U https://aclanthology.org/2024.semeval-1.103/
%U https://doi.org/10.18653/v1/2024.semeval-1.103
%P 716-720
Markdown (Informal)
[Team NP_PROBLEM at SemEval-2024 Task 7: Numerical Reasoning in Headline Generation with Preference Optimization](https://aclanthology.org/2024.semeval-1.103/) (Rajpoot & Chukamphaeng, SemEval 2024)
ACL