@inproceedings{sun-etal-2024-lmu,
title = "{LMU}-{B}io{NLP} at {S}em{E}val-2024 Task 2: Large Diverse Ensembles for Robust Clinical {NLI}",
author = "Sun, Zihang and
Yan, Danqi and
Wang, Anyi and
Agustoslu, Tanalp and
Feng, Qi and
Hu, Chengzhi and
Zuo, Longfei and
Zhou, Shijia and
Kleiner, Hermine and
Hong, Pingjun and
Seeha, Suteera and
Loftus, Sebastian and
Barwig, Anna Susanna and
Kraus, Oliver and
Voholonsky, Jona and
Sun, Yang and
Martin, Leopold and
Altinger, Lena and
Wang, Jing and
Weber-Genzel, Leon",
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-1.224/",
doi = "10.18653/v1/2024.semeval-1.224",
pages = "1577--1583",
abstract = "In this paper, we describe our submission for the NLI4CT 2024 shared task on robust Natural Language Inference over clinical trial reports. Our system is an ensemble of nine diverse models which we aggregate via majority voting. The models use a large spectrum of different approaches ranging from a straightforward Convolutional Neural Network over fine-tuned Large Language Models to few-shot-prompted language models using chain-of-thought reasoning.Surprisingly, we find that some individual ensemble members are not only more accurate than the final ensemble model but also more robust."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2024-lmu">
<titleInfo>
<title>LMU-BioNLP at SemEval-2024 Task 2: Large Diverse Ensembles for Robust Clinical NLI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zihang</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anyi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanalp</namePart>
<namePart type="family">Agustoslu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengzhi</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longfei</namePart>
<namePart type="family">Zuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijia</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hermine</namePart>
<namePart type="family">Kleiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pingjun</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suteera</namePart>
<namePart type="family">Seeha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Loftus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="given">Susanna</namePart>
<namePart type="family">Barwig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Kraus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jona</namePart>
<namePart type="family">Voholonsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leopold</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Altinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Weber-Genzel</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>In this paper, we describe our submission for the NLI4CT 2024 shared task on robust Natural Language Inference over clinical trial reports. Our system is an ensemble of nine diverse models which we aggregate via majority voting. The models use a large spectrum of different approaches ranging from a straightforward Convolutional Neural Network over fine-tuned Large Language Models to few-shot-prompted language models using chain-of-thought reasoning.Surprisingly, we find that some individual ensemble members are not only more accurate than the final ensemble model but also more robust.</abstract>
<identifier type="citekey">sun-etal-2024-lmu</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.224</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.224/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1577</start>
<end>1583</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LMU-BioNLP at SemEval-2024 Task 2: Large Diverse Ensembles for Robust Clinical NLI
%A Sun, Zihang
%A Yan, Danqi
%A Wang, Anyi
%A Agustoslu, Tanalp
%A Feng, Qi
%A Hu, Chengzhi
%A Zuo, Longfei
%A Zhou, Shijia
%A Kleiner, Hermine
%A Hong, Pingjun
%A Seeha, Suteera
%A Loftus, Sebastian
%A Barwig, Anna Susanna
%A Kraus, Oliver
%A Voholonsky, Jona
%A Sun, Yang
%A Martin, Leopold
%A Altinger, Lena
%A Wang, Jing
%A Weber-Genzel, Leon
%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 sun-etal-2024-lmu
%X In this paper, we describe our submission for the NLI4CT 2024 shared task on robust Natural Language Inference over clinical trial reports. Our system is an ensemble of nine diverse models which we aggregate via majority voting. The models use a large spectrum of different approaches ranging from a straightforward Convolutional Neural Network over fine-tuned Large Language Models to few-shot-prompted language models using chain-of-thought reasoning.Surprisingly, we find that some individual ensemble members are not only more accurate than the final ensemble model but also more robust.
%R 10.18653/v1/2024.semeval-1.224
%U https://aclanthology.org/2024.semeval-1.224/
%U https://doi.org/10.18653/v1/2024.semeval-1.224
%P 1577-1583
Markdown (Informal)
[LMU-BioNLP at SemEval-2024 Task 2: Large Diverse Ensembles for Robust Clinical NLI](https://aclanthology.org/2024.semeval-1.224/) (Sun et al., SemEval 2024)
ACL
- Zihang Sun, Danqi Yan, Anyi Wang, Tanalp Agustoslu, Qi Feng, Chengzhi Hu, Longfei Zuo, Shijia Zhou, Hermine Kleiner, Pingjun Hong, Suteera Seeha, Sebastian Loftus, Anna Susanna Barwig, Oliver Kraus, Jona Voholonsky, Yang Sun, Leopold Martin, Lena Altinger, Jing Wang, and Leon Weber-Genzel. 2024. LMU-BioNLP at SemEval-2024 Task 2: Large Diverse Ensembles for Robust Clinical NLI. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1577–1583, Mexico City, Mexico. Association for Computational Linguistics.