@inproceedings{pahwa-pahwa-2023-bphigh,
title = "{B}p{H}igh at {S}em{E}val-2023 Task 7: Can Fine-tuned Cross-encoders Outperform {GPT}-3.5 in {NLI} Tasks on Clinical Trial Data?",
author = "Pahwa, Bhavish and
Pahwa, Bhavika",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.266",
doi = "10.18653/v1/2023.semeval-1.266",
pages = "1936--1944",
abstract = "Many nations and organizations have begun collecting and storing clinical trial records for storage and analytical purposes so that medical and clinical practitioners can refer to them on a centralized database over the internet and stay updated with the current clinical information. The amount of clinical trial records have gone through the roof, making it difficult for many medical and clinical practitioners to stay updated with the latest information. To help and support medical and clinical practitioners, there is a need to build intelligent systems that can update them with the latest information in a byte-sized condensed format and, at the same time, leverage their understanding capabilities to help them make decisions. This paper describes our contribution to SemEval 2023 Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data (NLI4CT). Our results show that there is still a need to build domain-specific models as smaller transformer-based models can be finetuned on that data and outperform foundational large language models like GPT-3.5. We also demonstrate how the performance of GPT-3.5 can be increased using few-shot prompting by leveraging the semantic similarity of the text samples and the few-shot train snippets. We will also release our code and our models on open source hosting platforms, GitHub and HuggingFace.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pahwa-pahwa-2023-bphigh">
<titleInfo>
<title>BpHigh at SemEval-2023 Task 7: Can Fine-tuned Cross-encoders Outperform GPT-3.5 in NLI Tasks on Clinical Trial Data?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhavish</namePart>
<namePart type="family">Pahwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhavika</namePart>
<namePart type="family">Pahwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</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">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">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many nations and organizations have begun collecting and storing clinical trial records for storage and analytical purposes so that medical and clinical practitioners can refer to them on a centralized database over the internet and stay updated with the current clinical information. The amount of clinical trial records have gone through the roof, making it difficult for many medical and clinical practitioners to stay updated with the latest information. To help and support medical and clinical practitioners, there is a need to build intelligent systems that can update them with the latest information in a byte-sized condensed format and, at the same time, leverage their understanding capabilities to help them make decisions. This paper describes our contribution to SemEval 2023 Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data (NLI4CT). Our results show that there is still a need to build domain-specific models as smaller transformer-based models can be finetuned on that data and outperform foundational large language models like GPT-3.5. We also demonstrate how the performance of GPT-3.5 can be increased using few-shot prompting by leveraging the semantic similarity of the text samples and the few-shot train snippets. We will also release our code and our models on open source hosting platforms, GitHub and HuggingFace.</abstract>
<identifier type="citekey">pahwa-pahwa-2023-bphigh</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.266</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.266</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1936</start>
<end>1944</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BpHigh at SemEval-2023 Task 7: Can Fine-tuned Cross-encoders Outperform GPT-3.5 in NLI Tasks on Clinical Trial Data?
%A Pahwa, Bhavish
%A Pahwa, Bhavika
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F pahwa-pahwa-2023-bphigh
%X Many nations and organizations have begun collecting and storing clinical trial records for storage and analytical purposes so that medical and clinical practitioners can refer to them on a centralized database over the internet and stay updated with the current clinical information. The amount of clinical trial records have gone through the roof, making it difficult for many medical and clinical practitioners to stay updated with the latest information. To help and support medical and clinical practitioners, there is a need to build intelligent systems that can update them with the latest information in a byte-sized condensed format and, at the same time, leverage their understanding capabilities to help them make decisions. This paper describes our contribution to SemEval 2023 Task 7: Multi-evidence Natural Language Inference for Clinical Trial Data (NLI4CT). Our results show that there is still a need to build domain-specific models as smaller transformer-based models can be finetuned on that data and outperform foundational large language models like GPT-3.5. We also demonstrate how the performance of GPT-3.5 can be increased using few-shot prompting by leveraging the semantic similarity of the text samples and the few-shot train snippets. We will also release our code and our models on open source hosting platforms, GitHub and HuggingFace.
%R 10.18653/v1/2023.semeval-1.266
%U https://aclanthology.org/2023.semeval-1.266
%U https://doi.org/10.18653/v1/2023.semeval-1.266
%P 1936-1944
Markdown (Informal)
[BpHigh at SemEval-2023 Task 7: Can Fine-tuned Cross-encoders Outperform GPT-3.5 in NLI Tasks on Clinical Trial Data?](https://aclanthology.org/2023.semeval-1.266) (Pahwa & Pahwa, SemEval 2023)
ACL