@inproceedings{sengupta-etal-2025-top,
title = "{TOP}-Training: Target-Oriented Pretraining for Medical Extractive Question Answering",
author = "Sengupta, Saptarshi and
Heaton, Connor and
Ghosh, Shreya and
Yin, Wenpeng and
Nakov, Preslav and
Wang, Suhang",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.469/",
pages = "7035--7054",
abstract = "We study extractive question-answering in the medical domain (Medical-EQA). This problem has two main challenges: (i) domain specificity, as most AI models lack necessary domain knowledge, and (ii) extraction-based answering style, which restricts most autoregressive LLMs due to potential hallucinations. To handle those challenges, we propose TOP-Training, a target-oriented pre-training paradigm that stands out among all domain adaptation techniques with two desirable features: (i) TOP-Training moves one step further than popular domain-oriented fine-tuning since it not only moves closer to the target domain, but also familiarizes itself with the target dataset, and (ii) it does not assume the existence of a large set of unlabeled instances from the target domain. Specifically, for a target Medical-EQA dataset, we extract its entities and leverage large language models (LLMs) to generate synthetic texts containing those entities; we then demonstrate that pretraining on this synthetic text data yields better performance on the target Medical-EQA benchmarks. Overall, our contributions are threefold: (i) TOP-Training, a new pretraining technique to effectively adapt LLMs to better solve a target problem, (ii) TOP-Training has a wide application scope because it does not require the target problem to have a large set of unlabeled data, and (iii) our experiments highlight the limitations of autoregressive LLMs, emphasizing TOP-Training as a means to unlock the true potential of bidirectional LLMs."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sengupta-etal-2025-top">
<titleInfo>
<title>TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saptarshi</namePart>
<namePart type="family">Sengupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Connor</namePart>
<namePart type="family">Heaton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shreya</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenpeng</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study extractive question-answering in the medical domain (Medical-EQA). This problem has two main challenges: (i) domain specificity, as most AI models lack necessary domain knowledge, and (ii) extraction-based answering style, which restricts most autoregressive LLMs due to potential hallucinations. To handle those challenges, we propose TOP-Training, a target-oriented pre-training paradigm that stands out among all domain adaptation techniques with two desirable features: (i) TOP-Training moves one step further than popular domain-oriented fine-tuning since it not only moves closer to the target domain, but also familiarizes itself with the target dataset, and (ii) it does not assume the existence of a large set of unlabeled instances from the target domain. Specifically, for a target Medical-EQA dataset, we extract its entities and leverage large language models (LLMs) to generate synthetic texts containing those entities; we then demonstrate that pretraining on this synthetic text data yields better performance on the target Medical-EQA benchmarks. Overall, our contributions are threefold: (i) TOP-Training, a new pretraining technique to effectively adapt LLMs to better solve a target problem, (ii) TOP-Training has a wide application scope because it does not require the target problem to have a large set of unlabeled data, and (iii) our experiments highlight the limitations of autoregressive LLMs, emphasizing TOP-Training as a means to unlock the true potential of bidirectional LLMs.</abstract>
<identifier type="citekey">sengupta-etal-2025-top</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.469/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>7035</start>
<end>7054</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering
%A Sengupta, Saptarshi
%A Heaton, Connor
%A Ghosh, Shreya
%A Yin, Wenpeng
%A Nakov, Preslav
%A Wang, Suhang
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F sengupta-etal-2025-top
%X We study extractive question-answering in the medical domain (Medical-EQA). This problem has two main challenges: (i) domain specificity, as most AI models lack necessary domain knowledge, and (ii) extraction-based answering style, which restricts most autoregressive LLMs due to potential hallucinations. To handle those challenges, we propose TOP-Training, a target-oriented pre-training paradigm that stands out among all domain adaptation techniques with two desirable features: (i) TOP-Training moves one step further than popular domain-oriented fine-tuning since it not only moves closer to the target domain, but also familiarizes itself with the target dataset, and (ii) it does not assume the existence of a large set of unlabeled instances from the target domain. Specifically, for a target Medical-EQA dataset, we extract its entities and leverage large language models (LLMs) to generate synthetic texts containing those entities; we then demonstrate that pretraining on this synthetic text data yields better performance on the target Medical-EQA benchmarks. Overall, our contributions are threefold: (i) TOP-Training, a new pretraining technique to effectively adapt LLMs to better solve a target problem, (ii) TOP-Training has a wide application scope because it does not require the target problem to have a large set of unlabeled data, and (iii) our experiments highlight the limitations of autoregressive LLMs, emphasizing TOP-Training as a means to unlock the true potential of bidirectional LLMs.
%U https://aclanthology.org/2025.coling-main.469/
%P 7035-7054
Markdown (Informal)
[TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering](https://aclanthology.org/2025.coling-main.469/) (Sengupta et al., COLING 2025)
ACL