@inproceedings{behura-etal-2026-enhancing,
title = "Enhancing Factuality and Transparency in Generative Models for Biomedical Question Answering",
author = "Behura, Ankita and
Liang, Siting and
Sonntag, Daniel",
editor = "Rehm, Georg and
Dietze, Stefan and
Dessi, Danilo and
Maynard, Diana and
Schimmler, Sonja",
booktitle = "Proceedings of Natural Scientific Language Processing ({NSLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nslp-1.13/",
doi = "10.63317/3uxg7miycis4",
pages = "127--139",
abstract = "Biomedical Question Answering (BQA) systems are vital for providing clinicians and researchers with efficient access to large amount of biomedical scientific studies. Existing automated BQA models, however, often rely on complex hybrid architectures to handle diverse question and answer formats, leading to inefficiency and high complexity. While domain-specific generative language models like BioBART offer a unified and simplified alternative capable of producing fluent human-like responses, they are prone to hallucination and lack interpretability, undermining their trustworthiness in critical healthcare domains. To address these limitations, this work introduces an enhanced model that augments BioBART with a pointer network for accurate token copying and a novel Keyphrase Filter (KPF) to guide attention toward critical information during generation. Experimental results on the BioASQ challenge demonstrate that the proposed Pointer-KPF model significantly outperforms the baseline BioBART, particularly on metrics for ideal answers. Furthermore, our evaluation shows that the model enhances transparency: pointer-guided attention heatmaps reveal improved input-output alignment, while keyphrase scores act as saliency maps to identify the most influential input segments. This approach not only reduces hallucination by strengthening textual grounding but also provides crucial insights into the model{'}s reasoning, thereby increasing confidence and trust in its outputs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="behura-etal-2026-enhancing">
<titleInfo>
<title>Enhancing Factuality and Transparency in Generative Models for Biomedical Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankita</namePart>
<namePart type="family">Behura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siting</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Sonntag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Dietze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Dessi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Maynard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Biomedical Question Answering (BQA) systems are vital for providing clinicians and researchers with efficient access to large amount of biomedical scientific studies. Existing automated BQA models, however, often rely on complex hybrid architectures to handle diverse question and answer formats, leading to inefficiency and high complexity. While domain-specific generative language models like BioBART offer a unified and simplified alternative capable of producing fluent human-like responses, they are prone to hallucination and lack interpretability, undermining their trustworthiness in critical healthcare domains. To address these limitations, this work introduces an enhanced model that augments BioBART with a pointer network for accurate token copying and a novel Keyphrase Filter (KPF) to guide attention toward critical information during generation. Experimental results on the BioASQ challenge demonstrate that the proposed Pointer-KPF model significantly outperforms the baseline BioBART, particularly on metrics for ideal answers. Furthermore, our evaluation shows that the model enhances transparency: pointer-guided attention heatmaps reveal improved input-output alignment, while keyphrase scores act as saliency maps to identify the most influential input segments. This approach not only reduces hallucination by strengthening textual grounding but also provides crucial insights into the model’s reasoning, thereby increasing confidence and trust in its outputs.</abstract>
<identifier type="citekey">behura-etal-2026-enhancing</identifier>
<identifier type="doi">10.63317/3uxg7miycis4</identifier>
<location>
<url>https://aclanthology.org/2026.nslp-1.13/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>127</start>
<end>139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Factuality and Transparency in Generative Models for Biomedical Question Answering
%A Behura, Ankita
%A Liang, Siting
%A Sonntag, Daniel
%Y Rehm, Georg
%Y Dietze, Stefan
%Y Dessi, Danilo
%Y Maynard, Diana
%Y Schimmler, Sonja
%S Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F behura-etal-2026-enhancing
%X Biomedical Question Answering (BQA) systems are vital for providing clinicians and researchers with efficient access to large amount of biomedical scientific studies. Existing automated BQA models, however, often rely on complex hybrid architectures to handle diverse question and answer formats, leading to inefficiency and high complexity. While domain-specific generative language models like BioBART offer a unified and simplified alternative capable of producing fluent human-like responses, they are prone to hallucination and lack interpretability, undermining their trustworthiness in critical healthcare domains. To address these limitations, this work introduces an enhanced model that augments BioBART with a pointer network for accurate token copying and a novel Keyphrase Filter (KPF) to guide attention toward critical information during generation. Experimental results on the BioASQ challenge demonstrate that the proposed Pointer-KPF model significantly outperforms the baseline BioBART, particularly on metrics for ideal answers. Furthermore, our evaluation shows that the model enhances transparency: pointer-guided attention heatmaps reveal improved input-output alignment, while keyphrase scores act as saliency maps to identify the most influential input segments. This approach not only reduces hallucination by strengthening textual grounding but also provides crucial insights into the model’s reasoning, thereby increasing confidence and trust in its outputs.
%R 10.63317/3uxg7miycis4
%U https://aclanthology.org/2026.nslp-1.13/
%U https://doi.org/10.63317/3uxg7miycis4
%P 127-139
Markdown (Informal)
[Enhancing Factuality and Transparency in Generative Models for Biomedical Question Answering](https://aclanthology.org/2026.nslp-1.13/) (Behura et al., NSLP 2026)
ACL