@inproceedings{nguyen-etal-2025-doubt,
title = "When in Doubt, Ask First: A Unified Retrieval Agent-Based System for Ambiguous and Unanswerable Question Answering",
author = "Nguyen, Long and
Vo, Quynh and
Luu, Hung and
Quan, Tho",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.27/",
pages = "452--472",
ISBN = "979-8-89176-303-6",
abstract = "Large Language Models (LLMs) have shown strong capabilities in Question Answering (QA), but their effectiveness in high-stakes, closed-domain settings is often constrained by hallucinations and limited handling of vague or underspecified queries. These challenges are especially pronounced in Vietnamese, a low-resource language with complex syntax and strong contextual dependence, where user questions are often short, informal, and ambiguous. We introduce the Unified Retrieval Agent-Based System (URASys), a QA framework that combines agent-based reasoning with dual retrieval under the Just Enough principle to address standard, ambiguous, and unanswerable questions in a unified manner. URASys performs lightweight query decomposition and integrates document retrieval with a question{--}answer layer via a two-phase indexing pipeline, engaging in interactive clarification when intent is uncertain and explicitly signaling unanswerable cases to avoid hallucination. We evaluate URASys on Vietnamese and English QA benchmarks spanning single-hop, multi-hop, and real-world academic advising tasks, and release new dual-language ambiguous subsets for benchmarking interactive clarification. Results show that URASys outperforms strong retrieval-based baselines in factual accuracy, improves unanswerable handling, and achieves statistically significant gains in human evaluations for clarity and trustworthiness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2025-doubt">
<titleInfo>
<title>When in Doubt, Ask First: A Unified Retrieval Agent-Based System for Ambiguous and Unanswerable Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quynh</namePart>
<namePart type="family">Vo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tho</namePart>
<namePart type="family">Quan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have shown strong capabilities in Question Answering (QA), but their effectiveness in high-stakes, closed-domain settings is often constrained by hallucinations and limited handling of vague or underspecified queries. These challenges are especially pronounced in Vietnamese, a low-resource language with complex syntax and strong contextual dependence, where user questions are often short, informal, and ambiguous. We introduce the Unified Retrieval Agent-Based System (URASys), a QA framework that combines agent-based reasoning with dual retrieval under the Just Enough principle to address standard, ambiguous, and unanswerable questions in a unified manner. URASys performs lightweight query decomposition and integrates document retrieval with a question–answer layer via a two-phase indexing pipeline, engaging in interactive clarification when intent is uncertain and explicitly signaling unanswerable cases to avoid hallucination. We evaluate URASys on Vietnamese and English QA benchmarks spanning single-hop, multi-hop, and real-world academic advising tasks, and release new dual-language ambiguous subsets for benchmarking interactive clarification. Results show that URASys outperforms strong retrieval-based baselines in factual accuracy, improves unanswerable handling, and achieves statistically significant gains in human evaluations for clarity and trustworthiness.</abstract>
<identifier type="citekey">nguyen-etal-2025-doubt</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.27/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>452</start>
<end>472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When in Doubt, Ask First: A Unified Retrieval Agent-Based System for Ambiguous and Unanswerable Question Answering
%A Nguyen, Long
%A Vo, Quynh
%A Luu, Hung
%A Quan, Tho
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F nguyen-etal-2025-doubt
%X Large Language Models (LLMs) have shown strong capabilities in Question Answering (QA), but their effectiveness in high-stakes, closed-domain settings is often constrained by hallucinations and limited handling of vague or underspecified queries. These challenges are especially pronounced in Vietnamese, a low-resource language with complex syntax and strong contextual dependence, where user questions are often short, informal, and ambiguous. We introduce the Unified Retrieval Agent-Based System (URASys), a QA framework that combines agent-based reasoning with dual retrieval under the Just Enough principle to address standard, ambiguous, and unanswerable questions in a unified manner. URASys performs lightweight query decomposition and integrates document retrieval with a question–answer layer via a two-phase indexing pipeline, engaging in interactive clarification when intent is uncertain and explicitly signaling unanswerable cases to avoid hallucination. We evaluate URASys on Vietnamese and English QA benchmarks spanning single-hop, multi-hop, and real-world academic advising tasks, and release new dual-language ambiguous subsets for benchmarking interactive clarification. Results show that URASys outperforms strong retrieval-based baselines in factual accuracy, improves unanswerable handling, and achieves statistically significant gains in human evaluations for clarity and trustworthiness.
%U https://aclanthology.org/2025.findings-ijcnlp.27/
%P 452-472
Markdown (Informal)
[When in Doubt, Ask First: A Unified Retrieval Agent-Based System for Ambiguous and Unanswerable Question Answering](https://aclanthology.org/2025.findings-ijcnlp.27/) (Nguyen et al., Findings 2025)
ACL