@inproceedings{bhalerao-etal-2026-beyond,
title = "Beyond Factual {QA}: Mentorship-Oriented Question Answering over Long-Form Multilingual Content",
author = "Bhalerao, Parth and
Guan, Ruiwen and
Dsouza, Diola and
Ignat, Oana",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.953/",
doi = "10.18653/2026.findings-emnlp.953",
pages = "20086--20107",
ISBN = "979-8-89176-462-0",
abstract = "Question answering systems are usually evaluated for factual correctness, but many real world settings such as education and career guidance require mentorship responses that offer reflection, context, and guidance. We introduce MENTORQA, the first multilingual dataset and evaluation framework for mentorship focused question answering from long form videos, with nearly 9,000 QA pairs from 180 hours of content across four languages. We define evaluation dimensions that measure fluency, clarity, alignment, and mentorship value, and use them to compare Single Agent, Dual Agent, RAG, and Multi Agent QA pipelines under controlled conditions. Multi Agent pipelines produce the strongest mentorship responses, with larger gains for complex topics and lower resource languages. We also study LLM based evaluation and find substantial variation in alignment with human judgments. Overall, MENTORQA establishes mentorship focused QA as a distinct research problem and provides a benchmark for studying agentic architectures and evaluation design in educational AI. The dataset and evaluation framework are released at https://aim-scu.github.io/MentorQA/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhalerao-etal-2026-beyond">
<titleInfo>
<title>Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parth</namePart>
<namePart type="family">Bhalerao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiwen</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diola</namePart>
<namePart type="family">Dsouza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Ignat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Question answering systems are usually evaluated for factual correctness, but many real world settings such as education and career guidance require mentorship responses that offer reflection, context, and guidance. We introduce MENTORQA, the first multilingual dataset and evaluation framework for mentorship focused question answering from long form videos, with nearly 9,000 QA pairs from 180 hours of content across four languages. We define evaluation dimensions that measure fluency, clarity, alignment, and mentorship value, and use them to compare Single Agent, Dual Agent, RAG, and Multi Agent QA pipelines under controlled conditions. Multi Agent pipelines produce the strongest mentorship responses, with larger gains for complex topics and lower resource languages. We also study LLM based evaluation and find substantial variation in alignment with human judgments. Overall, MENTORQA establishes mentorship focused QA as a distinct research problem and provides a benchmark for studying agentic architectures and evaluation design in educational AI. The dataset and evaluation framework are released at https://aim-scu.github.io/MentorQA/.</abstract>
<identifier type="citekey">bhalerao-etal-2026-beyond</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.953</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.953/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>20086</start>
<end>20107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content
%A Bhalerao, Parth
%A Guan, Ruiwen
%A Dsouza, Diola
%A Ignat, Oana
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F bhalerao-etal-2026-beyond
%X Question answering systems are usually evaluated for factual correctness, but many real world settings such as education and career guidance require mentorship responses that offer reflection, context, and guidance. We introduce MENTORQA, the first multilingual dataset and evaluation framework for mentorship focused question answering from long form videos, with nearly 9,000 QA pairs from 180 hours of content across four languages. We define evaluation dimensions that measure fluency, clarity, alignment, and mentorship value, and use them to compare Single Agent, Dual Agent, RAG, and Multi Agent QA pipelines under controlled conditions. Multi Agent pipelines produce the strongest mentorship responses, with larger gains for complex topics and lower resource languages. We also study LLM based evaluation and find substantial variation in alignment with human judgments. Overall, MENTORQA establishes mentorship focused QA as a distinct research problem and provides a benchmark for studying agentic architectures and evaluation design in educational AI. The dataset and evaluation framework are released at https://aim-scu.github.io/MentorQA/.
%R 10.18653/2026.findings-emnlp.953
%U https://aclanthology.org/2026.findings-emnlp.953/
%U https://doi.org/10.18653/2026.findings-emnlp.953
%P 20086-20107
Markdown (Informal)
[Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content](https://aclanthology.org/2026.findings-emnlp.953/) (Bhalerao et al., Findings 2026)
ACL