@inproceedings{lee-etal-2026-mhts,
title = "{MHTS}: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable {QA} Datasets for {RAG} Evaluation",
author = "Lee, Jeongsoo and
Kwon, Daeyong and
Jin, Kyohoon and
Jeong, JunNyeong and
Sim, Minwoo and
Kim, Minwoo",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.403/",
doi = "10.63317/5mcjipa88zjm",
pages = "5158--5168",
abstract = "Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, ensuring complete and reliable ground truth (GT) responses; diversity, expanding semantic coverage to prevent overfitting; and difficulty, capturing the complexity of reasoning based on hops and the distribution of supporting evidence. However, current benchmarks lack a systematic approach to defining and controlling query difficulty at a fine-grained level. To address this, we propose MHTS (Multi-Hop Tree Structure), a novel dataset synthesis framework that systematically controls multi-hop reasoning complexity by leveraging a multi-hop tree structure to generate logically connected, multi-chunk queries. Our fine-grained difficulty estimation formula exhibits a strong correlation with the overall performance metrics of a RAG system, validating its effectiveness in assessing both retrieval and answer generation capabilities. By ensuring high-quality, diverse, and difficulty-controlled queries, our approach enhances RAG evaluation and benchmarking capabilities. This work contributes to the development of more reliable, efficient, and adaptable AI-driven research assistants, facilitating advancements in document-based reasoning and retrieval tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-mhts">
<titleInfo>
<title>MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeongsoo</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daeyong</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyohoon</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JunNyeong</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minwoo</namePart>
<namePart type="family">Sim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minwoo</namePart>
<namePart type="family">Kim</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 the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, ensuring complete and reliable ground truth (GT) responses; diversity, expanding semantic coverage to prevent overfitting; and difficulty, capturing the complexity of reasoning based on hops and the distribution of supporting evidence. However, current benchmarks lack a systematic approach to defining and controlling query difficulty at a fine-grained level. To address this, we propose MHTS (Multi-Hop Tree Structure), a novel dataset synthesis framework that systematically controls multi-hop reasoning complexity by leveraging a multi-hop tree structure to generate logically connected, multi-chunk queries. Our fine-grained difficulty estimation formula exhibits a strong correlation with the overall performance metrics of a RAG system, validating its effectiveness in assessing both retrieval and answer generation capabilities. By ensuring high-quality, diverse, and difficulty-controlled queries, our approach enhances RAG evaluation and benchmarking capabilities. This work contributes to the development of more reliable, efficient, and adaptable AI-driven research assistants, facilitating advancements in document-based reasoning and retrieval tasks.</abstract>
<identifier type="citekey">lee-etal-2026-mhts</identifier>
<identifier type="doi">10.63317/5mcjipa88zjm</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.403/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5158</start>
<end>5168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation
%A Lee, Jeongsoo
%A Kwon, Daeyong
%A Jin, Kyohoon
%A Jeong, JunNyeong
%A Sim, Minwoo
%A Kim, Minwoo
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F lee-etal-2026-mhts
%X Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, ensuring complete and reliable ground truth (GT) responses; diversity, expanding semantic coverage to prevent overfitting; and difficulty, capturing the complexity of reasoning based on hops and the distribution of supporting evidence. However, current benchmarks lack a systematic approach to defining and controlling query difficulty at a fine-grained level. To address this, we propose MHTS (Multi-Hop Tree Structure), a novel dataset synthesis framework that systematically controls multi-hop reasoning complexity by leveraging a multi-hop tree structure to generate logically connected, multi-chunk queries. Our fine-grained difficulty estimation formula exhibits a strong correlation with the overall performance metrics of a RAG system, validating its effectiveness in assessing both retrieval and answer generation capabilities. By ensuring high-quality, diverse, and difficulty-controlled queries, our approach enhances RAG evaluation and benchmarking capabilities. This work contributes to the development of more reliable, efficient, and adaptable AI-driven research assistants, facilitating advancements in document-based reasoning and retrieval tasks.
%R 10.63317/5mcjipa88zjm
%U https://aclanthology.org/2026.lrec-1.403/
%U https://doi.org/10.63317/5mcjipa88zjm
%P 5158-5168
Markdown (Informal)
[MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation](https://aclanthology.org/2026.lrec-1.403/) (Lee et al., LREC 2026)
ACL