@inproceedings{liu-etal-2025-beyond,
title = "Beyond the Answer: Advancing Multi-Hop {QA} with Fine-Grained Graph Reasoning and Evaluation",
author = "Liu, Qichuan and
Zhang, Chentao and
Zheng, Chenfeng and
Hu, Guosheng and
Li, Xiaodong and
Zhang, Zhihong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1142/",
doi = "10.18653/v1/2025.acl-long.1142",
pages = "23433--23456",
ISBN = "979-8-89176-251-0",
abstract = "Recent advancements in large language models (LLMs) have significantly improved the performance of multi-hop question answering (MHQA) systems. Despite the success of MHQA systems, the evaluation of MHQA is not deeply investigated. Existing evaluations mainly focus on comparing the final answers of the reasoning method and given ground-truths. We argue that the reasoning process should also be evaluated because wrong reasoning process can also lead to the correct final answers. Motivated by this, we propose a ``Planner-Executor-Reasoner'' (PER) architecture, which forms the core of the Plan-anchored Data Preprocessing (PER-DP) and the Plan-guided Multi-Hop QA (PER-QA).The former provides the ground-truth of intermediate reasoning steps and final answers, and the latter offers them of a reasoning method. Moreover, we design a fine-grained evaluation metric called Plan-aligned Stepwise Evaluation (PSE), which evaluates the intermediate reasoning steps from two aspects: planning and solving. Extensive experiments on ten types of questions demonstrate competitive reasoning performance, improved explainability of the MHQA system, and uncover issues such as ``fortuitous reasoning continuance'' and ``latent reasoning suspension'' in RAG-based MHQA systems. Besides, we also demonstrate the potential of our approach in data contamination scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-beyond">
<titleInfo>
<title>Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qichuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chentao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenfeng</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guosheng</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Recent advancements in large language models (LLMs) have significantly improved the performance of multi-hop question answering (MHQA) systems. Despite the success of MHQA systems, the evaluation of MHQA is not deeply investigated. Existing evaluations mainly focus on comparing the final answers of the reasoning method and given ground-truths. We argue that the reasoning process should also be evaluated because wrong reasoning process can also lead to the correct final answers. Motivated by this, we propose a “Planner-Executor-Reasoner” (PER) architecture, which forms the core of the Plan-anchored Data Preprocessing (PER-DP) and the Plan-guided Multi-Hop QA (PER-QA).The former provides the ground-truth of intermediate reasoning steps and final answers, and the latter offers them of a reasoning method. Moreover, we design a fine-grained evaluation metric called Plan-aligned Stepwise Evaluation (PSE), which evaluates the intermediate reasoning steps from two aspects: planning and solving. Extensive experiments on ten types of questions demonstrate competitive reasoning performance, improved explainability of the MHQA system, and uncover issues such as “fortuitous reasoning continuance” and “latent reasoning suspension” in RAG-based MHQA systems. Besides, we also demonstrate the potential of our approach in data contamination scenarios.</abstract>
<identifier type="citekey">liu-etal-2025-beyond</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1142</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1142/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>23433</start>
<end>23456</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation
%A Liu, Qichuan
%A Zhang, Chentao
%A Zheng, Chenfeng
%A Hu, Guosheng
%A Li, Xiaodong
%A Zhang, Zhihong
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F liu-etal-2025-beyond
%X Recent advancements in large language models (LLMs) have significantly improved the performance of multi-hop question answering (MHQA) systems. Despite the success of MHQA systems, the evaluation of MHQA is not deeply investigated. Existing evaluations mainly focus on comparing the final answers of the reasoning method and given ground-truths. We argue that the reasoning process should also be evaluated because wrong reasoning process can also lead to the correct final answers. Motivated by this, we propose a “Planner-Executor-Reasoner” (PER) architecture, which forms the core of the Plan-anchored Data Preprocessing (PER-DP) and the Plan-guided Multi-Hop QA (PER-QA).The former provides the ground-truth of intermediate reasoning steps and final answers, and the latter offers them of a reasoning method. Moreover, we design a fine-grained evaluation metric called Plan-aligned Stepwise Evaluation (PSE), which evaluates the intermediate reasoning steps from two aspects: planning and solving. Extensive experiments on ten types of questions demonstrate competitive reasoning performance, improved explainability of the MHQA system, and uncover issues such as “fortuitous reasoning continuance” and “latent reasoning suspension” in RAG-based MHQA systems. Besides, we also demonstrate the potential of our approach in data contamination scenarios.
%R 10.18653/v1/2025.acl-long.1142
%U https://aclanthology.org/2025.acl-long.1142/
%U https://doi.org/10.18653/v1/2025.acl-long.1142
%P 23433-23456
Markdown (Informal)
[Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation](https://aclanthology.org/2025.acl-long.1142/) (Liu et al., ACL 2025)
ACL