@inproceedings{hadifar-etal-2025-regraph,
title = "{R}e{G}raph: Learning to Reformulate Graph Encodings with Large Language Models",
author = "Hadifar, Amir and
Ochs, Christopher and
Van Ewijk, Arjan",
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.ijcnlp-short.32/",
pages = "386--394",
ISBN = "979-8-89176-299-2",
abstract = "Large language models can rephrase and restructure natural language effectively, but their potential for reformulating graph encodings remains underexplored despite the significant impact of encoding choices on performance.In this work, we introduce ReGraph, a reinforcement learning-based approach that guides language models to reformulate graph encodings for improved task alignment.We demonstrate that reformulating graph encodings enhances reasoning and yields consistent performance gains on graph question answering tasks.Our results show that language models often prefer specific graph encodings, even if they are suboptimal for the task at hand."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hadifar-etal-2025-regraph">
<titleInfo>
<title>ReGraph: Learning to Reformulate Graph Encodings with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Hadifar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ochs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjan</namePart>
<namePart type="family">Van Ewijk</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">979-8-89176-299-2</identifier>
</relatedItem>
<abstract>Large language models can rephrase and restructure natural language effectively, but their potential for reformulating graph encodings remains underexplored despite the significant impact of encoding choices on performance.In this work, we introduce ReGraph, a reinforcement learning-based approach that guides language models to reformulate graph encodings for improved task alignment.We demonstrate that reformulating graph encodings enhances reasoning and yields consistent performance gains on graph question answering tasks.Our results show that language models often prefer specific graph encodings, even if they are suboptimal for the task at hand.</abstract>
<identifier type="citekey">hadifar-etal-2025-regraph</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-short.32/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>386</start>
<end>394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReGraph: Learning to Reformulate Graph Encodings with Large Language Models
%A Hadifar, Amir
%A Ochs, Christopher
%A Van Ewijk, Arjan
%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
%@ 979-8-89176-299-2
%F hadifar-etal-2025-regraph
%X Large language models can rephrase and restructure natural language effectively, but their potential for reformulating graph encodings remains underexplored despite the significant impact of encoding choices on performance.In this work, we introduce ReGraph, a reinforcement learning-based approach that guides language models to reformulate graph encodings for improved task alignment.We demonstrate that reformulating graph encodings enhances reasoning and yields consistent performance gains on graph question answering tasks.Our results show that language models often prefer specific graph encodings, even if they are suboptimal for the task at hand.
%U https://aclanthology.org/2025.ijcnlp-short.32/
%P 386-394
Markdown (Informal)
[ReGraph: Learning to Reformulate Graph Encodings with Large Language Models](https://aclanthology.org/2025.ijcnlp-short.32/) (Hadifar et al., IJCNLP-AACL 2025)
ACL
- Amir Hadifar, Christopher Ochs, and Arjan Van Ewijk. 2025. ReGraph: Learning to Reformulate Graph Encodings with Large Language Models. In 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, pages 386–394, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.