@inproceedings{zhao-etal-2026-cofgraph,
title = "{C}o{FG}raph: Interleaving Reciprocal Calibration with Confidence Feedback for {LLM}-Augmented Graph Learning",
author = "Zhao, Feng and
Chen, Tiewen and
Liu, Xianggan and
Zhao, Ruilin and
Song, Yifan",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1428/",
pages = "32624--32635",
ISBN = "979-8-89176-459-0",
abstract = "Graph learning requires jointly leveraging node semantics and graph structure, but traditional methods often suffer from label scarcity and shallow semantic utilization. Although LLMs provide strong semantic reasoning for graph learning, existing LLM-augmented pipelines face two major challenges: their semantics-only outputs can inject semantic noise that conflicts with graph topology, and they often incur substantial overhead due to LLM fine-tuning or repeated LLM calls at training/inference. We propose CoFGraph, a confidence-feedback framework that interleaves reciprocal calibration between semantic and structural views to enable reliable and efficient LLM-augmented graph learning. To avoid expensive LLM adaptation, we keep the LLM frozen and train a lightweight Interpreter as a semantic proxy, eliminating the need for LLM fine-tuning and continual test-time prompting. To further mitigate semantic noise and the lack of structural feedback, we introduce confidence-based dual-view learning with node-wise confidence estimation and dynamic role switching, allowing the more reliable view to correct the other. Experiments on four public benchmarks validate the effectiveness of CoFGraph and demonstrate strong stability across varying training label ratios, with particularly consistent gains in low-resource regimes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2026-cofgraph">
<titleInfo>
<title>CoFGraph: Interleaving Reciprocal Calibration with Confidence Feedback for LLM-Augmented Graph Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiewen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianggan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruilin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Song</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Graph learning requires jointly leveraging node semantics and graph structure, but traditional methods often suffer from label scarcity and shallow semantic utilization. Although LLMs provide strong semantic reasoning for graph learning, existing LLM-augmented pipelines face two major challenges: their semantics-only outputs can inject semantic noise that conflicts with graph topology, and they often incur substantial overhead due to LLM fine-tuning or repeated LLM calls at training/inference. We propose CoFGraph, a confidence-feedback framework that interleaves reciprocal calibration between semantic and structural views to enable reliable and efficient LLM-augmented graph learning. To avoid expensive LLM adaptation, we keep the LLM frozen and train a lightweight Interpreter as a semantic proxy, eliminating the need for LLM fine-tuning and continual test-time prompting. To further mitigate semantic noise and the lack of structural feedback, we introduce confidence-based dual-view learning with node-wise confidence estimation and dynamic role switching, allowing the more reliable view to correct the other. Experiments on four public benchmarks validate the effectiveness of CoFGraph and demonstrate strong stability across varying training label ratios, with particularly consistent gains in low-resource regimes.</abstract>
<identifier type="citekey">zhao-etal-2026-cofgraph</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1428/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>32624</start>
<end>32635</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoFGraph: Interleaving Reciprocal Calibration with Confidence Feedback for LLM-Augmented Graph Learning
%A Zhao, Feng
%A Chen, Tiewen
%A Liu, Xianggan
%A Zhao, Ruilin
%A Song, Yifan
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhao-etal-2026-cofgraph
%X Graph learning requires jointly leveraging node semantics and graph structure, but traditional methods often suffer from label scarcity and shallow semantic utilization. Although LLMs provide strong semantic reasoning for graph learning, existing LLM-augmented pipelines face two major challenges: their semantics-only outputs can inject semantic noise that conflicts with graph topology, and they often incur substantial overhead due to LLM fine-tuning or repeated LLM calls at training/inference. We propose CoFGraph, a confidence-feedback framework that interleaves reciprocal calibration between semantic and structural views to enable reliable and efficient LLM-augmented graph learning. To avoid expensive LLM adaptation, we keep the LLM frozen and train a lightweight Interpreter as a semantic proxy, eliminating the need for LLM fine-tuning and continual test-time prompting. To further mitigate semantic noise and the lack of structural feedback, we introduce confidence-based dual-view learning with node-wise confidence estimation and dynamic role switching, allowing the more reliable view to correct the other. Experiments on four public benchmarks validate the effectiveness of CoFGraph and demonstrate strong stability across varying training label ratios, with particularly consistent gains in low-resource regimes.
%U https://aclanthology.org/2026.emnlp-main.1428/
%P 32624-32635
Markdown (Informal)
[CoFGraph: Interleaving Reciprocal Calibration with Confidence Feedback for LLM-Augmented Graph Learning](https://aclanthology.org/2026.emnlp-main.1428/) (Zhao et al., EMNLP 2026)
ACL