GNNS

How to Make LMs Strong Node Classifiers? (2026.findings-eacl)

Challenge:	Existing methods for summarizing semantic graph structure from raw text are cumbersome and inefficient for long-text documents.
Approach:	They propose a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization.
Outcome:	The proposed model performs state-of-the-art on single- and multi-document summarization tasks while using less memory and fewer parameters.

Copied to clipboard

Zhe Xu, Kaveh Hassani, Si Zhang, Hanqing Zeng, Michihiro Yasunaga, Limei Wang, Dongqi Fu, Ning Yao, Bo Long, Hanghang Tong

Information Retrieval

Challenge:	Language Models (LMs) are increasingly challenging the dominance of domain-specific models, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs).
Approach:	They propose a novel approach that empowers off-the-shelf LMs to achieve performance comparable to state-of-the art (SOTA) GNNs on node classification tasks without requiring any architectural modifications.
Outcome:	The proposed approach outperforms existing GNNs on node classification tasks and is open-source upon publication.

Multimodal Graph Transformer for Multimodal Question Answering (2023.eacl-main)

Copied to clipboard

Xuehai He, Xin Wang

XRec: Large Language Models for Explainable Recommendation (2024.findings-emnlp)

Challenge:	a myriad of complex tasks require both prior knowledge and reasoning intelligence.
Approach:	They propose a plug-and-play quasi-attention mechanism to integrate multimodal graph information to vanilla self-attention as effective prior.
Outcome:	The proposed model is able to perform reasoning across multiple modalities.

Copied to clipboard

Qiyao Ma, Xubin Ren, Chao Huang

Explainability & Interpretability in NLP

Challenge:	Collaborative filtering (CF) is a widely adopted approach, but lacks the ability to provide explanations for the recommended items.
Approach:	They propose a model-agnostic framework that enables large language models to provide comprehensive explanations for user behaviors in recommender systems.
Outcome:	The proposed framework outperforms baseline approaches in explainable recommender systems.

Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning (2025.emnlp-main)

Copied to clipboard

Enjun Du, Siyi Liu, Yongqi Zhang

An Experimental Analysis on Evaluating Patent Citations (2024.emnlp-main)

Challenge:	Existing graph neural networks (GNNs) adopt rigid, query-agnostic path-exploration strategies limiting their ability to adapt to diverse linguistic contexts and semantic nuances.
Approach:	They propose a mixture-of-experts framework that personalizes path exploration . framework uses length experts that adaptively selects and weights candidate paths . it also uses pruning experts that evaluates candidate path from a complementary perspective .
Outcome:	The proposed framework shows superior performance on a diverse benchmark . it uses a mixture of experts that weights and selects path lengths according to query complexity .

Copied to clipboard

Rabindra Nath Nandi, Suman Maity, Brian Uzzi, Sourav Medya

Marrying LLMs with Dynamic Forecasting: A Graph Mixture-of-expert Perspective (2025.findings-naacl)

Challenge:	Graph Neural Networks (GNNs)-based methods can predict patent citations using only patent text.
Approach:	They propose to use Graph Neural Networks to predict citations for patents based on their semantic similarities to generate a semantic graph of patents.
Outcome:	The proposed methods produce 94% recall for patents with high citations and outperform baselines.

Copied to clipboard

Dapeng Jiang, Xiao Luo

Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs (2026.eacl-long)

Challenge:	Recent data-driven approaches often use graph neural networks (GNNs) to learn relationships in dynamical systems.
Approach:	They propose a framework which leverages large language models to enhance generalization capabilities of dynamical system modeling.
Outcome:	The proposed framework improves on existing methods and compares to baselines.

Copied to clipboard

Hussein Abdallah, Ibrahim Abdelaziz, Panos Kalnis, Essam Mansour

Few-Shot Structured Policy Learning for Multi-Domain and Multi-Task Dialogues (2023.findings-eacl)

Challenge:	Traditional KGQA assumes a closed world where answers must exist in the KG, limiting real-world applicability.
Approach:	They propose a system that combines a pre-trained GNN and an LLM for open-world QA.
Outcome:	The proposed system outperforms existing LLM–GNN systems on standard benchmarks and GLOW-BENCH, achieving up to 53.3% and an average 38% improvement.

Copied to clipboard

Thibault Cordier, Tanguy Urvoy, Fabrice Lefèvre, Lina M. Rojas Barahona

SVD-GCL: A Noise-Augmented Hybrid Graph Contrastive Learning Framework for Recommendation (2025.coling-main)

Challenge:	Reinforcement learning is widely adopted to model dialogue managers in task-oriented dialogues, but the user simulator provided by state-of-the-art dialogue frameworks are only rough approximations of human behaviour.
Approach:	They propose to use structured policies to improve sample efficiency when learning on multi-domain and multi-task environments.
Outcome:	The proposed policies improve sample efficiency and performance on multi-domain and multi-task environments.

Copied to clipboard

Liping Wang, Shichao Li, Hui Wang, Yuyan Gao, Mingyao Wei

GAINER: Graph Machine Learning with Node-specific Radius for Classification of Short Texts and Documents (2024.eacl-long)

Challenge:	Recent advances in graph neural networks have made it difficult to capture user preferences.
Approach:	They propose a graph contrastive learning recommendation model based on noise augmentation that integrates truncated singular value decomposition in the feature engineering stage.
Outcome:	The proposed model reduces dimensionality and denoises the original data.

Copied to clipboard

Naganand Yadati

How Do Large Language Models Perform in Dynamical System Modeling (2025.findings-naacl)

Challenge:	Recent advances in Graph Machine Learning (GML) have led to the development of numerous models tailored for processing text for various natural language applications.
Approach:	They propose a framework called Graph mAchine learnIng with Node-spEcific Radius that is aimed at graph-based NLP.
Outcome:	The proposed framework is non-neural and novel for graph-based NLP.

Copied to clipboard

Xiao Luo, Binqi Chen, Haixin Wang, Zhiping Xiao, Ming Zhang, Yizhou Sun

Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters (2023.eacl-main)

Challenge:	Recent data-driven methods often use graph neural networks (GNNs) to learn interactions between objects.
Approach:	They propose prompting techniques for dynamical system modeling and evaluate their performance . they find that large language models demonstrate competitive performance without training .
Outcome:	The proposed methods show competitive performance without training compared to state-of-the-art methods in dynamical system modeling.

Copied to clipboard

Sebastien Montella, Alexis Nasr, Johannes Heinecke, Frederic Bechet, Lina M. Rojas Barahona

Pre-trained Semantic Interaction based Inductive Graph Neural Networks for Text Classification (2025.coling-main)

Challenge:	Recent approaches to text generation from Abstract Meaning Representation (AMR) have been based on neural-centered encoderdecoder architectures.
Approach:	They propose a structure-aware adapter which injects the input graph connectivity within PLMs using Graph Neural Networks.
Outcome:	The proposed adapter is robust to a variety of approaches and can be used to generate Graph-to-Text representations.

Copied to clipboard

Shiyu Wang, Gang Zhou, Jicang Lu, Jing Chen, Ningbo Huang

GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism (2024.findings-naacl)

Challenge:	Existing methods for text classification have vanishing or exploding gradients when dealing with long sequences, making it difficult to handle long-distance dependencies.
Approach:	They propose a graph neural network based on pre-trained semantic interaction called PaSIG . they construct a text-word heterogeneity graph and use context representation capability .
Outcome:	The proposed model outperforms existing methods on five datasets and achieves state-of-the-art performance.

Copied to clipboard

Shuzhou Yuan, Michael Färber

LegalSeg: Unlocking the Structure of Indian Legal Judgments Through Rhetorical Role Classification (2025.findings-naacl)

Challenge:	Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks.
Approach:	They propose a graph-guided self-attention mechanism that integrates token-level structural information into PLMs without additional alignment or concatenation efforts.
Outcome:	The proposed model outperforms baseline models and achieves comparable results to state-of-the-art models on WebNLG datasets.

Copied to clipboard

Shubham Kumar Nigam, Tanmay Dubey, Govind Sharma, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya

Text Classification

Challenge:	a lack of large-scale annotated datasets hinders effective training of ML models . despite advances in semantic segmentation, challenges persist in distinguishing between closely related roles .
Approach:	They propose a large annotated dataset for semantic segmentation of legal documents . they use a rhetorical role classification model to compare performance against other models .
Outcome:	The largest annotated dataset for this task outperforms models relying on sentence-level features.

Can LLMs Convert Graphs to Text-Attributed Graphs? (2025.naacl-long)

Copied to clipboard

Zehong Wang, Sidney Liu, Zheyuan Zhang, Tianyi Ma, Chuxu Zhang, Yanfang Ye

Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models (2025.findings-acl)

Challenge:	Existing approaches to model graph-structured data are limited by the availability of text-attributed graph data.
Approach:	They propose a method to convert existing graphs into text-attributed graphs using large language models.
Outcome:	The proposed method outperforms existing approaches that manually design node features on text-free graphs.

Copied to clipboard

Haochen Liu, Song Wang, Chen Chen, Jundong Li

Hierarchical Information Matters: Text Classification via Tree Based Graph Neural Network (2022.coling-1)

Challenge:	Existing methods for large language models require costly fine-tuning or retrieve noisy KG information.
Approach:	They propose to generate KG-based input embedding prefixes as soft prompts but fail to account for question relevance, resulting in noisy prompts.
Outcome:	The proposed model outperforms state-of-the-art methods across multiple datasets.

Copied to clipboard

Chong Zhang, He Zhu, Xingyu Peng, Junran Wu, Ke Xu

LLaSA: Large Language and Structured Data Assistant (2025.naacl-long)

Challenge:	Text classification is a primary task in natural language processing (NLP).
Approach:	They propose a graph neural network (HINT) that makes full use of hierarchical information contained in the text for the task of text classification.
Outcome:	The proposed method outperforms the state-of-the-art methods on popular benchmarks while having a simple structure and few parameters.

Copied to clipboard

Yao Xu, Shizhu He, Jiabei Chen, ZengXiangrong ZengXiangrong, Bingning Wang, Guang Liu, Jun Zhao, Kang Liu

ConTextING: Granting Document-Wise Contextual Embeddings to Graph Neural Networks for Inductive Text Classification (2022.coling-1)

Challenge:	Structured knowledge grounding (SKG) tasks are a key part of many NLP applications.
Approach:	They propose a framework for enhancing LLMs' ability to handle structured data . they represent various types of structured data in a unified hypergraph format .
Outcome:	The proposed framework outperforms existing methods on SKG tasks using LoRA finetuning.

Copied to clipboard

Yen-Hao Huang, Yi-Hsin Chen, Yi-Shin Chen

Graph Neural Networks for Multiparallel Word Alignment (2022.findings-acl)

Challenge:	Graph neural networks (GNNs) are used to learn document representation from graph structures.
Approach:	They propose a unified model with a joint training mechanism to learn from document embeddings and contextual word interactions simultaneously.
Outcome:	The proposed model outperforms pure inductive GNNs and BERT-style models . the proposed model also has a joint training mechanism to learn from document embeddings and contextual word interactions simultaneously.

Copied to clipboard

Ayyoob Imani, Lütfi Kerem Senel, Masoud Jalili Sabet, François Yvon, Hinrich Schuetze

Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction (2021.findings-acl)

Challenge:	Generally, word alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel.
Approach:	They propose a multiparallel word alignment graph and graph neural networks to exploit it . they add and remove edges from the initial alignments and generalize the model .
Outcome:	The proposed method outperforms previous work on three word alignment datasets and on a downstream task.

Copied to clipboard

Zhexue Chen, Hong Huang, Bang Liu, Xuanhua Shi, Hai Jin

Sentiment Analysis

Challenge:	Existing approaches to extract triplets from sentences neglect the mutual information between aspects and have the problem of error propagation.
Approach:	They propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model to exploit the syntactical and semantic relationships between the triplet elements and jointly extract them.
Outcome:	The proposed model outperforms existing methods on four benchmark datasets and significantly outperformed existing approaches.

OpenGraph: Towards Open Graph Foundation Models (2024.findings-emnlp)

Copied to clipboard

Lianghao Xia, Ben Kao, Chao Huang

Language is All a Graph Needs (2024.findings-eacl)

Challenge:	Graph Neural Networks (GNNs) have emerged as promising techniques for encoding structural information and improving performance in tasks like link prediction and node classification.
Approach:	They propose a graph foundation model that generalizes to unseen graph data with different properties.
Outcome:	The proposed model achieves remarkable zero-shot graph learning performance across various settings.

Copied to clipboard

Ruosong Ye, Caiqi Zhang, Runhui Wang, Shuyuan Xu, Yongfeng Zhang

Document-level Relation Extraction with Dual-tier Heterogeneous Graph (2020.coling-main)

Challenge:	Existing work on integrating graph problems into generative language modeling framework remains limited.
Approach:	They propose an LLM with instructions based on natural language to perform graph tasks.
Outcome:	The proposed model surpasses all GNN baselines on ogbn-arxiv, Cora and PubMed datasets and sheds light on generative LLMs as new foundation model for graph machine learning.

Copied to clipboard

Zhenyu Zhang, Bowen Yu, Xiaobo Shu, Tingwen Liu, Hengzhu Tang, Wang Yubin, Li Guo

VISPool: Enhancing Transformer Encoders with Vector Visibility Graph Neural Networks (2024.findings-acl)

Challenge:	Existing methods focus on extracting relations from single sentence . document-level relation extraction requires a comprehension of the whole document .
Approach:	They propose a graph-based model with Dual-tier Heterogeneous Graph (DHG) for document-level relation extraction.
Outcome:	The proposed model achieves state-of-the-art performance on two widely used datasets.

Copied to clipboard

Tuna Alikaşifoğlu, Arda Aras, Aykut Koc

DGLF: A Dual Graph-based Learning Framework for Multi-modal Sarcasm Detection (2024.emnlp-main)

Challenge:	Existing graph-based graph construction methods rely on static graphs and are not scalable with increasing document and word counts.
Approach:	They propose a dynamic graph construction method based on vector visibility graphs (VVGs) they propose scalable model architecture that integrates VVG convolutional networks into transformer pipelines.
Outcome:	The proposed model outperforms baseline models on the GLUE benchmark datasets.

Copied to clipboard

Zhihong Zhu, Kefan Shen, Zhaorun Chen, Yunyan Zhang, Yuyan Chen, Xiaoqi Jiao, Zhongwei Wan, Shaorong Xie, Wei Liu, Xian Wu, Yefeng Zheng

Taming Language Models for Text-attributed Graph Learning with Decoupled Aggregation (2025.acl-long)

Challenge:	Existing methods for multimodal sarcasm detection neglect high-order relationships and underestimate high-frequency messages.
Approach:	They propose a Dual Graph-based Learning Framework to capture inter-modal inconsistencies . they propose combining a hypergraph and a vanilla graph to achieve enhanced propagation .
Outcome:	The proposed model outperforms existing state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Chuang Zhou, Zhu Wang, Shengyuan Chen, Jiahe Du, Qiyuan Zheng, Zhaozhuo Xu, Xiao Huang

ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs (2022.findings-emnlp)

Challenge:	Existing approaches to learning text-attributed graphs neglect interaction between textual and structural information.
Approach:	They propose a framework that integrates textual and structural information into TAG learning . they propose combining semantic aggregation and structural aggregations to improve learning a .
Outcome:	The proposed framework outperforms state-of-the-art learning methods while requiring less resources.

Copied to clipboard

Costas Mavromatis, George Karypis

Graph Reasoning for Question Answering with Triplet Retrieval (2023.findings-acl)

Challenge:	Knowledge Graph Question Answering (KGQA) involves retrieving entities as answers from a Knowledge Flow using natural language queries.
Approach:	They propose a method to decode a question into instructions that are dense question representations used to guide the KG traversals.
Outcome:	The proposed method improves instruction decoding and execution by using a KG-aware information to update the initial instructions.

Copied to clipboard

Shiyang Li, Yifan Gao, Haoming Jiang, Qingyu Yin, Zheng Li, Xifeng Yan, Chao Zhang, Bing Yin

LLM as Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge Graphs (2024.findings-acl)

Challenge:	Existing methods to answer complex questions require reasoning over knowledge graphs (KGs) state-of-the-art methods constrain retrieved knowledge in local subgraphs and discard more diverse triplets that are disconnected but useful for question answering.
Approach:	They propose a method to retrieve the most relevant triplets from KGs and then rerank them, which are then concatenated with questions to be fed into language models.
Outcome:	The proposed method outperforms state-of-the-art methods on commonsenseQA and OpenbookQA datasets with 4.6% absolute accuracy.

Copied to clipboard

Kai Wang, Yuwei Xu, Zhiyong Wu, Siqiang Luo

Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification (2021.naacl-main)

Challenge:	Knowledge Graph (KG) inductive reasoning is widely adopted in various applications.
Approach:	They propose a framework for low-resource inductive reasoning using Large Language Models to generate a graph-structural prompt for pre-trained KGs.
Outcome:	The proposed framework outperforms previous methods in three-shot, one-shot and zero-shot reasoning tasks.

Copied to clipboard

Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He, Bowen Zhou

Sentiment Analysis

Challenge:	Recent work on aspect-level sentiment classification has shown that syntactic information is effective in capturing long-range syntaktic relations that are obscure from the surface form.
Approach:	They propose a graph ensemble technique that integrates syntactic structures with GNNs to better leverage syntaktic information in the face of parsing errors.
Outcome:	The proposed model outperforms models with single dependency tree and beats other models without adding model parameters.

Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph (2020.coling-main)

Copied to clipboard

Xu Wang, Shuai Zhao, Jiale Han, Bo Cheng, Hao Yang, Jianchang Ao, Zhenzi Li

Text is All You Need: LLM-enhanced Incremental Social Event Detection (2025.acl-long)

Challenge:	Existing studies rely on deep graph neural networks (GNNs) to capture rich structural information, but they lack the structural information needed for QA.
Approach:	They propose a framework which captures structural information from KBs and models long-distance node relations from two perspectives.
Outcome:	The proposed framework models long-distance node relations from two perspectives . it is based on two widely used multi-hop KBQA datasets .

Copied to clipboard

Zitai Qiu, Congbo Ma, Jia Wu, Jian Yang

Graph-based Dependency Parsing with Graph Neural Networks (P19-1)

Challenge:	Existing state-of-the-art (SOTA) SED models rely on graph neural networks (GNNs) Existing SED frameworks rely heavily on GNNs, which require complex graph construction and time-consuming training processes.
Approach:	They propose a framework that leverages the rich background knowledge of large language models to formalize and disambiguate short texts by completing abbreviations and summarizing informal expressions.
Outcome:	The proposed framework outperforms existing models on two challenging real-world datasets.

Copied to clipboard

Tao Ji, Yuanbin Wu, Man Lan

Green & Sustainable NLP

Challenge:	In graph-based dependency parsers, learning representations is gaining in importance, and we use graph neural networks to learn the representations.
Approach:	They propose to use graph neural networks to learn dependency tree nodes and propose to add a new aggregation function to the system.
Outcome:	The proposed model achieves the best UAS and LAS on PTB (96.0%, 94.3%) without using external resources.

Graph Language Models (2024.acl-long)

Copied to clipboard

Moritz Plenz, Anette Frank

Bridging Attribution and Open-Set Detection using Graph-Augmented Instance Learning in Synthetic Speech (2026.eacl-long)

Challenge:	Language Models (LMs) are the workhorses of NLP, but their interplay with structured knowledge graphs (KGs) is still actively researched.
Approach:	They propose a Graph Language Model (GLM) that integrates the strengths of both approaches and mitigates their weaknesses.
Outcome:	Empirical evaluations show that the proposed model surpasses both LM- and GNN-based baselines in supervised and zero-shot setting, demonstrating their versatility.

Copied to clipboard

Mohd Mujtaba Akhtar, null Girish, Farhan Sheth, Muskaan Singh

Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation (2023.acl-long)

Challenge:	Synthetic speech detection is a critical part of safeguarding digital communication, enabling systems to identify and mitigate the risks posed by highly realistic, machine-generated voices.
Approach:	They propose a framework that combines SFMs with graph-based modeling and open-set generalization to capture meaningful relationships between utterances and recognize speech that doesn’t belong to any known generator.
Outcome:	The proposed framework improves performance across both tasks, with Mamba-based embeddings delivering particularly strong results.

Copied to clipboard

Chen Tang, Hongbo Zhang, Tyler Loakman, Chenghua Lin, Frank Guerin

Learning to Update Knowledge Graphs by Reading News (D19-1)

Challenge:	Existing graph neural networks (GNNs) teach message passing on a graph from text, resulting in a semantic gap between graph knowledge and text.
Approach:	They propose a framework to integrate external graph knowledge into chatbots by coagulating representations of both text and graph knowledge.
Outcome:	The proposed framework outperforms state-of-the-art (SOTA) baselines on dialogue generation.

Copied to clipboard

Jizhi Tang, Yansong Feng, Dongyan Zhao

Challenges in Pre-Training Graph Neural Networks for Context-Based Fake News Detection: An Evaluation of Current Strategies and Resource Limitations (2024.lrec-main)

Challenge:	Existing methods to update knowledge graphs rely on elaborately designed IE systems and domain-specific rules.
Approach:	They propose a novel neural network method to update knowledge graphs (KGs) they use a text-based attention mechanism to guide updating messages through KGs .
Outcome:	The proposed method can effectively broadcast news information to KG structures and perform necessary link-adding or link-deleting operations to ensure the KG up-to-date according to news snippets.

Copied to clipboard

Gregor Donabauer, Udo Kruschwitz

Ethical NLP

Challenge:	Graph Neural Networks (GNNs) are used to train neural networks to detect fake news based on context-based methods.
Approach:	They propose to combine the two by applying pre-training of Graph Neural Networks (GNNs) in the domain of context-based fake news detection.
Outcome:	The proposed methods show that transfer learning does not lead to significant improvements over training a model from scratch in the domain of context-based fake news detection.

Exploring the Potential of Large Language Models for Heterophilic Graphs (2025.naacl-long)

Copied to clipboard

Yuxia Wu, Shujie Li, Yuan Fang, Chuan Shi

Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models (2025.emnlp-main)

Challenge:	Existing approaches for heterophilic graphs overlook rich textual data associated with nodes, which could unlock deeper insights into their heterophilistic contexts.
Approach:	They propose a two-stage framework to enhance node classification on heterophilic graphs by leveraging open-world knowledge encoded by large language models.
Outcome:	The proposed framework can be used to better characterize heterophilic graphs, where neighboring nodes often exhibit different labels.

Copied to clipboard

Mo Zhiqiang, Yang Hua, Jiahui Li, Yuan Liu, Shawn Wong, Jianmin Huang

Neural Topic Modeling by Incorporating Document Relationship Graph (2020.emnlp-main)

Challenge:	Existing approaches to integrating graph and language models face two key limitations: achieving robust semantic alignment and ensuring interpretability in outputs.
Approach:	They propose a framework to integrate graph and language modalities while enhancing transparency.
Outcome:	Extensive experiments on three benchmark datasets show that the proposed framework surpasses existing methods in efficiency and generates outputs that are significantly more interpretable.

Copied to clipboard

Deyu Zhou, Xuemeng Hu, Rui Wang

MARK: Multi-agent Collaboration with Ranking Guidance for Text-attributed Graph Clustering (2025.findings-acl)

Challenge:	Graph Topic Models (GNNs) capture relationships between graph nodes via message passing . recent research has focused on topic modeling using latent Dirichlet Allocation .
Approach:	They propose a Graph Topic Model (GTM) that captures relationships between graph nodes via message passing.
Outcome:	The proposed model captures the relationships between nodes via message passing . the results demonstrate that the proposed model is effective in generating documents .

Copied to clipboard

Yiwei Fu, Yuxing Zhang, Chunchun Chen, JianwenMa JianwenMa, Quan Yuan, Rong-Cheng Tu, Xinli Huang, Wei Ye, Xiao Luo, Minghua Deng

Graph Enhanced Contrastive Learning for Radiology Findings Summarization (2022.acl-long)

Challenge:	Existing approaches to cluster graphs with GNNs are limited due to label scarcity.
Approach:	They propose to leverage large language models to enhance text-attributed graph clustering by using three LLMs as ranking-based supervision signals.
Outcome:	The proposed approach generates reliable guidance using collaboration of three LLM-based agents as ranking-based supervision signals.

Copied to clipboard

Jinpeng Hu, Zhuo Li, Zhihong Chen, Zhen Li, Xiang Wan, Tsung-Hui Chang

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning (2025.emnlp-main)

Challenge:	Existing methods for automating impression generation have limited the relationship between extra knowledge and the original findings.
Approach:	They propose a framework for automating impression generation that exploits extra knowledge and original findings . they propose combining key words and their relations to extract critical information .
Outcome:	The proposed framework exploits extra knowledge and the original findings in an integrated way . the state-of-the-art results on two datasets confirm the effectiveness of the proposed method .

Copied to clipboard

Gangwei Jiang, Yahui Liu, Zhaoyi Li, Wei Bi, Fuzheng Zhang, Linqi Song, Ying Wei, Defu Lian

Reasoning

Challenge:	Recent advances in reasoning with large language models have popularized Long Chain-of-Thought (LCoT) a framework that converts sequential LCoTs into hierarchical tree structures enables deeper structural analysis of LLM reasoning.
Approach:	They propose a framework that converts sequential LCoTs into hierarchical tree structures and enables deeper structural analysis of LLM reasoning.
Outcome:	The proposed framework can be used to analyze LLM reasoning in a variety of tasks and models.

Graph Neural Network Enhanced Retrieval for Question Answering of Large Language Models (2025.naacl-long)

Copied to clipboard

Zijian Li, Qingyan Guo, Jiawei Shao, Lei Song, Jiang Bian, Jun Zhang, Rui Wang

Natural Language Interfaces

Challenge:	Existing retrieval methods divide reference documents into passages, treating them in isolation. Existing methods only use contiguous passages or keywords.
Approach:	They propose a retrieval method that leverages graph neural networks to exploit relatedness between passages to enhance retrieval.
Outcome:	The proposed method improves retrieval by exploiting the relatedness between passages.

A Knowledge Graph Reasoning-Based Model for Computerized Adaptive Testing (2025.coling-main)

Copied to clipboard

Xinyi Qiu, Zhiyun Chen

ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction (2023.findings-emnlp)

Challenge:	Existing studies have failed to account for the differences in concept relevance when a question involves multiple concepts .
Approach:	They propose a Knowledge Graph Reasoning-Based Model for CAT that captures semantic and relational information between concepts and questions and incorporates multiple evaluation objectives.
Outcome:	The proposed model outperforms existing methods on three authentic educational datasets.

Copied to clipboard

Yaorui Shi, An Zhang, Enzhi Zhang, Zhiyuan Liu, Xiang Wang

AGRec: Adapting Autoregressive Decoders with Graph Reasoning for LLM-based Sequential Recommendation (2025.findings-acl)

Challenge:	Existing methods for predicting chemical reactions are limited by insufficient training data and inability to utilize textual information.
Approach:	They propose a framework that leverages chemical knowledge encoded in language models to assist GNNs, thereby enhancing the accuracy of real-world chemical reaction predictions.
Outcome:	The proposed framework improves state-of-the-art GNN-based methods across chemical reaction datasets especially in out-of distribution settings.

Copied to clipboard

Xinfeng Wang, Jin Cui, Fumiyo Fukumoto, Yoshimi Suzuki

JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering (2022.naacl-main)

Challenge:	Autoregressive decoders in large language models excel at capturing sequential behaviors for generative recommendations, but they lack graph-structured user-item interactions, which are widely recognized as beneficial.
Approach:	They propose a novel algorithm that adapts LLMs’ decoders with graph reasoning for recommendation by augmenting the decoding logits with an auxiliary GNN model to optimize token generation.
Outcome:	The proposed model outperforms state-of-the-art models in sequential recommendations.

Copied to clipboard

Yueqing Sun, Qi Shi, Le Qi, Yu Zhang

MGM: Global Understanding of Audience Overlap Graphs for Predicting the Factuality and the Bias of News Media (2025.naacl-long)

Challenge:	Existing KG-augmented models for commonsense question answering ignore the effectively fusing and reasoning over question context representations and the KG representations.
Approach:	They propose a novel model which combines a logical reasoning and a dynamic pruning mechanism to solve these limitations.
Outcome:	The proposed model improves existing models and performs interpretable reasoning on the CommonsenseQA and OpenBookQA datasets.

Copied to clipboard

Muhammad Arslan Manzoor, Ruihong Zeng, Dilshod Azizov, Preslav Nakov, Shangsong Liang

Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs (2025.coling-main)

Challenge:	Existing methods for profiling news media focus on textual features, causing them to overlook complex relationships between entities.
Approach:	They propose a framework for profiling news media from the lens of political bias and factuality.
Outcome:	The proposed framework improves existing models and improves them by integrating structural information from similar nodes.

Copied to clipboard

Taiqiang Wu, Zhe Zhao, Jiahao Wang, Xingyu Bai, Lei Wang, Ngai Wong, Yujiu Yang

Green & Sustainable NLP

Challenge:	Existing methods to train low-latency multilayer perceptrons (MLPs) on graph tasks are based on graph nodes and lack graph structural information.
Approach:	They propose to distill graph structural information from Graph Neural Networks (GNNs) to low-latency multilayer perceptrons (MLPs) on graph tasks.
Outcome:	The proposed method does not require graph edges (edge-free setting) yet learns structure-aware MLPs.

Be More with Less: Hypergraph Attention Networks for Inductive Text Classification (2020.emnlp-main)

Copied to clipboard

Kaize Ding, Jianling Wang, Jundong Li, Dingcheng Li, Huan Liu

Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective on Molecule Graphs (2024.findings-emnlp)

Challenge:	Text classification is a critical research topic with broad applications in natural language processing. graph neural networks (GNNs) have received increasing attention but their performance is jeopardized in practice.
Approach:	They propose a model which captures long-distance interactions between words and a graph-based model which can be used to perform text classification.
Outcome:	The proposed model can achieve more expressive power with less computational consumption on the text classification task.

Copied to clipboard

Yinhan He, Zaiyi Zheng, Patrick Soga, Yaochen Zhu, Yushun Dong, Jundong Li

DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text (2023.findings-emnlp)

Challenge:	Graph Neural Networks (GNNs) are successful in molecular property prediction tasks, but their outputs are often black-box and not easily understandable by humans.
Approach:	They propose a method to unleash the power of large language models (LLMs) to explain GNNs for molecular property prediction.
Outcome:	The proposed method uses autoencoder to generate the counterfactual graph topology from a set of counterfact text pairs based on an input graph.

Copied to clipboard

Shuaiyi Li, Yang Deng, Wai Lam

Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation (2022.coling-1)

Challenge:	Existing approaches for spatial reasoning in text overlook the gap between natural language and symbolic structures.
Approach:	They propose a novel depth-wise Graph Neural Network to aggregate spatial information over the depth dimension instead of the breadth dimension of the graph.
Outcome:	The proposed model outperforms existing methods on two multi-hop spatial reasoning datasets.

Copied to clipboard

Binh Nguyen, Long Nguyen, Dien Dinh

Automated Molecular Concept Generation and Labeling with Large Language Models (2025.coling-main)

Challenge:	Recent studies have used Graph Neural Networks (GNNs) to encode language knowledge into token embeddings.
Approach:	They propose a multi-level community-awareness Graph Neural Network layer to jointly model local and global relationships between words and their linguistic roles in multiple communities.
Outcome:	The proposed method reduces time complexity in very long sentences while preserving the original meaning.

Copied to clipboard

Zimin Zhang, Qianli Wu, Botao Xia, Fang Sun, Ziniu Hu, Yizhou Sun, Shichang Zhang

MuSe: Multi-Stage Graph Reasoning via Vision-Language Models (2026.acl-long)

Challenge:	Concept-based models lack explainability and need predefined concepts and manual labeling in molecular science.
Approach:	They propose a framework that leverages Large Language Models to generate and label predictive molecular concepts without human input.
Outcome:	The proposed framework outperforms existing models on several benchmarks while maintaining explainability and allowing easy intervention.

Copied to clipboard

Guanyu Wang, Xu Chu, Zhijie Tan, Xinrong Chen, Tong Mo, Weiping Li

A Survey of Automatic Text Summarization Using Graph Neural Networks (2022.coling-1)

Challenge:	Graph Neural Networks (GNNs) and graph transformers are inadequate for tasks with limited generalization.
Approach:	They propose a multi-stage graph reasoning framework based on vision-language models that incrementally samples and visualizes task-relevant subgraphs.
Outcome:	The proposed framework outperforms existing benchmarks in Graph-related tasks.

Copied to clipboard

Marco Ferdinand Salchner, Adam Jatowt

Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision? (2025.acl-long)

Challenge:	Abstractive ATS involves generating factually correct and fluent sentences.
Approach:	They provide an overview of the use of graph neural networks (GNNs) for automatic text summarization.
Outcome:	The proposed model is based on a set of graph neural networks (GNNs) that are used to generate a concise, correct and fluent summary of a given text.

Copied to clipboard

Zihao Li, Lecheng Zheng, Bowen Jin, Dongqi Fu, Baoyu Jing, Yikun Ban, Jingrui He, Jiawei Han

Distilling Structured Knowledge for Text-Based Relational Reasoning (2020.emnlp-main)

Challenge:	Graph Neural Networks (GNNs) with CLIP pipeline are difficult because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and conceptual gaps between domains.
Approach:	They propose a multi-modal prompt learning paradigm to adapt pre-trained GNNs to downstream tasks with weak text supervision.
Outcome:	The proposed model can generalize graphs to unseen classes with weak text supervision.

Copied to clipboard

Jin Dong, Marc-Antoine Rondeau, William L. Hamilton

‘Hello, World!’: Making GNNs Talk with LLMs (2025.findings-emnlp)

Challenge:	Existing text-based relational reasoning models lack a symbolic representation of text . performance gap between NLP models and structured models remains .
Approach:	They first pre-train a GNN on a reasoning task using structured inputs and then incorporate its knowledge into an NLP model.
Outcome:	The proposed model improves on two state-of-the-art NLP models on 13 different inductive reasoning datasets from the CLUTRR benchmark.

Copied to clipboard

Sunwoo Kim, Soo Yong Lee, Jaemin Yoo, Kijung Shin

AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs (2025.naacl-long)

Challenge:	graph neural networks have shown remarkable performance across diverse graph-related tasks, but their high-dimensional hidden representations render them black boxes.
Approach:	They propose a graph-based neural network with hidden representations in the form of human-readable text.
Outcome:	The proposed GNN outperforms existing LLM-based baseline methods on node classification and link prediction.

Copied to clipboard

Quazi Ishtiaque Mahmud, Ali TehraniJamsaz, Hung D Phan, Le Chen, Mihai Capotă, Theodore L. Willke, Nesreen K. Ahmed, Ali Jannesari

Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification using Graph Neural Networks? (2023.findings-emnlp)

Challenge:	In-Context Learning (ICL) is a powerful technique to augment the capabilities of LLMs for a diverse range of tasks.
Approach:	They propose a way to generate context using guidance from graph neural networks to generate efficient parallel codes.
Outcome:	The proposed method improves state-of-the-art LLMs by 19.9% and 6.48% on NAS and rodinia benchmarks.

Copied to clipboard

Margarita Bugueño, Gerard de Melo

CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection (2024.findings-acl)

Challenge:	Graph Neural Networks have been used for text classification, but only in domains with limited data characteristics.
Approach:	They compare graph representation methods for text classification using different architectures and setups.
Outcome:	The proposed graph representation methods outperform other models in document comprehension tasks.

Copied to clipboard

Sirry Chen, Shuo Feng, Liang Songsong, Chen-Chen Zong, Jing Li, Piji Li

Few-Shot Semantic Dependency Parsing via Graph Contrastive Learning (2024.lrec-main)

Challenge:	Existing methods for social media bot detection neglect community structure and poor model generalization due to the relatively small scale of the dataset.
Approach:	They propose a framework that constructs social networks as heterogeneous graphs and uses community-aware modules to mine hard positive and hard negative samples for supervised graph contrastive learning.
Outcome:	The proposed framework outperforms baselines on three social media bot benchmarks.

Copied to clipboard

Bin Li, Yunlong Fan, Yikemaiti Sataer, Chuanqi Shi, Miao Gao, Zhiqiang Gao

Deep Attention Diffusion Graph Neural Networks for Text Classification (2021.emnlp-main)

Challenge:	Existing graph neural networks (GNNs) have shown promising performance on semantic dependency parsing (SDP) training a high-performing model requires a large amount of labeled data and it is prone to over-fitting in the absence of sufficient labele .
Approach:	They propose a syntax-guided graph contrastive learning framework to train GNNs with unlabeled data and fine-tune pre-trained GNN models with few-shot labeled SDP data.
Outcome:	The proposed framework achieves promising results when few-shot training samples are available.

Copied to clipboard

Yonghao Liu, Renchu Guan, Fausto Giunchiglia, Yanchun Liang, Xiaoyue Feng

Towards Enhancing Relational Rules for Knowledge Graph Link Prediction (2023.findings-emnlp)

Challenge:	Existing methods for text classification based on graph neural networks (GNNs) consider only one-hop neighborhoods and low-frequency information within texts, which suffer from over-smoothing issues if many graph layers are stacked.
Approach:	They propose a deep attention diffusion Graph Neural Network model to learn text representations by bridging the chasm of interaction difficulties between a word and its distant neighbors.
Outcome:	The proposed model outperforms existing methods on standard benchmark datasets on a set of textual features.

Copied to clipboard

Shuhan Wu, Huaiyu Wan, Wei Chen, Yuting Wu, Junfeng Shen, Youfang Lin

Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge Graphs (2021.emnlp-main)

Challenge:	Existing knowledge graph reasoning methods are inadequate for missing knowledge . Various methods are explored to facilitate reasoning for missing information .
Approach:	They propose a novel knowledge graph reasoning approach that uses a query-related fusion gate unit to model the sequentiality of relation composition and a buffering update mechanism to alleviate lagged entity information propagation.
Outcome:	Experimental results show that the proposed approach is superior on both transductive and inductive link prediction tasks.

Copied to clipboard

Chengjin Xu, Fenglong Su, Jens Lehmann

IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval (2025.emnlp-main)

Challenge:	Existing embedding-based approaches disregard time information that exists in many large-scale knowledge graphs, leaving much room for improvement.
Approach:	They propose a Time-aware Entity Alignment approach that incorporates relation and time information into a vector space and uses Graph Neural Networks to learn entity representations.
Outcome:	The proposed approach outperforms the state-of-the-art methods on real-world TKG datasets due to the inclusion of time information.

Copied to clipboard

Shounak Paul, Dhananjay Ghumare, Pawan Goyal, Saptarshi Ghosh, Ashutosh Modi

Information Retrieval

Challenge:	Existing models for identifying/retrieving relevant statutes and prior cases/precedents are inherently related, e.g., similar cases tend to cite similar statutes due to similar factual situation.
Approach:	They propose a corpus that provides a common testbed for developing models that exploit the dependence between the two tasks.
Outcome:	The proposed corpus exploits the dependence between the two retrieval tasks and provides a baseline model for the two tasks.

RecLM: Recommendation Instruction Tuning (2025.acl-long)

Copied to clipboard

Yangqin Jiang, Yuhao Yang, Lianghao Xia, Da Luo, Kangyi Lin, Chao Huang

Fair Text-Attributed Graph Representation Learning (2025.findings-emnlp)

Challenge:	Modern recommender systems aim to understand user-item relationships through past interactions, but their effectiveness is limited when handling sparse data or zero-shot scenarios.
Approach:	They propose a model-agnostic recommendation instruction-tuning paradigm that integrates large language models with collaborative filtering.
Outcome:	The proposed model-agnostic recommendation instruction-tuning paradigm improves performance across various settings and plug-and-play compatibility with state-of-the-art recommender systems.

Copied to clipboard

Ruilin Luo, Tianle Gu, Lin Wang, Yunfeng Zhou, Songtao Jiang, Lei Wang, Yujiu Yang

Improving Robustness of GNN-based Anomaly Detection by Graph Adversarial Training (2024.lrec-main)

Challenge:	Text-Attributed Graphs (TAGs) inherit issues from Graph Neural Networks such as fairness.
Approach:	They propose to evolve LM-as-encoder to LM as-fair-encoding process to explore fairness in TAGRL.
Outcome:	The proposed process can be integrated with fairness-enhancing strategies on the GNNs decoder side.

Copied to clipboard

Xiangping Zheng, Bo Wu, Alex X. Zhang, Wei Li

Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis (2024.lrec-main)

Challenge:	Graph neural networks excel at anomaly detection, but exhibit vulnerability to attacks . novel mechanism for graph adversarial training designed to bolster anomaly detectors .
Approach:	They propose a mechanism for graph adversarial training to bolster anomaly detection systems against potential poisoning attacks.
Outcome:	The proposed method bolsters GNN-based anomaly detection systems against poisoning attacks.

Copied to clipboard

Akash Anil, Victor Gutierrez-Basulto, Yazmin Ibanez-Garcia, Steven Schockaert

GNN-SL: Sequence Labeling Based on Nearest Examples via GNN (2023.findings-acl)

Challenge:	Existing methods for inductive knowledge graph completion are underperforming . implausible entities are not ranked and only the most informative path is taken into account .
Approach:	They propose to use a rule-based approach to find plausible triples missing from a given KG.
Outcome:	The proposed models outperform state-of-the-art methods on inductive knowledge graph completion.

Copied to clipboard

Shuhe Wang, Yuxian Meng, Rongbin Ouyang, Jiwei Li, Tianwei Zhang, Lingjuan Lyu, Guoyin Wang

Double-Branch Multi-Attention based Graph Neural Network for Knowledge Graph Completion (2023.acl-long)

Challenge:	Existing sequence labeling algorithms can be decomposed into two parts .
Approach:	They propose a graph neural networks sequence labeling (GNN-SL) that augments the vanilla SL model output with similar tagging examples retrieved from the whole training set.
Outcome:	The proposed model performs well on three sequence labeling tasks.

Copied to clipboard

Hongcai Xu, Junpeng Bao, Wenbo Liu

GNN-RAG: Graph Neural Retrieval for Efficient Large Language Model Reasoning on Knowledge Graphs (2025.findings-acl)

Challenge:	Existing knowledge graph embedding methods cannot capture local and global information and are not designed well to learn representations of seen entities with sparse neighborhoods in isolated subgraphs.
Approach:	They propose a double-branch multi-attention based graph neural network to learn more expressive entity representations which contain rich global-local structural information.
Outcome:	The proposed method outperforms a general GNN-based approach for KGC.

Copied to clipboard

Costas Mavromatis, George Karypis

HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answering (2025.findings-emnlp)

Challenge:	Existing approaches to retrieval-augmented generation (RAG) rely on costly LLM calls to generate relation paths or traverse the KG.
Approach:	They propose a framework that uses lightweight Graph Neural Networks to enhance retrieval.
Outcome:	The proposed framework outperforms existing methods on multi-hop and multi-entity questions.

Copied to clipboard

Runsong Jia, Mengjia Wu, Ying Ding, Jie Lu, Yi Zhang

Question Answering

Challenge:	graph neural networks capture structured graph information, but lack integration at the reasoning level.
Approach:	They propose a framework that leverages graph structural information to reason interpretable academic QA results.
Outcome:	The proposed framework outperforms sota baselines on OpenAlex and DBLP datasets.

Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights (2025.acl-long)

Copied to clipboard

Célia Nouri, Chloé Clavel, Jean-Philippe Cointet

Linking Adaptive Structure Induction and Neuron Filtering: A Spectral Perspective for Aspect-based Sentiment Analysis (2024.lrec-main)

Challenge:	Existing approaches to detect abusive language often ignore conversational context, leading to inconsistent and sometimes inconclusive results.
Approach:	They propose a graph neural network approach that uses conversational context to model social media conversations as graphs, where nodes represent comments and edges capture reply structures.
Outcome:	The proposed model outperforms baseline and linear context-aware methods and achieves significant improvements in F1 scores.

Copied to clipboard

Hao Niu, Maoyi Wang, Yun Xiong, Biao Yang, Xing Jia, Zhonglei Guo

Sentiment Analysis

Challenge:	incorporating structure information can improve the performance of aspect-based sentiment analysis.
Approach:	They propose a method to conduct neuron-level manipulations on word representations in the frequency domain.
Outcome:	The proposed method can achieve or come close to state-of-the-art in ABSA.

GAMIC: Graph-Aligned Molecular In-context Learning for Molecule Analysis via LLMs (2025.findings-emnlp)

Copied to clipboard

Ali Al Lawati, Jason S Lucas, Zhiwei Zhang, Prasenjit Mitra, Suhang Wang

LGA: LLM-GNN Aggregation for Temporal Evolution Attribute Graph Prediction (2025.emnlp-main)

Challenge:	Current methods for retrieving large language models rely on molecule feature similarity, such as Morgan fingerprints, which do not adequately capture the global molecular and atom-binding relationships.
Approach:	They propose a self-supervised learning technique that embeds demonstration examples into the input prompt.
Outcome:	The proposed technique outperforms simple Morgan-based retrieval methods across tasks by up to 45%.

Copied to clipboard

Feng Zhao, Ruoyu Chai, Kangzheng Liu, Xianggan Liu

Representation Learning

Challenge:	Current methods focus on 1-hop neighborhood aggregation, lacking capability to capture complex structural interactions.
Approach:	They propose a framework that integrates structural information into attribute embeddings through an attribute embedded loss.
Outcome:	The proposed framework shows significant improvements over existing methods on real-world datasets.

Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning (2025.emnlp-main)

Copied to clipboard

Yicong Wu, Guangyue Lu, Yuan Zuo, Huarong Zhang, Junjie Wu

Reasoning

Challenge:	Recent advances in Large Reasoning Models (LLMs) provide a zero-shot alternative via explicit, long chain-of-thought reasoning.
Approach:	They propose a GNN-free approach that reformulates graph tasks as textual reasoning problems solved by LRMs.
Outcome:	The proposed approach outperforms state-of-the-art baselines in zero-shot settings, producing interpretable and effective predictions.

Compressing LLM Knowledge into Graph Representations for Text-attributed Graphs Learning (2026.acl-long)

Copied to clipboard

Runhuai Chen, Dian Shen, Dandan Zhang, Kaihong Huang, Linghui Meng, Beilun Wang

MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language Models (2026.findings-acl)

Challenge:	Existing GNN-LLM approaches use large language models at inference time for processing text attributes, resulting in costly deployment.
Approach:	They propose a framework that internalizes LLM knowledge within graph models and supports inference-efficient TAG learning.
Outcome:	The proposed framework internalizes LLM knowledge within graph models and supports inference-efficient TAG learning.

Copied to clipboard

Zhiwen Xie, Xin Wang, Guangyou Zhou, Derek F. Wong

Can Large Language Models Act as Ensembler for Multi-GNNs? (2025.emnlp-main)

Challenge:	Existing knowledge graph completion methods struggle to capture structural information in knowledge graphs (KGs) Existing approaches for KGC focus on learning representations of entities and relations through observed structural patterns.
Approach:	They propose a multi-layer Aligned Knowledge Injection model that tightly integrates structured KG information into LLMs through multi-layered alignment.
Outcome:	The proposed method outperforms state-of-the-art methods on benchmark datasets.

Copied to clipboard

Hanqi Duan, Yao Cheng, Jianxiang Yu, Yao Liu, Xiang Li

TRUST: Towards Robust Social Bot Detection via Uncertainty-Guided Pseudo-Labeling and Graph Structure Purification (2026.findings-acl)

Challenge:	Existing graph neural networks lack the inherent semantic understanding capability of rich textual attributes, limiting their effectiveness in applications.
Approach:	They propose a model that integrates multiple GNNs and LLMs to provide an ensemble for multi-GNNs.
Outcome:	The proposed model outperforms existing models in terms of semantic understanding of graph structures and graph structures.

Copied to clipboard

Ruixuan Xu, Mengting Hu, Zhunheng Wang, Ming Jiang, Rui Ying, Zhen Zhang, Hang Gao, Shuaipeng Liu, Renhong Cheng

Responsible & Trustworthy NLP

Challenge:	Existing graph-based detection models are vulnerable to deceptive message propagation, where bots deliberately interact with legitimate users.
Approach:	They propose a framework to mitigate deceptive message propagation by node-level uncertainty estimation and graph structure purification.
Outcome:	The proposed framework improves on three benchmark datasets and six GNN backbones on real-world social bots.

A Graph Talks, But Who’s Listening? Rethinking Evaluations for Graph-Language Models (2026.findings-acl)

Copied to clipboard

Soham Petkar, Hari Aakash K, Anirudh Vempati, Akshit Sinha, Ponnurangam Kumaraguru, Chirag Agarwal

Investigating Links between Illicit Massage Businesses through Natural Language Processing and Graph Machine Learning (2026.findings-acl)

Challenge:	Existing benchmarks for Graph-Language Models (GLMs) do not assess true multimodal integration.
Approach:	They propose a benchmark to evaluate multimodal reasoning over graph topology and textual semantics.
Outcome:	The proposed benchmarks show that strong performance is achievable using textual or structural features in isolation, bypassing the need for joint reasoning.

Copied to clipboard

Vasuki Garg, Osman Ozaltin, Maria Mayorga, Sherrie Caltagirone