Papers by Jingwei Zhang

CE-DA: Custom Embedding and Dynamic Aggregation for Zero-Shot Relation Extraction (2025.coling-main)

Challenge:	Recent advances in Relation Extraction (RE) emphasize Zero-Shot methodologies, aiming to recognize unseen relations between entities with no annotated data.
Approach:	They propose a plug-in retrieval adjuster that allows rapid fine-tuning without accessing LLMs’ parameters.
Outcome:	The proposed model demonstrates comparable performance on multiple benchmarks.

Copied to clipboard

Fu Zhang, He Liu, Zehan Li, Jingwei Cheng

RRHF-V: Ranking Responses to Mitigate Hallucinations in Multimodal Large Language Models with Human Feedback (2025.coling-main)

Challenge:	Existing methods to predict relationships with given entity pairs are lacking in supervised methods.
Approach:	They propose a framework for zero-shot Relation Extraction that includes two modules: Custom Embedding and Dynamic Aggregation.
Outcome:	The proposed framework shows competitive performance on two ZSRE datasets.

Copied to clipboard

Guoqing Chen, Fu Zhang, Jinghao Lin, Chenglong Lu, Jingwei Cheng

MultiCMET: A Novel Chinese Benchmark for Understanding Multimodal Metaphor (2023.findings-emnlp)

Challenge:	Existing methods to mitigate hallucinations generate erroneous or fabricated information.
Approach:	They propose a rank-response-based model that annotates pair-reponses and trains alignment algorithms to improve the correspondence between images and text.
Outcome:	The proposed model outperforms the DPO method and outperfies existing methods on two MLLMs of different sizes and four widely used benchmarks.

Copied to clipboard

Dongyu Zhang, Jingwei Yu, Senyuan Jin, Liang Yang, Hongfei Lin

Knowledge-augmented Financial Market Analysis and Report Generation (2024.emnlp-industry)

Challenge:	Existing research on multimodal metaphors does not address categorizing the source and target domains in metaphors beyond the English language.
Approach:	They propose a Cascading Domain Knowledge Integration benchmark to detect metaphors by introducing domain-specific lexical features.
Outcome:	The proposed dataset includes 13,820 text-image pairs of advertisements with manual annotations of the occurrence of metaphors, domain categories, and sentiments metaphors convey.

Copied to clipboard

Yuemin Chen, Feifan Wu, Jingwei Wang, Hao Qian, Ziqi Liu, Zhiqiang Zhang, Jun Zhou, Meng Wang

Probing Relative Interaction and Dynamic Calibration in Multi-modal Entity Alignment (2025.acl-long)

Challenge:	Existing methods to generate financial market analysis text require extensive financial knowledge and skill of financial analysts.
Approach:	They propose a task to generate financial market analysis reports using financial market data using a financial knowledge graph.
Outcome:	The proposed framework outperforms large-scale language models and retrieval-augmented baselines in the financial market analysis generation task.

Copied to clipboard

Chenxiao Li, Jingwei Cheng, Qiang Tong, Fu Zhang, Cairui Wang

SGMEA: Structure-Guided Multimodal Entity Alignment (2025.coling-main)

Challenge:	Current methods for multi-modal entity alignment ignore relative interactions between modalities and the accuracy of weights.
Approach:	They propose a relative interaction and calibration framework for multi-modal entity alignment that uses attention mechanisms to perceive the uncertainty of the weight for each modality.
Outcome:	The proposed framework outperforms baselines across 5 datasets and 23 settings.

Copied to clipboard

Jingwei Cheng, Mingxiao Guo, Fu Zhang

DLTKG: Denoising Logic-based Temporal Knowledge Graph Reasoning (2025.findings-emnlp)

Challenge:	Existing methods focus on interactions between neighboring entities in the structural modality while neglecting interactions between entities in visual and attribute modalities.
Approach:	They propose a structure-guided multimodal entity alignment method which prioritizes structural information from knowledge graphs to enhance the visual and attribute modalities.
Outcome:	The proposed method achieves state-of-the-art performance across multiple datasets, validating its effectiveness and superiority in practical applications.

Copied to clipboard

Xiaoke Wang, Fu Zhang, Jingwei Cheng, Yiwen Chi, Jiashun Peng, Yingsong Ning

Knowledge Representation

Challenge:	Current approaches to temporal knowledge representation face limited generalization to unseen facts and insufficient interpretability of reasoning processes.
Approach:	They propose a framework that uses a denoising diffusion process to complete reasoning tasks . they propose introducing a noise source and historical conditionguiding mechanism to improve interpretability .
Outcome:	The proposed framework outperforms state-of-the-art methods on three benchmark datasets.

DAEA: Enhancing Entity Alignment in Real-World Knowledge Graphs Through Multi-Source Domain Adaptation (2025.coling-main)

Copied to clipboard

Linyan Yang, Shiqiao Zhou, Jingwei Cheng, Fu Zhang, Jizheng Wan, Shuo Wang, Mark Lee

Breaking the Noise Barrier: LLM-Guided Semantic Filtering and Enhancement for Multi-Modal Entity Alignment (2025.emnlp-main)

Challenge:	Entity Alignment (EA) is a critical task in Knowledge Graph (KG) integration.
Approach:	They propose a novel approach that leverages the data characteristics of synthetic benchmarks to improve performance in real-world datasets.
Outcome:	The proposed approach outperforms state-of-the-art models on real-world datasets and achieves a 29.94% improvement in Hits@1 on DOREMUS and 5.64% improvement on AGROLD.

Copied to clipboard

Chenglong Lu, Chenxiao Li, Jingwei Cheng, Yongquan Ji, Guoqing Chen, Fu Zhang

Document-Level Relation Extraction with Global Relations and Entity Pair Reasoning (2025.findings-acl)

Challenge:	Multi-modal entity alignment (MMEA) aims to identify equivalent entities between two multimodal knowledge graphs.
Approach:	They propose a novel LLMguided MMEA framework that prioritizes noise reduction before fusion.
Outcome:	The proposed framework prioritizes noise reduction before fusion and improves semantics on the noisy FB YG dataset.

Copied to clipboard

Fu Zhang, Yi Yan, Jingwei Cheng

Not All Modalities at Once: Dynamic Dropout and Bidirectional Fusion for Robust Multi-modal Knowledge Graph Completion (2026.findings-acl)

Challenge:	Existing document-level relation extraction models focus on individual entity pairs, limiting their ability to handle complex reasoning tasks.
Approach:	They propose a document-level relation extraction framework based on global relations and entity pair reasoning that captures fine-grained interactions between entity pairs.
Outcome:	The proposed framework outperforms existing models on widely-used datasets.

Copied to clipboard

Jiashun Peng, Fu Zhang, Hongzhi Chen, Jingwei Cheng, Yingsong Ning, Xiaoke Wang

ATGL: An Adaptive-Threshold Global Loss for Document-level Relation Extraction (2026.acl-long)

Challenge:	Existing MKGC methods train with all modalities available, implicitly assuming consistent complementarity . however, this often induces modality dependence and modality competition under heterogeneous noise, which can hinder robust multi-modal fusion and limit overall performance.
Approach:	They propose a framework to infer missing links in multimodal knowledge graphs by leveraging structured triples together with auxiliary modalities such as text and images.
Outcome:	The proposed framework outperforms baselines and achieves new state-of-the-art results.

Copied to clipboard

Huangming Xu, Fu Zhang, Zhixuan Yang, Lu Zhang, Jingwei Cheng

SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework (2024.emnlp-main)

Challenge:	Document-level relation extraction (DocRE) aims to determine which relations hold between a given entity pair in a document.
Approach:	They propose a document-level relation extraction paradigm that decouples existing losses into independent positive and negative losses, which interact solely with a shared threshold.
Outcome:	The proposed model outperforms existing models on four datasets and achieves state-of-the-art results.

Copied to clipboard

Fu Zhang, Qi Miao, Jingwei Cheng, Hongsen Yu, Yi Yan, Xin Li, Yongxue Wu

Exploring the Impacts of Feature Fusion Strategy in Multi-modal Entity Alignment (2025.coling-main)

Challenge:	Existing methods for document-level relation extraction ignore bidirectional mention interaction when generating relational features for entity pairs.
Approach:	They propose a document-level relation extraction model that incorporates bidirectional mention fusion and a simple yet effective evidence extraction module for relation prediction.
Outcome:	The proposed model achieves SOTA performance and the proposed method is effective and general when integrated into existing models.

Copied to clipboard

Chenxiao Li, Jingwei Cheng, Qiang Tong, Fu Zhang

NALA: an Effective and Interpretable Entity Alignment Method (2024.findings-emnlp)

Challenge:	Existing approaches to merge multi-modal knowledge only use one fusion strategy . however, the impact of the fusion on individual entities could be ignored .
Approach:	They propose an adaptive multi-modal feature fusion strategy for entity alignment that selects the optimal entity-level feature blending strategy.
Outcome:	The proposed model achieves state-of-the-art (SOTA) performance compared to models using the same modality on a dataset with multiple inconsistent images and styles.

Copied to clipboard

Chuanhao Xu, Jingwei Cheng, Fu Zhang

Zero-shot Jianzi Recognition as Structured Visual Information Extraction in Open Compositional Symbolic Systems (2026.acl-long)

Challenge:	Existing embedding-based EA methods encode entities as embeddables and learn to align embeddibles.
Approach:	They propose to capture three types of logical inference paths with Non-Axiomatic Logic to iteratively align entities and relations by integrating the conclusions of the inference path.
Outcome:	The proposed method outperforms state-of-the-art methods in terms of Hits@1 on all three datasets of DBP15K with both supervised and unsupervised settings.

Copied to clipboard

Zehan Li, Fu Zhang, Zhijun Liu, Jingwei Cheng

SALMON: A Structure-Aware Language Model with logicality and densification strategy for Temporal Knowledge Graph Reasoning (2024.findings-emnlp)

Challenge:	Optical character recognition (OCR) is a relatively new form of tablature recognition, but its accuracy is limited due to its unbounded composition and manuscript-level variability.
Approach:	They propose a method that predicts component sequences under a zero-shot split and synthesize manuscript-like training images via component-wise style recomposition and manuscript-domain noise modeling.
Outcome:	The proposed method achieves 63.02% sequence accuracy on real-world Jianzi benchmark, surpassing Gemini-3-Pro by 35.11%.

Copied to clipboard

Fu Zhang, Jinghao Lin, Jingwei Cheng

Structured Pruning for Large Language Models Using Coupled Components Elimination and Minor Fine-tuning (2024.findings-naacl)

Challenge:	Temporal knowledge graph reasoning (TKGR) is a crucial task that involves reasoning at known timestamps to complete the future facts.
Approach:	They propose a temporal knowledge graph reasoning model with logicality and densification strategy that captures temporal evolving pattern and structural information in TKGs.
Outcome:	The proposed model outperforms the state-of-the-art models and is based on a structure-aware language model with logicality and densification strategy.

Copied to clipboard

Honghe Zhang, XiaolongShi XiaolongShi, Jingwei Sun, Guangzhong Sun

Language Models

Challenge:	Large language models (LLMs) have demonstrated powerful capabilities in natural language processing, yet their vast number of parameters poses challenges for deployment and inference efficiency.
Approach:	They propose a structured pruning algorithm that derives the importance of different components based on intermediate data dependencies and removes coupled components across different layers simultaneously.
Outcome:	The proposed algorithm reduces model size and accelerates inference without specialized operators and libraries, while maintaining its utility as versatile problem solvers.

PresentAgent: Multimodal Agent for Presentation Video Generation (2025.emnlp-demos)

Copied to clipboard

Jingwei Shi, Zeyu Zhang, Biao Wu, Yanjie Liang, Meng Fang, Ling Chen, Yang Zhao

CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations (2025.coling-main)

Challenge:	Existing methods for generating static slides or text summaries are limited to producing narrated presentations.
Approach:	They propose a multimodal agent that transforms long-form documents into narrated presentations.
Outcome:	The present agent produces fully synchronized visual and spoken content that closely mimics human-style presentations.

Copied to clipboard

Jiahao Zhao, Jingwei Zhu, Minghuan Tan, Min Yang, Renhao Li, Yang Di, Chenhao Zhang, Guancheng Ye, Chengming Li, Xiping Hu, Derek F. Wong

Challenge:	CPsyExam prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.
Approach:	They propose a psychological benchmark, CPsyExam, constructed from questions from Chinese examination systems.
Outcome:	The proposed benchmark prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.

An Adaptive Multi-Threshold Loss and a General Framework for Collaborating Losses in Document-Level Relation Extraction (2025.findings-acl)

Copied to clipboard

Huangming Xu, Fu Zhang, Jingwei Cheng

AlignRE: An Encoding and Semantic Alignment Approach for Zero-Shot Relation Extraction (2024.findings-acl)

Challenge:	Document-level relation extraction (DocRE) aims to identify relations for a given entity pair within a document.
Approach:	They propose to partition the label space into different sub-label spaces and learn an adaptive threshold for each sub-labeled space.
Outcome:	The proposed model outperforms single-loss methods on the concurrent application of multiple losses across four datasets.

Copied to clipboard

Zehan Li, Fu Zhang, Jingwei Cheng

EasyEA: Large Language Model is All You Need in Entity Alignment Between Knowledge Graphs (2025.findings-acl)

Challenge:	Existing prototype-based methods for ZSRE ignore abundant side information and suffer from a significant encoding gap between prototypes and sentences.
Approach:	They propose a framework to encode schema alignment to enhance prototype-based ZSRE methods.
Outcome:	The proposed method outperforms existing methods on FewRel and Wiki-ZSL datasets and exhibits substantially faster performance and reduces the need for extensive manual labor in prototype construction.

Copied to clipboard

Jingwei Cheng, Chenglong Lu, Linyan Yang, Guoqing Chen, Fu Zhang

DEBAR: Mitigating Contextual Bias in Cross-Document Relation Extraction via Dual-Stream Decoupling (2026.acl-long)

Challenge:	Entity alignment (EA) aims to identify entities in different knowledge graphs (KGs) that represent the same real-world object.
Approach:	They propose an end-to-end EA framework based on large language models that requires no training to implement.
Outcome:	The proposed framework significantly reduces the reliance on seed entity pairs while achieving state-of-the-art (SOTA) performance on diverse datasets.

Copied to clipboard

Zhixuan Yang, Fu Zhang, Huangming Xu, Jingwei Cheng

CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling (2024.findings-acl)

Challenge:	Existing methods focus on sentence-level or singledocument settings, resulting in one-sided relation transfer contextual bias and incomplete reasoning chains.
Approach:	They propose a framework to explicitly decouple and preserve bidirectional bridge evidence and a dynamic loss optimization objective to separate head and tail contexts.
Outcome:	The proposed framework decouples and preserves bidirectional bridge evidence while capturing global dependencies through iterative message passing.

Copied to clipboard

Chenhao Zhang, Renhao Li, Minghuan Tan, Min Yang, Jingwei Zhu, Di Yang, Jiahao Zhao, Guancheng Ye, Chengming Li, Xiping Hu

Dialogue Systems & Conversational Agents

Challenge:	Existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence.
Approach:	They propose a report-based multi-turn dialogue reconstruction framework for Chinese psychological counseling that uses large language models to assist counseling.
Outcome:	The proposed framework is open-source and can be used in future research.

MWPO: Enhancing LLMs Performance through Multi-Weight Preference Strength and Length Optimization (2025.findings-acl)

Copied to clipboard

Shiyue Xu, Fu Zhang, Jingwei Cheng, Linfeng Zhou

Entity Pair-guided Relation Summarization and Retrieval in LLMs for Document-level Relation Extraction (2025.findings-naacl)

Challenge:	Existing offline alternatives to Reinforcement Learning from Human Feedback (RLHF) are available at https://github.com/AIR-hl/MWPO.
Approach:	They propose an offline method to optimize preference pairs based on implicit reward margins and response length margins by reweighting them using a geometric mixture.
Outcome:	The proposed method outperforms state-of-the-art methods on four different scales and reduces generation length by 9.4%.

Copied to clipboard

Fu Zhang, Hongsen Yu, Jingwei Cheng, Huangming Xu

ATAP: Automatic Template-Augmented Commonsense Knowledge Graph Completion via Pre-Trained Language Models (2024.emnlp-main)

Challenge:	Document-level relation extraction (DocRE) aims to extract relations between entities in a document.
Approach:	They propose an entity pair-guided relation summarization and retrieval model for DocRE . the model uses entity pairs to guide relation summaries and retrievals .
Outcome:	The proposed model achieves state-of-the-art (SOTA) performance on three datasets.

Copied to clipboard

Fu Zhang, Yifan Ding, Jingwei Cheng

SRM-LLM: Semantic Relationship Mining with LLMs for Temporal Knowledge Graph Extrapolation (2025.findings-emnlp)

Challenge:	Commosense knowledge graphs (CKGC) are powerful representations of real-world commonsense knowledge.
Approach:	They propose a framework that uses automatically generated prompt templates combined with pre-trained language models to improve CKGC performance.
Outcome:	The proposed framework mitigates the long-tail problem and improves CKGC performance on a large dataset.

Copied to clipboard

Fu Zhang, Panfeng Zhang, Jingwei Cheng

Structured Data in NLP

Challenge:	Existing methods for temporal knowledge graph extrapolation neglect the complex semantic relationships between relations when modeling their dynamic evolution.
Approach:	They propose a method for extracting semantic relationships to achieve TKG extrapolation . they use large language models to analyze the types of relations in TKGs .
Outcome:	The proposed method improves on five TKG datasets and shows performance gains.

From Local Perspective to Global Reasoning: A Neuro-Symbolic Framework for Zero-Shot Relation Extraction (2026.findings-acl)

Copied to clipboard

Kailun Lyu, Fu Zhang, Zehan Li, Jingwei Cheng

Low-Resource NLP

Challenge:	Existing methods for zero-shot relationship extraction do not distinguish between unseen, semantically similar relations.
Approach:	They propose a framework to enable global reasoning across a set of predictions.
Outcome:	The proposed framework outperforms existing methods and establishes new state-of-the-art results on widely used datasets.

Rethinking the Role of LLMs for Document-level Relation Extraction: a Refiner with Task Distribution and Probability Fusion (2025.naacl-long)

Copied to clipboard

Fu Zhang, Xinlong Jin, Jingwei Cheng, Hongsen Yu, Huangming Xu

Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models (2026.acl-long)

Challenge:	Document-level relation extraction (DocRE) provides a broad context for extracting relations for entities.
Approach:	They propose a method that utilizes LLMs as a refiner and task distribution and probability fusion to refine LLM-based relation extraction methods.
Outcome:	The proposed method outperforms existing LLM-based methods without fine-tuning by 25.2% F1.

Copied to clipboard

Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu, Mubashara Akhtar, Jiaheng Zhang, Elliott Ash, Markus Leippold, Timothy Baldwin, See-Kiong Ng, Artem Shelmanov, Mrinmaya Sachan

Critic Rule Induction: Improving Temporal Knowledge Graph Forecasting with Generator-Critic Language Models (2026.findings-acl)

Challenge:	Existing verification approaches, such as Process Reward Models, are computationally expensive and limited to specific domains.
Approach:	They propose a transformer-based probe that uses internal states of frozen LLMs to estimate credibility of reasoning steps during generation.
Outcome:	The proposed probes match or exceed PRMs that are up to 810 larger.

Copied to clipboard

Yingsong Ning, Fu Zhang, Jingwei Cheng, Jiashun Peng, Xiaoke Wang

Frame First, Then Extract: A Frame-Semantic Reasoning Pipeline for Zero-Shot Relation Triplet Extraction (2025.emnlp-main)

Challenge:	Existing methods for predicting future facts from time-evolving graphs rely on statistical co-occurrences and extensive path enumeration.
Approach:	They propose a Critic-Guided Rule Induction method which treats temporal rules as rule hypotheses to be examined and adopts a decoupled Generation-Discrimination pipeline to induce rules that are high-coverage and high-precision.
Outcome:	The proposed method outperforms strong baselines on three benchmarks and achieves state-of-the-art performance.

Copied to clipboard

Zehan Li, Fu Zhang, Wenqing Zhang, Jiawei Li, Zhou Li, Jingwei Cheng, Tianyue Peng

AI2Agent: An End-to-End Framework for Deploying AI Projects as Autonomous Agents (2025.acl-demo)

Challenge:	Existing methods to extract triplets for unseen relations rely on costly fine-tuning and lack structured semantic guidance.
Approach:	They propose a framework that adopts a "frame first, then extract" paradigm to extract triplets from unstructured text.
Outcome:	The proposed framework achieves competitive zero-shot performance on multiple benchmarks and can be used to enhance existing extraction methods.

Copied to clipboard

Jiaxiang Chen, Jingwei Shi, Lei Gan, Jiale Zhang, Qingyu Zhang, Dongqian Zhang, Pang Xin, Zhucong Li, Xu Yinghui

Capturing Latent Modal Association For Multimodal Entity Alignment (2025.findings-emnlp)

Challenge:	a new framework automates deployment and debugging of AI projects . complexity of environment configurations, dependency conflicts, and debuggering issues hinder scalability and adoption.
Approach:	They propose an end-to-end framework that automates AI project deployment . they conducted experiments on 30 AI deployment cases to evaluate its effectiveness .
Outcome:	The proposed framework reduces deployment time and improves success rates by reducing human intervention.

Copied to clipboard

Yongquan Ji, Jingwei Cheng, Fu Zhang, Chenglong Lu

Representation Learning

Challenge:	Existing methods for multimodal entity alignment overlook the quality of input modality embeddings during modality interaction, amplifying noise propagation while suppressing discriminative feature representations.
Approach:	They propose a model for capturing latent modal association for multimodal entity alignment using a self-attention mechanism to enhance salient information while attenuating noise within individual modality embeddings.
Outcome:	The proposed model achieves an absolute 3.1% higher Hits@1 score than the sota method.

Advancing Cross-Lingual Entity Alignment with Large Language Models: Tailored Sample Segmentation and Zero-Shot Prompts (2024.findings-emnlp)

Copied to clipboard

Linyan Yang, Jingwei Cheng, Fu Zhang

Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Relation Triplet Extraction (2025.coling-main)

Challenge:	Existing approaches to integrate large language models into cross-lingual entity alignment tasks pose challenges in handling large-scale data, generating suitable data samples, and adapting prompts for the EA task.
Approach:	They propose a framework that integrates distance feature extraction, sample Segmentation, and zero-shot prompts to integrate LLMs into cross-lingual entity alignment tasks.
Outcome:	The proposed framework is able to extract features from large-scale data and adapt prompts to the task.

Copied to clipboard

Zehan Li, Fu Zhang, Kailun Lyu, Jingwei Cheng, Tianyue Peng

Low-Resource NLP

Challenge:	Existing methods to extract triplets from context often decompose into named entity recognition and relation classification, which may introduce error propagation.
Approach:	They propose a Relation-centric joint ZSRTE method which leverages unseen relation labels to extract triplets in one go.
Outcome:	The proposed method achieves state-of-the-art performance with fewer parameters and does not rely on synthetic data or manual labor.

ET-MIER: Entity Type-guided Key Mention Identification and Evidence Retrieval for Document-level Relation Extraction (2025.findings-emnlp)

Copied to clipboard

Xin Li, Huangming Xu, Fu Zhang, Jingwei Cheng