Papers by Ning Zhang

Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization (2026.findings-acl)

Challenge:	Existing fashion recommendation systems struggle with the unique challenges of the fashion domain.
Approach:	They propose a sequential fashion recommendation framework that leverages a pre-trained large language model enhanced with recommendation-specific prompts.
Outcome:	The proposed framework significantly improves fashion recommendation performance on Amazon fashion.

Copied to clipboard

Yueyang Cang, Xiaoteng Zhang, Erlu Zhao, Zehua Ji, Yuhang Liu, Yuchen He, Zhiyuan Ning, Chen Yijun, Wenge Que, Li Shi

Word Surprisal Correlates with Sentential Contradiction in LLMs (2026.eacl-long)

Challenge:	Recent approaches to optimize communication topology rely on single-sample policy gradients with absolute rewards.
Approach:	They propose a topology optimization framework that integrates Group Relative Policy Optimization.
Outcome:	The proposed topology optimization framework outperforms state-of-the-art methods on reasoning and code generation benchmarks.

Copied to clipboard

Ning Shi, Bradley Hauer, David Basil, John Zhang, Grzegorz Kondrak

Reasoning

Challenge:	Existing models are primarily optimized for task-specific performance, lacking well-defined objectives or linguistic grounding.
Approach:	They propose a token-to-word decoding algorithm that extends theoretically grounded probability estimation to open-vocabulary settings.
Outcome:	The proposed algorithm can localize sentence-level inconsistency at the word level, establishing a quantitative link between lexical uncertainty and sentential semantics.

Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method (2025.acl-long)

Copied to clipboard

Yupei Ren, Xinyi Zhou, Ning Zhang, Shangqing Zhao, Man Lan, Xiaopeng Bai

Argument Mining

Challenge:	Existing research on argument mining has proposed various argument annotation schemes and tasks.
Approach:	They propose a framework comprising 14 fine-grained relation types to capture the interplay between argument components for a thorough understanding of argument structure.
Outcome:	The proposed framework captures the interplay between argument components for a thorough understanding of argument structure.

GMH: A General Multi-hop Reasoning Model for KG Completion (2021.emnlp-main)

Copied to clipboard

Yao Zhang, Hongru Liang, Adam Jatowt, Wenqiang Lei, Xin Wei, Ning Jiang, Zhenglu Yang

Structured Data in NLP

Challenge:	Knowledge graphs are incomplete with many facts missing, causing performance bottlenecks in many applications.
Approach:	They propose a general multi-hop reasoning task that can be formulated as a search process and can be extended to long-distance reasoning scenarios.
Outcome:	The proposed model improves on baselines in short and long distance reasoning scenarios.

Protecting Language Models Against Unauthorized Distillation through Trace Rewriting (2026.acl-long)

Copied to clipboard

Xinhang Ma, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik

Generating Fluent Adversarial Examples for Natural Languages (P19-1)

Challenge:	Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models.
Approach:	They propose methods for modifying teacher-generated reasoning traces to achieve two objectives that deter unauthorized distillation: (1) anti-distillation, or degrading the training usefulness of query responses; and (2) API watermarking, which embeds verifiable signatures in student models.
Outcome:	The proposed method achieves strong anti-distillation effect while maintaining or even improving teacher performance.

Copied to clipboard

Huangzhao Zhang, Hao Zhou, Ning Miao, Lei Li

Robustness in NLP

Challenge:	Current methods for building adversarial attackers for NLP are inefficient as the gradient is discarded.
Approach:	They propose an adversarial attacker which performs Metropolis-Hastings sampling with the guidance of gradients to solve these problems.
Outcome:	The proposed algorithm outperforms the baseline model on attacking capability on IMDB and SNLI.

ClusterAttn: KV Cache Compression under Intrinsic Attention Clustering (2025.acl-long)

Copied to clipboard

Minwei Zhang, Haifeng Sun, Jingyu Wang, Shaolong Li, Wanyi Ning, Qi Qi, Zirui Zhuang, Jianxin Liao

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

Challenge:	Existing methods for sparse attention apply the same pattern across different attention heads and inputs, but fail to capture the intrinsic attention clustering in large language models.
Approach:	They propose a training-free sparse attention method that provides an efficient prompt cache compression scheme under intrinsic attention clustering for efficient LLM inference.
Outcome:	The proposed method reduces memory usage by 10%–65% and increases throughput by 2.6–4.8 times with no accuracy loss.

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.

Selected Languages are All You Need for Cross-lingual Truthfulness Transfer (2025.coling-main)

Copied to clipboard

Weihao Liu, Ning Wu, Wenbiao Ding, Shining Liang, Ming Gong, Dongmei Zhang

Multilinguality

Challenge:	Existing methods for truthfulness enhancement in English are limited to multilingual scenarios.
Approach:	They propose a method for cross-lingual truthfulness transfer that uses language bias and transfer contributions to select an optimal subset of all tested languages and employ translation instruction tuning for cross language truthfulness transfers.
Outcome:	The proposed method reduces multilingual representation disparity and boosts cross-lingual truthfulness transfer of LLMs.

Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension (2022.acl-long)

Copied to clipboard

Huibin Zhang, Zhengkun Zhang, Yao Zhang, Jun Wang, Yufan Li, Ning Jiang, Xin Wei, Zhenglu Yang

CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following (2024.acl-long)

Challenge:	Procedural Multimodal Documents organize textual instructions and corresponding images step by step.
Approach:	They propose a novel temporal-modal entity Graph for comprehending PMDs . they propose encoding and reasoning modules to capture textual and visual entities .
Outcome:	The proposed model can capture textual and visual entities and trace their temporal-modal evolution.

Copied to clipboard

Kaiyan Zhang, Jianyu Wang, Ermo Hua, Biqing Qi, Ning Ding, Bowen Zhou

LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring (2026.acl-long)

Challenge:	Large-scale language models (LLMs) are increasingly exposed to private data and are becoming more and more prevalent.
Approach:	They propose a collaborative generation framework that integrates large and small language models to address privacy concerns logically.
Outcome:	The proposed framework combines large and small models to address privacy concerns logically.

Copied to clipboard

Ning Li, Zheng Zhang, Zhenya Huang, Rui Li, Yi Zhan, Yinbo Luo, Qi Liu, Enhong Chen

Counterfactual Adversarial Learning with Representation Interpolation (2021.findings-emnlp)

Challenge:	Existing evaluations focus on isolated, short-term interactions, overlooking the inherently long-term nature of learning.
Approach:	They propose a benchmark for long-term personalized tutoring based on an annotated learning log . they propose an automated generator–verifier pipeline to enable benchmark expansion .
Outcome:	The proposed benchmarks evaluate LLMs across three progressive tasks: evidence acquisition, knowledge state diagnosis, and adaptive teaching action.

Copied to clipboard

Wei Wang, Boxin Wang, Ning Shi, Jinfeng Li, Bingyu Zhu, Xiangyu Liu, Rong Zhang

Robustness in NLP

Challenge:	Existing models with statistical bias are prone to memorized correlations . large pre-trained models such as BERT have revolutionized the model development paradigm in natural language processing .
Approach:	They propose a framework to tackle the problem from a causal perspective using a latent space interpolation approach.
Outcome:	Extensive experiments show that CAT achieves substantial performance improvement over SOTA across different downstream tasks, including sentence classification, natural language inference and question answering.

PM2F2N: Patient Multi-view Multi-modal Feature Fusion Networks for Clinical Outcome Prediction (2022.findings-emnlp)

Copied to clipboard

Ying Zhang, Baohang Zhou, Kehui Song, Xuhui Sui, Guoqing Zhao, Ning Jiang, Xiaojie Yuan

OpenDelta: A Plug-and-play Library for Parameter-efficient Adaptation of Pre-trained Models (2023.acl-demo)

Challenge:	Existing methods focused on time series data but ignored clinical notes . fusion of multi-modal features of patients from different views is not feasible due to the time series and clinical notes data being stored as time series.
Approach:	They propose to combine time series and clinical notes to fuse multi-modal features of patients from different perspectives using graph neural networks.
Outcome:	The proposed method is superior to existing models on MIMIC-III benchmark.

Copied to clipboard

Shengding Hu, Ning Ding, Weilin Zhao, Xingtai Lv, Zhen Zhang, Zhiyuan Liu, Maosong Sun

Recurrent Inference in Text Editing (2020.findings-emnlp)

Challenge:	Existing implementations that modify the code of the backbone PTMs and hard-code specific delta tuning methods for each PTM have limited the practicality and flexibility of delta tuning.
Approach:	They propose an open-source library that provides a plug-and-play implementation of delta tuning methods for pre-trained models.
Outcome:	The proposed methods eliminate the need to modify the backbone PTMs’ code, making OpenDelta compatible with different, even novel PTM.

Copied to clipboard

Ning Shi, Ziheng Zeng, Haotian Zhang, Yichen Gong

Challenge:	Existing inference methods map the unedited text to the edited text or to the editing operations, but performance is degraded by the limited source text encoding and long, varying decoding steps.
Approach:	They propose a new inference method that iteratively performs editing actions . they introduce three types of editing tasks: AOR, AES, AEC .
Outcome:	The proposed method significantly narrows the problem space by iterating editing actions.

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models (2025.findings-acl)

Copied to clipboard

Huangyw Huangyw, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, Jing Xiao

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

Challenge:	Existing methods, such as a n-terminal coding, do not provide accurate data for large language models.
Approach:	They propose a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding.
Outcome:	Experiments on open-book QA datasets show that DAGCD improves faithfulness and robustness while preserving computational efficiency.

Copied to clipboard

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

EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models (2025.emnlp-main)

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

Han Liu, Ruoyao Wen, Srijith Nair, Jia Liu, Wenjing Lou, Chongjie Zhang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang

Query-Aware Graph Attention for Precise Subgraph Retrieval in Knowledge-Augmented Reasoning (2026.findings-acl)

Challenge:	Recurrent exchange of model updates in FL can result in prohibitively high communication costs, hindering the distributed learning process.
Approach:	They propose a federated fine-tuning framework that uses a round-robin segment sharing scheme to reduce network bandwidth and adaptive sparsification methods tailored to LoRA’s training dynamics.
Outcome:	The proposed framework reduces communication overhead without compromising performance on question-answering and value-alignment tasks.

Copied to clipboard

Yuanye Xu, Linyi Guo, Yue Zhang, Fu Ning

Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation (2026.acl-long)

Challenge:	Existing Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) systems insufficiently model the interaction between query semantics and relation types, resulting in imprecise subgraph retrieval and unstable reasoning.
Approach:	They propose a retrieval framework that integrates query semantics and relation embeddings directly into the attention mechanism.
Outcome:	Experiments on WebQSP and CWQ establish new state-of-the-art results in both Triple Recall and Answer Recall.

Copied to clipboard

Ning Wang, Zhanyang Liu, Taotao Zhou, Xinrui Zhang, Zongru Shao, Haojie Zhou

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data (2026.acl-long)

Challenge:	Existing approaches to align LLMs with diverse human values rely on ground-truth scores . existing approaches implicitly approximate an average-user preference, thereby failing to capture heterogeneity of human values or accommodate conflicting user needs.
Approach:	They propose a framework that transforms passive reward dependency into an intrinsic adaptive sensing capability.
Outcome:	The proposed framework outperforms state-of-the-art models in multiple model scales and improves preference alignment.

Copied to clipboard

Shiping Yang, Jie Wu, Wenbiao Ding, Ning Wu, Shining Liang, Ming Gong, Hongzhi Li, Hengyuan Zhang, Angel X. Chang, Dongmei Zhang

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring (2026.acl-long)

Challenge:	Existing studies on robustness to explicit noise (e.g., document semantics) but overlook implicit noise (spurious features).
Approach:	They propose a framework to quantify the robustness of RAGs against spurious features by integrating a data synthesis pipeline and a taxonomy.
Outcome:	The proposed framework quantifies the robustness of RALMs against spurious features.

Copied to clipboard

Peichun Hua, Hao Li, Shanghao Shi, Zhiyuan Yu, Ning Zhang

SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue (2026.findings-acl)

Challenge:	Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating a generalizable defense that is efficient for practical deployment.
Approach:	They propose a framework that uses a lightweight projection to separate benign and malicious inputs in safety-critical layers.
Outcome:	The proposed framework enables a simple yet powerful contrastive score that differentiates true malicious intent from mere distribution shift.

Copied to clipboard

Yuqin Dai, Ning Gao, Wei Zhang, Jie Wang, null Luozichen, Ruiyuan Wu, Jinpeng Wang, Chaozheng Wang

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models have demonstrated remarkable capabilities in open-domain dialogues, but their performance in service dialogues remains suboptimal.
Approach:	They propose a framework that enables agents to learn effective strategies without large-scale human annotations.
Outcome:	The proposed framework decouples user modeling into two components that provide adaptive training scenarios rather than acting as an unfair adversary.

S2O: Early Stopping for Sparse Attention via Online Permutation (2026.acl-long)

Copied to clipboard

Yu Zhang, Songwei Liu, Chenqian Yan, null Linsheng, Beichen Ning, Fangmin Chen, Xing Wang

Challenge:	Existing block-granularity sparsification can reduce latency, but coarse blocks impose an intrinsic sparsity ceiling.
Approach:	They propose a method that performs early stopping for sparse attention via online permutation.
Outcome:	The proposed approach reduces the complexity of the model and its performance.

Event-Centric Natural Language Processing (2021.acl-tutorials)

Copied to clipboard

Muhao Chen, Hongming Zhang, Qiang Ning, Manling Li, Heng Ji, Kathleen McKeown, Dan Roth

Challenge:	This tutorial will provide an introduction to various methods for automating the extraction, conceptualization and prediction of events and their relations.
Approach:	This tutorial will provide an introduction to various methods for automating events and their relations, and a wide range of NLU and commonsense understanding tasks.
Outcome:	This tutorial will provide an introduction to various methods for automating extraction, conceptualization and prediction of events and their relations, and a wide range of NLU and commonsense understanding tasks.

LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)

Copied to clipboard

Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time (2025.emnlp-main)

Challenge:	LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases .
Approach:	They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website .
Outcome:	The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks.

Copied to clipboard

Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang

Fusing Highly Specialized Language Models for Comprehensive Expertise (2025.acl-long)

Challenge:	Existing monotonic scaling methods for large reasoning models are not reliable.
Approach:	They propose a universal framework for modulating reasoning progress in large reasoning models at test time.
Outcome:	The proposed framework unifies and generalizes existing monotonic scaling methods and enables flexible and dense slow-to-fast reasoning modulation.

Copied to clipboard

Ning Ding, Yulin Chen, Ganqu Cui, Xingtai Lv, Weilin Zhao, Kaiyan Zhang, Ruobing Xie, Bowen Zhou, Zhiyuan Liu, Maosong Sun

Extracting Temporal Event Relation with Syntax-guided Graph Transformer (2022.findings-naacl)

Challenge:	Existing models that focus on language, programming code, and mathematical symbols are not able to achieve mastery of all three domains simultaneously.
Approach:	They propose to fuse highly-specialized models that are already sufficiently trained on different domains to achieve a highly-specific model.
Outcome:	The proposed model could achieve mastery of the three crucial domains simultaneously.

Copied to clipboard

Shuaicheng Zhang, Qiang Ning, Lifu Huang

Open Domain Question Answering with Conflicting Contexts (2025.findings-naacl)

Challenge:	Temporal relationship extraction is crucial for understanding complex events and reasoning over them.
Approach:	They propose a Syntax-guided Graph Transformer network to extract temporal relations between events by explicitly exploiting the connection between two events based on their dependency parsing trees.
Outcome:	The proposed approach outperforms state-of-the-art methods on MATRES and TB-DENSE with up to 7.9% absolute F-score gain.

Copied to clipboard

Siyi Liu, Qiang Ning, Kishaloy Halder, Zheng Qi, Wei Xiao, Phu Mon Htut, Yi Zhang, Neha Anna John, Bonan Min, Yassine Benajiba, Dan Roth

Natural Language Interfaces

Challenge:	Open domain question answering systems often rely on information retrieved from large collections of text to answer questions.
Approach:	They evaluate and benchmark three powerful Large Language Models with a dataset . they find that 25% of unambiguous open domain questions can lead to conflicting contexts .
Outcome:	The proposed model can't be used to answer questions with conflicting contexts . it can be fine tuned to provide richer information into the model's training .

Don’t Trust ChatGPT when your Question is not in English: A Study of Multilingual Abilities and Types of LLMs (2023.emnlp-main)

Copied to clipboard

Xiang Zhang, Senyu Li, Bradley Hauer, Ning Shi, Grzegorz Kondrak

Multilinguality

Challenge:	Existing studies have shown that large language models can perform a wide variety of language tasks when presented in English.
Approach:	They propose a method to evaluate the multilingual capabilities of large language models using a prompt back-translation method to find out how LLMs acquire their multilingual abilities.
Outcome:	The proposed method shows that large language models can transfer learned knowledge across different languages, but struggle to provide accurate results in translation-variant tasks.

Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process (2025.acl-long)

Copied to clipboard

Ermo Hua, Biqing Qi, Kaiyan Zhang, Kai Tian, Xingtai Lv, Ning Ding, Bowen Zhou

Hierarchy-Aware Global Model for Hierarchical Text Classification (2020.acl-main)

Challenge:	Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models with human preferences post pre-training.
Approach:	They propose to combine Supervised Fine-Tuning and Preference Optimization (PO) with two sub-processes defined at token level within the Markov Decision Process (MDP)
Outcome:	The proposed process performs comparably or even superiorly to SFT and some typical PO methods across several tasks, particularly those requires generation, reasoning, and fact-following abilities.

Copied to clipboard

Jie Zhou, Chunping Ma, Dingkun Long, Guangwei Xu, Ning Ding, Haoyu Zhang, Pengjun Xie, Gongshen Liu

Information Extraction & Text Mining

Challenge:	Existing methods for hierarchical text classification are limited and lack holistic structural information.
Approach:	They propose a hierarchy-aware global model with two variants that learn hierarchy-based label embeddings through an encoder and conduct inductive fusion of label-alike text features.
Outcome:	The proposed model improves on three benchmark datasets.

iAgent: LLM Agent as a Shield between User and Recommender Systems (2025.findings-acl)

Copied to clipboard

Wujiang Xu, Yunxiao Shi, Zujie Liang, Xuying Ning, Kai Mei, Kun Wang, Xi Zhu, Min Xu, Yongfeng Zhang

Challenge:	Traditional recommender systems focus on the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms.
Approach:	They propose a user-agent-platform paradigm where agent serves as the protective shield between user and recommender system that enables indirect exposure.
Outcome:	The proposed model improves 16.6% over baselines on four datasets and mitigates echo chamber effects and reduces model bias in disadvantaged users.

Test of Time: Rethinking Temporal Signal of Benchmark Contamination (2026.acl-long)

Copied to clipboard

Terry Jingchen Zhang, Gopal Dev, Ning Wang, Max Obreiter, Punya Syon Pandey, Keenan Samway, Wenyuan Jiang, Yinya Huang, Bernhard Schölkopf, Mrinmaya Sachan, Zhijing Jin

Challenge:	Existing work on benchmarks containing publicly available information has been interpreted as a temporal signal for benchmark contamination.
Approach:	They show that LLM-transformed questions can produce remarkably different temporal patterns compared to fill-in-the-blank questions directly retrieved from the very same documents.
Outcome:	The proposed model can produce different temporal patterns compared to fill-in-the-blank questions retrieved from the same documents.

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning (2024.naacl-long)

Copied to clipboard

Ming Li, Yong Zhang, Zhitao Li, Jiuhai Chen, Lichang Chen, Ning Cheng, Jianzong Wang, Tianyi Zhou, Jing Xiao

MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have revolutionized the landscape of artificial intelligence.
Approach:	They propose a self-guided method to identify and select cherry samples from open-source datasets, minimizing manual curation and potential cost for instruction tuning an LLM.
Outcome:	The proposed method enables LLMs to identify discrepancies between expected responses and intrinsic generation capability, and a marked uptick in model training efficiency.

Copied to clipboard

Yu Zhao, Xiangrui Cai, Yike Wu, Haiwei Zhang, Ying Zhang, Guoqing Zhao, Ning Jiang

LLM-Driven Implicit Target Augmentation and Fine-Grained Contextual Modeling for Zero-Shot and Few-Shot Stance Detection (2025.emnlp-main)

Challenge:	Existing methods to predict missing entities share relation representation across modalities, which results in mutual interference between modality.
Approach:	They propose a framework for multimodal knowledge graph completion that learns modality-split relation embeddings for each modality instead of a single modality shared one.
Outcome:	The proposed framework outperforms state-of-the-art methods on three KG datasets.

Copied to clipboard

Yanxu Ji, Jinzhong Ning, Yijia Zhang, Zhi Liu, Hongfei Lin

Sentiment Analysis

Challenge:	Recent studies on zero-shot and few-shot stance detection neglect implicit yet semantically important targets.
Approach:	They propose a framework that uses Large Language Models to annotate implicit targets . they also propose 'DyMCA' to dynamically adjust text-target contributions based on context .
Outcome:	The proposed framework achieves state-of-the-art on a benchmark dataset.

GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis (2026.findings-acl)

Copied to clipboard

Shaoting Tan, Ning Liu, Yuntao Du, Shuyue Wei, Wu Shuai, Qian Li, Yanyu Xu, Wei Zhang, Lizhen Cui, Haitao Yuan

Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention (2024.emnlp-main)

Challenge:	Existing Large Language Models struggle to reason systematically under cost constraints . Existing approaches lack the knowledge-reasoning capability to reason under cost .
Approach:	They propose a knowledge-enhanced framework that leverages large language models to construct MDKGs . they propose three collaborative agents that handle language understanding and generation .
Outcome:	GraphDx improves diagnostic success rates from 50–68% to 79–93% while reducing test costs by 20–54%.

Copied to clipboard

Xingtai Lv, Ning Ding, Kaiyan Zhang, Ermo Hua, Ganqu Cui, Bowen Zhou

An Intent-based and Annotation-free Method for Duplicate Question Detection in CQA Forums (2023.findings-emnlp)

Challenge:	Existing studies have found that low-rank pre-training often compromises effectiveness.
Approach:	They propose to apply low-dimensional module only to the attention layer to improve both effectiveness and efficiency.
Outcome:	The proposed model saves 12.4% time while improving test perplexity and on downstream tasks compared with vanilla Transformer.

Copied to clipboard

Yubo Shu, Hansu Gu, Peng Zhang, Tun Lu, Ning Gu

Natural Language Interfaces

Challenge:	Existing methods for detecting duplicate questions in CQA rely on generic text-pair matching models, overlooking the intent behind the questions.
Approach:	They propose a new intent-based duplication detector that leverages intent information to address the problem of duplicate question detection in CQA.
Outcome:	The proposed detector leverages the characteristics of CQA forums and extracts training labels to recognize and match intents without human annotation.

E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition (2026.findings-acl)

Copied to clipboard

Meng Zhang, Jinzhong Ning, Xiaolong Wu, Hongfei Lin, Yijia Zhang

PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter (2023.emnlp-main)

Challenge:	Existing approaches decouple textual entity recognition and visual grounding, leading to error accumulation and suboptimal joint optimization.
Approach:	They propose a fully end-to-end generative framework that unifies recognition, semantic typing, visual grounding and implicit knowledge reasoning within a single multimodal large language model.
Outcome:	The proposed framework achieves highly competitive performance compared with state-of-the-art methods.

Copied to clipboard

Haoyan Yang, Zhitao Li, Yong Zhang, Jianzong Wang, Ning Cheng, Ming Li, Jing Xiao

Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)

Challenge:	Large Language Models (LLMs) are too large to be fine-tuned with budget constraints and some are only accessible via APIs.
Approach:	They propose a pluggable Reward-Driven Contextual Adapter that integrates large language models as generators and trains them to refine the retrieved information.
Outcome:	The proposed method improves ReQA performance on three datasets by up to 20% compared to existing methods.

Copied to clipboard

Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao

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

Challenge:	Existing training data detectors fail to detect clean samples from contaminated test sets . existing methods fail to identify clean samples due to black-box nature of LLMs .
Approach:	They propose a framework that detects and filters contaminated evaluation data . they propose 'failure detection' to reduce the proportion of contaminated samples mistakenly retained .
Outcome:	The proposed framework reduces false discovery rate (FDR) under valid FDR control while maintaining evaluation consistency.

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.

Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models (2026.findings-acl)

Copied to clipboard

Kainan Liu, Yong Zhang, Ning Cheng, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao

V-GameGym: Visual Game Generation for Code Large Language Models (2026.findings-acl)

Challenge:	Existing methods for fine-tuning pre-trained models are limited due to suboptimal activation subspaces.
Approach:	They propose a method that leverages tail eigenvectors of model output activations to construct low-rank adapters.
Outcome:	The proposed method outperforms existing methods across 16 benchmarks and surpasses full fine-tuning in certain scenarios.

Copied to clipboard

Wei Zhang, Jian Yang, Renshuai Tao, Linzheng Chai, Shuyue Guo, Jiajun Wu, Xiaoming Chen, Ganqu Cui, Ning Ding, Xander Xu, HU Wei, Bowen Zhou

Enhancing Learning-Based Binary Code Similarity Detection Model through Adversarial Training with Multiple Function Variants (2024.findings-emnlp)

Challenge:	Existing code-related benchmarks focus on single modality rather than visual game development.
Approach:	They propose a multimodal benchmark for evaluating code large language models in visual game generation that integrates a clustering-based curation methodology and a pipeline for visual code synthesis.
Outcome:	The proposed framework assesses code generation and visual game generation using a sandbox environment.

Copied to clipboard

Lichen Jia, Chenggang Wu, Bowen Tang, Peihua Zhang, Zihan Jiang, Yang Yang, Ning Liu, Jingfeng Zhang, Zhe Wang

MIO: A Foundation Model on Multimodal Tokens (2025.emnlp-main)

Challenge:	Existing Learning-Based Binary Code Similarity Detection (LB-BCSD) methods exhibit lower accuracy in recognizing functions with the same functionality but different implementations.
Approach:	They propose a gradient-guided adversarial attack method based on critical code called FuncFooler which perturbs critical code to generate multiple variants of the same function.
Outcome:	The proposed method increases the accuracy of the current Learning-Based Binary Code Similarity Detection (LB-BCSD) model by 5%-7%.

Copied to clipboard

Zekun Moore Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jessie Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang

JX4MEI: Multimodal Semantically-Enhanced LLM for Joint Multimodal Emotion-Intent Explanation and Classification (2026.findings-acl)

Challenge:	Existing models lack multimodal understanding capabilities, resulting in closed-source model that does not support multimodal interleaved sequences.
Approach:	They propose a foundation model built on multimodal tokens capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
Outcome:	The proposed model is able to understand speech, text, images, and videos in an end-to-end, autoregressive manner.

Copied to clipboard

YiJie Huang, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Ning Yuan, Zhuoyue Jia, Wen Zhang

Information Retrieval

Challenge:	Existing multimodal emotion and intent recognition tasks focus on classification, not rationale and intrinsic connections between these states.
Approach:	They propose a task that requires models to jointly predict emotion and intent while generating natural language explanations for why they co-occur.
Outcome:	The proposed model outperforms baseline models in prediction and explanation generation.

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization (2024.findings-emnlp)

Copied to clipboard

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu, Zheng Liu, Tun Lu, Xing Xie, Ning Gu

Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning (2024.acl-long)

Challenge:	Existing methods to steer LLMs towards human preference suffer from noisy positive-negative training pairs.
Approach:	They propose a distributional preference optimization method which maximizes discrepancy between dispreferred responses and generated non-negative ones.
Outcome:	The proposed method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence.

Copied to clipboard

Ming Li, Yong Zhang, Shwai He, Zhitao Li, Hongyu Zhao, Jianzong Wang, Ning Cheng, Tianyi Zhou

FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning (2022.emnlp-main)

Challenge:	Earlier studies of instruction tuning on Large Language Models focus on creating large, varied, and high-quality datasets with responses curated by human experts.
Approach:	They propose to use a smaller and weaker model to fine tune a larger and stronger model . they find it can largely speed up the data filtering and improve performance .
Outcome:	The proposed model can filter instruction data faster and better on benchmarks.

Copied to clipboard

Suvir Mirchandani, Licheng Yu, Mengjiao Wang, Animesh Sinha, Wenwen Jiang, Tao Xiang, Ning Zhang

Challenges to Open-Domain Constituency Parsing (2022.findings-acl)

Challenge:	Prior work on multimodal fashion tasks has been limited by the data in individual benchmarks or has leveraged generic vision-and-language pre-training but have not taken advantage of the characteristics of fashion data.
Approach:	They propose a fashion-specific pre-training framework based on weakly-supervised triplets constructed from fashion image-text pairs.
Outcome:	The proposed framework is based on weakly-supervised triplets constructed from fashion image-text pairs and is competitive on a diverse set of fashion tasks.

Copied to clipboard

Sen Yang, Leyang Cui, Ruoxi Ning, Di Wu, Yue Zhang

Challenge:	Existing findings on cross-domain constituency parsing are only made on a limited number of domains.
Approach:	They manually annotate a high-quality constituency treebank containing five domains and analyze challenges to open-domain constituency parsing using a set of linguistic features.
Outcome:	The proposed model significantly improves the performance of the proposed model on the domain-variant features.

Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances (2022.coling-1)

Copied to clipboard

Yike Wu, Yu Zhao, Shiwan Zhao, Ying Zhang, Xiaojie Yuan, Guoqing Zhao, Ning Jiang

Visual Data in NLP

Challenge:	Existing VQA models rely on the superficial correlation between question type and frequent answers to make predictions, without really understanding the input.
Approach:	They propose a training framework that explicitly encourages the VQA model to distinguish between superficially similar instances.
Outcome:	The proposed framework achieves state-of-the-art performance on VQA-CP v2 . it explicitly encourages the model to distinguish between the superficially similar instances .

Evaluating Models’ Local Decision Boundaries via Contrast Sets (2020.findings-emnlp)

Copied to clipboard

Matt Gardner, Yoav Artzi, Victoria Basmov, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, Ananth Gottumukkala, Nitish Gupta, Hannaneh Hajishirzi, Gabriel Ilharco, Daniel Khashabi, Kevin Lin, Jiangming Liu, Nelson F. Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, Noah A. Smith, Sanjay Subramanian, Reut Tsarfaty, Eric Wallace, Ally Zhang, Ben Zhou

Challenge:	Standard test sets for supervised learning evaluate in-distribution generalization but are misleading when a dataset has systematic gaps.
Approach:	They propose a more rigorous annotation paradigm for NLP that helps to close systematic gaps in the test data.
Outcome:	The proposed model performs significantly lower on contrast sets than on the original test sets—up to 25% in some cases.

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)

Copied to clipboard

Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou

Multilinguality

Challenge:	XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios .
Approach:	They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora.
Outcome:	The proposed dataset is labeled in English and includes only natural language understanding tasks.

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring (2026.acl-long)

Copied to clipboard

Dongxu Zhang, Yiding Sun, Cheng Tan, Wenbiao Yan, Ning Yang, Jihua Zhu, Haijun Zhang

AutoFigure-Edit: Generating Editable Scientific Illustrations via Reference-Guided Styling (2026.acl-demo)

Challenge:	Existing efforts to mitigate this via token compression fail due to its autoregressive nature . linguistically redundant tokens are erroneously pruned, leading to hallucinations .
Approach:	They propose a method that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem.
Outcome:	Experiments on Qwen2-VL and Llama-3.2 families show that the proposed model achieves a speedup with negligible accuracy loss.

Copied to clipboard

Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li, QiYao Sun, Enhao Gu, Yiran Ding, Ke Sun, Fang Guo, Panzhong Lu, Zhiyuan Ning, Yixuan Weng, Yue Zhang

Green & Sustainable NLP

Challenge:	Existing automated systems for scientific illustrations are limited in editability, stylistic controllability, and efficiency.
Approach:	They propose an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images.
Outcome:	The proposed system generates fully editable scientific illustrations from long-form scientific texts while enabling flexible style adaptation through user-provided reference images.

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models (2025.emnlp-industry)

Copied to clipboard

Yi Shen, Jian Zhang, Jieyun Huang, Shuming Shi, Wenjing Zhang, Jiangze Yan, Ning Wang, Kai Wang, Zhaoxiang Liu, Shiguo Lian

Green & Sustainable NLP

Challenge:	Recent advances in slow-thinking reasoning models have shown exceptional performance in complex reasoning tasks.
Approach:	They propose a framework that enables models to automatically adjust Chain-of-Thought (CoT) length based on problem difficulty.
Outcome:	The proposed framework penalizes inefficiency on simple problems while incentivizing deep reasoning for complex ones.

GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression (2025.emnlp-main)

Copied to clipboard

Kainan Liu, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, Jing Xiao

Green & Sustainable NLP

Challenge:	Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing these layers to reduce inference cost.
Approach:	They propose a framework that removes redundant layers to reduce inference cost by preserving sensitivity-aware singular values.
Outcome:	The proposed framework outperforms existing methods in 90% of the original model under a 20% compression ratio.

Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions (2023.tacl-1)

Copied to clipboard

Zhihan Zhang, Wenhao Yu, Zheng Ning, Mingxuan Ju, Meng Jiang

Natural Language Interfaces

Challenge:	Existing studies on the ability of a model to make consistently correct predictions in the presence of perturbations have not been conducted in open-domain question answering (OpenQA).
Approach:	They propose a query-side contrastive loss to improve the dense passage retriever (DPR) to improve DPR training.
Outcome:	The proposed approach improves the density of the dense passage retriever (DPR) training set without sacrificing accuracy on standard test sets.

Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations (2024.findings-emnlp)

Copied to clipboard

Nuo Chen, Zinan Zheng, Ning Wu, Ming Gong, Dongmei Zhang, Jia Li

Reasoning

Challenge:	Existing research focuses on developing powerful large language models for mathematical reasoning within monolingual languages.
Approach:	They propose to use translation to build powerful multilingual math reasoning models . they propose different training strategies to build xMR LLMs that outperform open-source LLM .
Outcome:	The proposed model outperforms open-source LLMs and surpasses ChatGPT in few-shot scenarios.

RoChBert: Towards Robust BERT Fine-tuning for Chinese (2022.findings-emnlp)

Copied to clipboard

Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

Visual Attention Model for Name Tagging in Multimodal Social Media (P18-1)

Challenge:	Pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts.
Approach:	They propose to fuse Chinese phonetic and glyph features into pre-trained models by using a more comprehensive adversarial graph.
Outcome:	The proposed framework outperforms existing methods in significant ways on a wide range of tasks while remaining accurate on benign texts.

Copied to clipboard

Di Lu, Leonardo Neves, Vitor Carvalho, Ning Zhang, Heng Ji

PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free (2025.acl-long)

Challenge:	Name tagging is a key task for language understanding, but is often limited by the short textual components.
Approach:	They propose a novel model architecture based on visual attention that outperforms other methods . they use multimodal datasets to analyze the name tagging task on social media .
Outcome:	The proposed model outperforms existing methods and significantly outperformed existing methods.

Copied to clipboard

Hao Li, Xiaogeng Liu, Ning Zhang, Chaowei Xiao

Bridging the Gap Between BabelNet and HowNet: Unsupervised Sense Alignment and Sememe Prediction (2023.eacl-main)

Challenge:	Prompt injection attacks pose a critical threat to large language models, enabling goal hijacking and data leakage.
Approach:	They propose a prompt guard model that incorporates a new training strategy to mitigate over-defense for free . PIGuard significantly reduces the bias on trigger words, enabling fine-grained evaluation .
Outcome:	The proposed model outperforms the existing model on diverse benchmarks by 30.4%.

Copied to clipboard

Xiang Zhang, Ning Shi, Bradley Hauer, Grzegorz Kondrak

AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists (2025.emnlp-main)

Challenge:	Sememes are the minimum semantic units of natural languages, but their use is limited by a lack of available sememe knowledge bases.
Approach:	They propose to use sense alignment to connect BabelNet with HowNet by relaxing constraints until a complete alignment is achieved.
Outcome:	The proposed method improves on previous supervised methods by 12% . it is based on interpretable propagation of sememe information between lexical resources .

Copied to clipboard

Yifei Li, Hanane Nour Moussa, Ziru Chen, Shijie Chen, Botao Yu, Mingyi Xue, Benjamin Burns, Tzu-Yao Chiu, Vishal Dey, Zitong Lu, Chen Wei, Qianheng Zhang, Tianyu Zhang, Song Gao, Xuhui Huang, Xia Ning, Nesreen K. Ahmed, Ali Payani, Huan Sun

CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model (2023.emnlp-main)

Challenge:	AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery.
Approach:	They propose an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows.
Outcome:	The proposed pipeline synthesizes accurate tasks and tasks from a dataset of 5,404 tasks covering four scientific disciplines and 756 Python packages.

Copied to clipboard

Kaiyan Zhang, Ning Ding, Biqing Qi, Xuekai Zhu, Xinwei Long, Bowen Zhou

Foreseeing the Benefits of Incidental Supervision (2021.emnlp-main)

Challenge:	Instruction tuning is an effective way of aligning large language models with private instruction data.
Approach:	They propose a training-free strategy to derive improved emulators from LLMs by using Offsite-Tuning (OFT) they propose CRaSh, which transfers transformer blocks between centralized LLM and downstream emulators .
Outcome:	The proposed technique boosts performance of large language models with billions of parameters.

Copied to clipboard

Hangfeng He, Mingyuan Zhang, Qiang Ning, Dan Roth

Challenge:	Real-world applications often require improved models by leveraging a range of cheap incidental supervision signals.
Approach:	They propose a unified PAC-Bayesian motivated informativeness measure that characterizes the uncertainty reduction provided by incidental supervision signals.
Outcome:	The proposed measure quantifies the value added by incidental supervision signals to sequence tagging tasks.

WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning (2024.acl-long)

Copied to clipboard

Zhaojian Yu, Xin Zhang, Ning Shang, Yangyu Huang, Can Xu, Yishujie Zhao, Wenxiang Hu, Qiufeng Yin

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

Challenge:	Recent work shows that Code Large Language Models can address a wide range of code-related tasks.
Approach:	They propose a method to generate widespread and versatile instruction data from open source code datasets and use it to train code-related models.
Outcome:	The proposed model outperforms open-source models in generalization ability across code-related tasks.

Copied to clipboard

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