Papers by Xiaodong Zhang

Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding (2023.findings-emnlp)

Challenge:	a novel approach to contrastive learning for language understanding is not fully explored . contrastive training has been widely applied to self-supervised representation learning .
Approach:	They propose a label anchored contrastive learning approach for language understanding using a class label.
Outcome:	The proposed approach improves on GLUE and CLUE benchmarks by 4.1% compared to the state-of-the-art approaches . the proposed approach also improves under the few-shot and data imbalance settings .

Copied to clipboard

Yu Zhang, Hao Cheng, Zhihong Shen, Xiaodong Liu, Ye-Yi Wang, Jianfeng Gao

Correctable-DST: Mitigating Historical Context Mismatch between Training and Inference for Improved Dialogue State Tracking (2022.emnlp-main)

Challenge:	Pre-trained language models (LMs) have shown effectiveness in literature understanding tasks, especially when tuned via contrastive learning.
Approach:	They propose a multi-task contrastive learning framework that enables common knowledge sharing across different scientific literature understanding tasks while preventing task-specific skills from interfering with each other.
Outcome:	The proposed framework outperforms state-of-the-art pre-trained language models on a comprehensive dataset.

Copied to clipboard

Hongyan Xie, Haoxiang Su, Shuangyong Song, Hao Huang, Bo Zou, Kun Deng, Jianghua Lin, Zhihui Zhang, Xiaodong He

Dialogue Systems & Conversational Agents

Challenge:	Existing dialogue state tracking approaches predict the dialogue state of a target turn sequentially based on the ground-truth previous dialogue state.
Approach:	They propose a method that predicts dialogue state sequentially based on previous dialogue state . they propose generating a previously “predicted” dialogue state using ground-truth previous dialogue states .
Outcome:	The proposed method achieves 67.51%, 68.24%, 70.30%, 71.38%, and 81.27% joint goal accuracy on MultiWOZ 2.0-2.4 datasets.

LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline (2025.findings-acl)

Copied to clipboard

Biao Fu, Minpeng Liao, Kai Fan, Chengxi Li, Liang Zhang, Yidong Chen, Xiaodong Shi

Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents (2023.findings-eacl)

Challenge:	Large language models perform well in offline machine translation when the complete source sentence is provided . however, in many real scenarios, the source tokens arrive in a streaming manner and simultaneous machine translation is required .
Approach:	They propose a new paradigm that includes constructing supervised fine-tuning data for simultaneous machine translation (SiMT) to achieve SiMT, source and target tokens are rearranged into interleaved sequences, separated by special tokens according to varying latency requirements.
Outcome:	The proposed approach achieves state-of-the-art performance across various SiMT benchmarks and evaluation metrics while maintaining efficient auto-regressive decoding.

Copied to clipboard

Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, Wee Sun Lee

Information Extraction & Text Mining

Challenge:	Existing datasets do not cover documents with complex spatial structures and a lack of spatial information for document entity classification.
Approach:	They propose a new spatial bias in attention calculation based on the K-nearest-neighbor graph of document entities that limits entities’ attention to their local radius.
Outcome:	The proposed model outperforms baselines in most entity types and is highly parameter-efficient compared to existing methods.

Towards Better Document-level Relation Extraction via Iterative Inference (2022.emnlp-main)

Copied to clipboard

Liang Zhang, Jinsong Su, Yidong Chen, Zhongjian Miao, Min Zijun, Qingguo Hu, Xiaodong Shi

Information Extraction & Text Mining

Challenge:	Existing methods only consider feature information of entity pairs, but our model exploits both feature information and previous predictions of entity pair.
Approach:	They propose a document-level relation extraction model with iterative inference to extract relations between entities from raw texts.
Outcome:	The proposed model outperforms existing methods on three commonly-used datasets.

On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation (2021.acl-long)

Copied to clipboard

Wei Zhang, Ziming Huang, Yada Zhu, Guangnan Ye, Xiaodong Cui, Fan Zhang

Continuous Decomposition of Granularity for Neural Paraphrase Generation (2022.coling-1)

Challenge:	Existing methods for explaining "black-box" models such as Influence Functions are becoming more popular.
Approach:	They propose a semantic-based evaluation metric that can better align with humans’ judgment of explanations than the widely adopted diagnostic or re-training measures.
Outcome:	The proposed method can better align with humans’ judgment of explanations than diagnostic or re-training measures.

Copied to clipboard

Xiaodong Gu, Zhaowei Zhang, Sang-Woo Lee, Kang Min Yoo, Jung-Woo Ha

Text Generation

Challenge:	Prior work has shown that decomposing sentences at different levels of granularity has improved paragraph generation.
Approach:	They propose a model for continuous decomposing granularity for neural paraphrase generation that incorporates granules into attention.
Outcome:	The proposed model outperforms baseline models on Quora question pairs and Twitter URLs on two benchmarks.

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference (2024.findings-acl)

Copied to clipboard

Dongjie Yang, Xiaodong Han, Yan Gao, Yao Hu, Shilin Zhang, Hai Zhao

Challenge:	Existing methods to reduce memory usage for large language models neglect inter-layer dependency between layers and huge memory consumption in pre-computation.
Approach:	They propose a method that compresses the KV cache by layer-wise retaining crucial context.
Outcome:	The proposed method reduces memory usage by layer-wise retaining crucial context . it can improve 2.2x throughput compared to Accelerate with over 54% memory reduction .

SOTOPIA-: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents (2025.acl-long)

Copied to clipboard

Wenyuan Zhang, Tianyun Liu, Mengxiao Song, Xiaodong Li, Tingwen Liu

Challenge:	Existing studies on the social simulation of large language model intelligent agents have shown that even expert agents 1 perform significantly worse on challenging social tasks compared to expert agents.
Approach:	They propose a framework that dynamically injects a variety of social strategies into expert agents, thereby automating the construction of high-quality social dialogue training corpus.
Outcome:	The proposed framework enables the integration of social strategies into language agents and improves their performance on social tasks.

Representation Purification for End-to-End Speech Translation (2025.coling-main)

Copied to clipboard

Chengwei Zhang, Yue Zhou, Rui Zhao, Yidong Chen, Xiaodong Shi

Speech & Audio in NLP

Challenge:	Existing approaches to enhance speech translation focus on enhancing knowledge transfer . factors in speech that are not relevant to translation content, such as timbre and rhythm, often limit the efficiency of knowledge transfer.
Approach:	They propose a framework that excludes content-agnostic perturbations from speech representations to mitigate their negative impact on ST.
Outcome:	The proposed framework significantly improves translation performance across all translation directions in three settings and achieves preeminent performance under a transcript-free setting.

RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)

Copied to clipboard

Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji

Visual Data in NLP

Challenge:	We present a new information extraction system that can construct temporal event graphs from news documents.
Approach:	They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction .
Outcome:	The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities.

Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries (2025.findings-acl)

Copied to clipboard

Ganlin Xu, Zhoujia Zhang, Wangyi Mei, Jiaqing Liang, Weijia Lu, Xiaodong Zhang, Zhifei Yang, Xiaofeng Ma, Yanghua Xiao, Deqing Yang

Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task (2022.coling-1)

Challenge:	Current dense retrieval methods compute similarities between dense vectors but overlook the real query intents.
Approach:	They propose a neuro-symbolic information retrieval method that leverages first-order logic to optimize the embeddings of naive natural language by considering the logical consistency between queries and documents.
Outcome:	The proposed method outperforms existing methods on negative-constraint queries under zero-shot and low-resource retrieval tasks.

Copied to clipboard

Liang Wen, Juan Li, Houfeng Wang, Yingwei Luo, Xiaolin Wang, Xiaodong Zhang, Zhicong Cheng, Dawei Yin

EvoHyper: Evolving Hypergraph Topologies for Unified Collaboration in Multi-Agent Communication (2026.findings-acl)

Challenge:	Existing answer selection approaches for community question answering lack additional answer summaries due to redundancy and lengthiness issues of crowdsourced answers.
Approach:	They constructed a dataset which contains a corresponding reference summary for each original lengthy answer.
Outcome:	The proposed model improves the performance of a question and candidate answer on a WikiHowQA dataset.

Copied to clipboard

Heng Zhang, Yihao Zhong, Lubin Gan, Zhihe Chen, Jiajun Wu, Yuling Shi, Xiaodong Gu, Hao Zhang, Haochen You, Jin Huang

Challenge:	Existing methods for multi-agent collaboration use a fixed communication graph and manage collaboration structure and shared memory in separate modules.
Approach:	They propose a framework that uses an evolving hypergraph topology for multi-agent collaboration.
Outcome:	The proposed framework achieves 3.2% to 7.8% accuracy gains over state-of-the-art methods and efficient, reducing token consumption by up to 23.5%.

Unsupervised Deep Structured Semantic Models for Commonsense Reasoning (N19-1)

Copied to clipboard

Shuohang Wang, Sheng Zhang, Yelong Shen, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Jing Jiang

Reasoning

Challenge:	Existing methods for commonsense reasoning rely on human-crafted features and knowledge bases, but unsupervised learning is not feasible due to the lack of labeled training data or comprehensive knowledge bases.
Approach:	They propose two unsupervised models based on the Deep Structured Semantic Models framework to tackle two commonsense reasoning tasks: Winograd Schema Challenge (WSC) and Pronoun Disambiguation (PDP).
Outcome:	The proposed models capture contextual information in the sentence and co-reference information between pronouns and nouns, and achieve significant improvement over previous state-of-the-art approaches.

Knowledge-Rich Self-Supervision for Biomedical Entity Linking (2022.findings-emnlp)

Copied to clipboard

Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon

HittER: Hierarchical Transformers for Knowledge Graph Embeddings (2021.emnlp-main)

Challenge:	Entity linking is challenging in high-value domains with myriad entities . standard classification approaches suffer from the annotation bottleneck .
Approach:	They propose a self-supervised approach to learn domain knowledge for biomedical entity linking . it generates self-reported mention examples on unlabeled text and trains contextual encoder .
Outcome:	The proposed method outperforms existing methods by 20 points in accuracy on biomedical datasets.

Copied to clipboard

Sanxing Chen, Xiaodong Liu, Jianfeng Gao, Jian Jiao, Ruofei Zhang, Yangfeng Ji

SWE-QA: Can Language Models Answer Repository-level Code Questions? (2026.findings-acl)

Challenge:	Existing knowledge graph embedding methods to learn representations of knowledge graphs are conceptually simple and can be applied to tasks like factoid question answering (Saxena et al., 2020) and reasoning.
Approach:	They propose a Hierarchical Transformer model to jointly learn Entity-relation composition and Relational contextualization based on a source entity’s neighborhood.
Outcome:	The proposed model achieves state-of-the-art on multiple link prediction datasets and can be integrated into BERT and demonstrate its effectiveness on two Freebase factoid question answering datasets.

Copied to clipboard

Weihan Peng, Yuling Shi, Yuhang Wang, Xinyun Zhang, Beijun Shen, Xiaodong Gu

GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts (2026.findings-acl)

Challenge:	Existing benchmarks for understanding and reasoning about entire soft-ware repositories focus on small, self-contained code snippets.
Approach:	They propose a repository-level code question answering benchmark to facilitate research on automated QA systems in real-world repositories.
Outcome:	The proposed benchmarks are designed to facilitate research on automated QA systems in real-world repositories.

Copied to clipboard

Wenhao Zeng, Xuteng Zhang, Yuling Shi, Chao Hu, Yuting Chen, Beijun Shen, Xiaodong Gu

Chain-of-Skills: A Configurable Model for Open-Domain Question Answering (2023.acl-long)

Challenge:	Existing routing strategies rely on local token probabilities or post-hoc verification, introducing significant inference overhead.
Approach:	They propose a step-wise collaboration framework that generates only the first token of each reasoning step and routes it to a larger model only when initial token entropy exceeds a threshold.
Outcome:	The proposed approach reduces inference latency while preserving accuracy.

Copied to clipboard

Kaixin Ma, Hao Cheng, Yu Zhang, Xiaodong Liu, Eric Nyberg, Jianfeng Gao

Information Retrieval

Challenge:	Using customized retrieval models, model transferability and scalability are limited.
Approach:	They propose a modular retrieval model where individual modules correspond to key skills that can be reused across datasets.
Outcome:	The proposed model outperforms self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA.

Compositional Mathematical Encoding for Math Word Problems (2023.findings-acl)

Copied to clipboard

Zhenwen Liang, Jipeng Zhang, Kehan Guo, Xiaodong Wu, Jie Shao, Xiangliang Zhang

Numerical Reasoning

Challenge:	Existing MWP encoders work in a unimodal setting and map problem description to latent representation, then for decoding.
Approach:	They propose a Compositional Math Word Problem Solver which maps problem description to latent representation and decodes it in an interactive way.
Outcome:	Extensive experiments show that the proposed model outperforms state-of-the-art models on public benchmarks.

Adaptive Simultaneous Sign Language Translation with Confident Translation Length Estimation (2024.lrec-main)

Copied to clipboard

Tong Sun, Biao Fu, Cong Hu, Liang Zhang, Ruiquan Zhang, Xiaodong Shi, Jinsong Su, Yidong Chen

Multimodality

Challenge:	Existing non-simultaneous sign language translation methods suffer from inherent inference delays in real-time scenarios.
Approach:	They propose an adaptive policy for simultaneous sign language translation that progressively converts incrementally received sign video into its corresponding natural sentence.
Outcome:	The proposed policy excels in situations requiring extremely low latency.

MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking (2023.findings-acl)

Copied to clipboard

Haoning Zhang, Junwei Bao, Haipeng Sun, Youzheng Wu, Wenye Li, Shuguang Cui, Xiaodong He

Dialogue Systems & Conversational Agents

Challenge:	Experimental results show that MoNET outperforms previous DST methods in alleviating state momentum issues and improving the anti-noise ability.
Approach:	They propose to use previous state of each turn in training data as input to learn to predict current state.
Outcome:	The proposed model outperforms existing methods on multiWOZ datasets and shows that it can update and correct slot values and improve anti-noise ability.

Transplant Then Regenerate: A New Paradigm for Text Data Augmentation (2025.emnlp-main)

Copied to clipboard

Guangzhan Wang, Hongyu Zhang, Beijun Shen, Xiaodong Gu

Low-Resource NLP

Challenge:	Data augmentation is a critical technique in deep learning.
Approach:	They propose a novel text augmentation paradigm leveraging large language models . they incorporate seed text into a context expanded by LLM and ask it to regenerate a variant based on the expanded context.
Outcome:	The proposed model generates high-quality and diverse augmented text with a transplant-then-regenerate approach.

A Neural Question Answering Model Based on Semi-Structured Tables (C18-1)

Copied to clipboard

Hao Wang, Xiaodong Zhang, Shuming Ma, Xu Sun, Houfeng Wang, Mengxiang Wang

Multimodality

Challenge:	Existing question answering systems rely on raw text and structured knowledge graphs.
Approach:	They build an end-to-end system to answer multiple choice questions with semi-structured tables as its knowledge.
Outcome:	The proposed system improves on the state-of-the-art question answering system with tabMCQ dataset.

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.

ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Parity LLM Data Valuation (2025.naacl-long)

Copied to clipboard

Yanzhou Pan, Huawei Lin, Yide Ran, Jiamin Chen, Xiaodong Yu, Weijie Zhao, Denghui Zhang, Zhaozhuo Xu

DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning (2026.findings-acl)

Challenge:	Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance.
Approach:	They propose a third-party data valuation approach that assesses the value of individual data samples and proposes a learning strategy to approximate LinFiK.
Outcome:	The proposed approach surpasses baselines in effectiveness and efficiency, showing significant scalability advantages as LLM parameters increase.

Copied to clipboard

Chao Huang, Zeliang Zhang, Jiang Liu, Ximeng Sun, Jialian Wu, Xiaodong Yu, Ze Wang, Chenliang Xu, Emad Barsoum, Zicheng Liu

Reasoning

Challenge:	Multimodal large language models (MLLMs) have made rapid progress in perception and alignment, but their reasoning ability often lags behind strong text-only LLMs.
Approach:	They propose a method that transfers reasoning knowledge in the gradient space while preserving multimodal alignment.
Outcome:	Experiments on multimodal reasoning benchmarks show that DRIFT outperforms naive merging and standard SFT.

Text Level Graph Neural Network for Text Classification (D19-1)

Copied to clipboard

Lianzhe Huang, Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang

Information Extraction & Text Mining

Challenge:	Recent researches have explored graph neural network (GNN) techniques on text classification, but they are faced with the problems of fixed corpus level graph structure which don’t support online testing and high memory consumption.
Approach:	They propose a graph neural network model that builds graphs for each input text with global parameters sharing instead of a single graph for the whole corpus.
Outcome:	The proposed model outperforms existing models on several text classification datasets even with consuming less memory.

Multimodal Sentence Summarization via Multimodal Selective Encoding (2020.coling-main)

Copied to clipboard

Haoran Li, Junnan Zhu, Jiajun Zhang, Xiaodong He, Chengqing Zong

Multimodality

Challenge:	Existing methods for generating summary from text and image ignore that the image can improve the ability of the encoder to identify highlights of a news event or document.
Approach:	They propose a multimodal selective gate network that takes reciprocal relationships between textual and multi-level visual features into account to select highlights of the event.
Outcome:	The proposed model can generate summary for a given sentence-image pair using visual signals . it can also capture highlights embedded in the image more accurately, the authors show .

Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach (P18-1)

Copied to clipboard

Jingjing Xu, Xu Sun, Qi Zeng, Xiaodong Zhang, Xuancheng Ren, Houfeng Wang, Wenjie Li

Machine Translation

Challenge:	Existing studies for sentiment-to-sentiment "translation" only change the underlying sentiment and fail to keep the semantic content.
Approach:	They propose a cycled reinforcement learning method that combines neutralization module and emotionalization module.
Outcome:	The proposed method outperforms state-of-the-art systems on Yelp and Amazon review datasets.

Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience (2025.emnlp-main)

Copied to clipboard

Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Bin Ji, Ma Jun, Xiaodong Liu, Jing Wang, Jianfeng Zhang, Jie Yu, Feilong Bao, null Wangbaosheng

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios (2025.acl-long)

Challenge:	Existing methods to generate human-aligned content with a “jailbreak prompt” are inefficient and repetitive, causing inefficiency and a lack of experience.
Approach:	They propose a framework that integrates past attack experiences to aid current jailbreak attempts.
Outcome:	The proposed framework improves both attack effectiveness and efficiency compared to the current black-box jailbreak method.

Copied to clipboard

Xiaodong Wu, Minhao Wang, Yichen Liu, Xiaoming Shi, He Yan, Lu Xiangju, Junmin Zhu, Wei Zhang

Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation (2025.acl-long)

Challenge:	Existing benchmarks rarely focus on instruction-following in long-context scenarios or stability on different inputs.
Approach:	They propose a scalable dataset to evaluate LLMs’ instruction-following capabilities and stability across long contexts.
Outcome:	The proposed method evaluates LLMs’ instruction-following capabilities and stability across long contexts.

Copied to clipboard

Qichuan Liu, Chentao Zhang, Chenfeng Zheng, Guosheng Hu, Xiaodong Li, Zhihong Zhang

Structured Data in NLP

Challenge:	Existing evaluations of multi-hop question answering systems focus on comparing final answers of reasoning method and given ground-truths.
Approach:	They propose a "Planner-Executor-Reasoner" architecture that evaluates reasoning . they propose PER-DP and PER QA architectures that provide ground-truths .
Outcome:	The proposed model improves the performance of multi-hop question answering systems.

GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillation (2024.emnlp-industry)

Copied to clipboard

Wenjie Zhou, Zhenxin Ding, Xiaodong Zhang, Haibo Shi, Junfeng Wang, Dawei Yin

Signer Diversity-driven Data Augmentation for Signer-Independent Sign Language Translation (2024.findings-naacl)

Challenge:	Pre-trained language models have achieved remarkable performance in OpenQA, but for practical deployment, knowledge distillation is crucial to maintain high performance while operating under computational constraints.
Approach:	They propose an algorithm to perform unsupervised knowledge distillation without the guidance of labels to achieve 99.5% of performance.
Outcome:	The proposed algorithm achieves 99.5% of performance in a commercial question-answering system.

Copied to clipboard

Honghao Fu, Liang Zhang, Biao Fu, Rui Zhao, Jinsong Su, Xiaodong Shi, Yidong Chen