Papers by Yue Dong

Domain Adaptation for Question Answering via Question Classification (2022.coling-1)

Challenge:	Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling agent collaboration through message-based communications.
Approach:	They propose an attack that exploits communication mechanisms in Large Language Model-based Multi-Agent Systems (LLM-MAS) by intercepting and manipulating inter-agent messages.
Outcome:	The proposed attack exploits communication mechanisms in large language model-based multi-agent systems by intercepting and manipulating inter-agencies.

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Ziyi Kou, Lanyu Shang, Dong Wang

ExpertGenQA: Open-ended QA generation in Specialized Domains (2025.findings-emnlp)

Challenge:	Question answering systems often experience performance deterioration upon user-generated questions.
Approach:	They propose a question classification framework to help QA domains adapt to different domains.
Outcome:	The proposed framework improves on state-of-the-art datasets against multiple datasets.

Copied to clipboard

Haz Sameen Shahgir, Chansong Lim, Jia Chen, Evangelos E. Papalexakis, Yue Dong

Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent (2025.findings-acl)

Challenge:	Existing methods for generating high-quality question–answer (QA) pairs yield generic or shallow questions that fail to reflect the depth and structure of expert-written examples.
Approach:	They propose a question-answer generation protocol that combines few-shot prompting with dual categorization by topic and question style to produce more diverse and cognitively meaningful QA pairs.
Outcome:	The proposed protocol achieves twice the efficiency of standard few-shot methods while maintaining 94.4% topic coverage.

Copied to clipboard

Xueyang Feng, Jingsen Zhang, Jiakai Tang, Wei Li, Guohao Cai, Xu Chen, Quanyu Dai, Yue Zhu, Zhenhua Dong

Dialogue Systems & Conversational Agents

Challenge:	Recent advances in Large Language Models (LLMs) have propelled the development of Conversational Recommendation Agents (CRAs).
Approach:	They propose a multi-turn preference optimization paradigm that leverages Expectation Confirmation Theory to explicitly model the evolution of user satisfaction throughout multi-turned dialogues.
Outcome:	The proposed paradigm eliminates the significant sampling overhead of existing MTPO methods while ensuring the optimization process drives meaningful improvements.

QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation (2022.emnlp-main)

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Bernhard Kratzwald, Stefan Feuerriegel, Dong Wang

Low-Resource NLP

Challenge:	Question answering models often suffer from performance deterioration upon deployment .
Approach:	They propose a self-supervised framework called QADA for QA domain adaptation . they propose to augment training QA samples with hidden space augmentation .
Outcome:	The proposed framework improves on multiple target datasets over state-of-the-art methods.

Biasly: An Expert-Annotated Dataset for Subtle Misogyny Detection and Mitigation (2024.findings-acl)

Copied to clipboard

Brooklyn Sheppard, Anna Richter, Allison Cohen, Elizabeth Smith, Tamara Kneese, Carolyne Pelletier, Ioana Baldini, Yue Dong

Challenge:	the Biasly dataset captures misogyny in movies in ways unique within the literature.
Approach:	The Biasly dataset captures misogyny in North American film by combining annotations of movie subtitles with common NLP algorithms.
Outcome:	The Biasly dataset captures misogyny expressions in North American film . it contains annotations of movie subtitles and text generation for rewrites .

Discourse-Aware Unsupervised Summarization for Long Scientific Documents (2021.eacl-main)

Copied to clipboard

Yue Dong, Andrei Mircea, Jackie Chi Kit Cheung

C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of References (2022.acl-short)

Challenge:	Existing extractive models for short news summarization are weak, despite recent advances in abstractive summarizing.
Approach:	They propose an unsupervised graph-based ranking model that uses a hierarchical graph representation to determine sentence importance.
Outcome:	The proposed model outperforms strong unsupervised baselines by wide margins in automatic metrics and human evaluation.

Copied to clipboard

Xiang Yue, Xiaoman Pan, Wenlin Yao, Dian Yu, Dong Yu, Jianshu Chen

Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments (2024.acl-long)

Challenge:	Existing approaches to pretrain open-domain question answering systems lack task-specific annotations.
Approach:	They propose to pretrain a two-stage open-domain question answering system with strong transfer capabilities by using a dictionary and a large-scale corpus.
Outcome:	The proposed approach leads to 2%-10% gains in top-20 accuracy and improves with reader.

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Lanyu Shang, Yifan Liu, Yang Zhang, Dong Wang

Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment (2025.emnlp-main)

Challenge:	Existing methods to verify claim credibility rely on embedded knowledge or unreliable context.
Approach:	They propose retrieval augmented fact verification through the synthesis of contrasting arguments (RAFTS) they use an embedding model to identify informative demonstrations and in-context prompts to generate the prediction and explanation.
Outcome:	The proposed method outperforms existing methods with smaller LLMs or unreliable contexts.

Copied to clipboard

Pedram Zaree, Md Abdullah Al Mamun, Quazi Mishkatul Alam, Yue Dong, Ihsen Alouani, Nael Abu-Ghazaleh

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs (2026.findings-acl)

Challenge:	Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment.
Approach:	They propose a method for generating highly effective Jailbreak attacks that selectively strengthen or weaken attention among different parts of the prompt.
Outcome:	The proposed attacks amplify the success rate of existing Jailbreak algorithms while lowering generation cost.

Copied to clipboard

Jinbo Liu, Defu Cao, Yifei Wei, Tianyao Su, Yuan Liang, Yushun Dong, Yan Liu, Yue Zhao, Xiyang Hu

Factual Error Correction for Abstractive Summarization Models (2020.emnlp-main)

Challenge:	Multi-agent LLMs are rapidly moving from prototype to real-world use . network topology is a first-order security parameter in multi-aggent systems .
Approach:	They propose a framework for comparing topology-conditioned memory leakage in multi-agent LLM systems.
Outcome:	The proposed framework evaluates topology-conditioned memory leakage in multi-agent LLM systems.

Copied to clipboard

Meng Cao, Yue Dong, Jiapeng Wu, Jackie Chi Kit Cheung

Summarization

Challenge:	Existing methods for abstractive summarization are unable to ensure factual consistency of generated summaries.
Approach:	They propose a post-editing corrector module to identify and correct factual errors in generated summaries.
Outcome:	The proposed model outperforms existing models on CNN/DailyMail dataset on factual consistency evaluation.

Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination (2022.emnlp-main)

Copied to clipboard

Yue Yang, Wenlin Yao, Hongming Zhang, Xiaoyang Wang, Dong Yu, Jianshu Chen

Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs? (2024.naacl-long)

Challenge:	Large-scale pretrained language models suffer from reporting bias, describing the lack of explicit commonsense knowledge in written text.
Approach:	They propose to endow language models with visual imagination capabilities by recalling existing images and synthesizing nonexistent images via text-to-image generation.
Outcome:	The proposed model improves the performance of existing language models across a diverse set of language tasks.

Copied to clipboard

Kai Sun, Yifan Xu, Hanwen Zha, Yue Liu, Xin Luna Dong

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations (2024.findings-emnlp)

Challenge:	Existing large language models lack knowledge of nuanced, domain-specific details and are susceptible to hallucinations.
Approach:	They construct a benchmark that measures head, torso, and tail facts in terms of popularity.
Outcome:	The proposed model is based on 18K question-answer pairs regarding head, torso, and tail facts in terms of popularity.

Copied to clipboard

Lei Yu, Meng Cao, Jackie Cheung, Yue Dong

Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning (2023.acl-long)

Challenge:	State-of-the-art language models (LMs) sometimes generate that misalign with world knowledge.
Approach:	They propose a method to mitigate hallucinations by restoring the LM's internal fact recall pipeline by a targeted restoration of its internal fact-recall pipeline.
Outcome:	The proposed method shows superior performance compared to baselines.

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Mengfei Lan, Heng Ji, Dong Wang

Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles (2020.emnlp-main)

Challenge:	Existing methods for event detection often fail to detect unseen or rare events due to the lack of domain knowledge.
Approach:	They propose a meta learning-based framework for zero-shot event detection that uses a prompt-based prompt and a trigger-aware soft verbalizer to efficiently project output to unseen tasks.
Outcome:	The proposed framework performs state-of-the-art in zero-shot and few-shot scenarios on benchmark datasets FewEvent and MAVEN.

Copied to clipboard

Yao Lu, Yue Dong, Laurent Charlin

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack (2024.acl-long)

Challenge:	Multi-XScience is a dataset construction protocol that favours abstractive modeling approaches.
Approach:	They propose a large-scale multi-document summarization dataset that is based on articles and lexical databases and WordNet synonymy information to generate related-work sections of a paper.
Outcome:	The proposed method is based on lexical databases and WordNet synonymy information to write related work sections of a paper based upon their abstract and the articles they reference.

Copied to clipboard

Yu Fu, Yufei Li, Wen Xiao, Cong Liu, Yue Dong

PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering (2024.findings-acl)

Challenge:	Recent developments in balancing usefulness and safety of large language models raise a critical question . current attacks, especially adversarial ones that manipulate malicious prompts, often aim to manipulate the input .
Approach:	They show that LLMs can effectively summarize malicious long documents but often refuse to translate them.
Outcome:	The findings highlight a vulnerability in LLMs that can't translate or summarize documents . the study focuses on LLM models, Gemini and GPT-4, which can' be exploited .

Copied to clipboard

Jannat Meem, Muhammad Rashid, Yue Dong, Vagelis Hristidis

Question Answering

Challenge:	Existing work on Temporal Question Answering (TQA) has focused on questions anchored to specific timestamps or events.
Approach:	They introduce a benchmark to address present-anchored temporal QA (PATQA) which includes single and multi-hop temporal questions.
Outcome:	The proposed model can be automatically refreshed by re-running SPARQL queries on a knowledge graph.

Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding (2026.acl-long)

Copied to clipboard

Wenqing Hou, Hongkui Tu, Ye Wang, Yue Zhang, Yuying Liu, Dong Zhu, Liqun Gao, Bin Zhou

AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Challenge:	Existing methods for identifying harmful memes rely on modal alignment or black-box classifiers . BPDMoE-Hate provides visual explanations for viewpoint selection and hierarchical structuring .
Approach:	They propose a framework that conceptualizes harmful meme detection as a process of "viewpoint decoupling and hierarchical fusion" they propose BPDMoE-Hate, which generates adversarial binary perspectives via VLMs and incorporates an adaptive viewpoint gating to facilitate viewpoint selection.
Outcome:	The proposed framework surpasses existing methods in performance and provides visual explanations for viewpoint selection and hierarchical structuring.

Copied to clipboard

Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang

Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis (2021.acl-long)

Challenge:	Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach:	They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome:	The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.

Copied to clipboard

Linyi Yang, Jiazheng Li, Padraig Cunningham, Yue Zhang, Barry Smyth, Ruihai Dong

Sentiment Analysis

Challenge:	Existing approaches to improve performance of deep neural models are limited by the nature of spurious patterns in the data.
Approach:	They propose to use augmented data to generate spurious patterns in NLP models . they propose to generate counterfactual data for data augmentation and explanation .
Outcome:	The proposed approach improves performance on augmented data and on human-generated data.

RelationalCoder: Rethinking Complex Tables via Programmatic Relational Transformation (2025.acl-long)

Copied to clipboard

Haoyu Dong, Yue Hu, Huailiang Peng, Yanan Cao

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Semi-structured tables remain a major obstacle for automated data processing and analytics.
Approach:	They propose a technique called Loop Reference Decoding which identifies expandable groups and replicates each group using a concise loop over its repetitive region.
Outcome:	The proposed technique reduces output length from O(N M) to approximately O(K) Extensive experiments on HiTab and MultiHiertt show that it boosts Llama-2 and Mistral models by more than 20%, and GPT-4o by over 4%.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks (2024.findings-acl)

Copied to clipboard

Haz Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong

Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses (D19-1)

Challenge:	Existing studies on adversarial attacks against text-to-image models have not explored the reasons for their effectiveness.
Approach:	They propose an adversarial attack objective - entity swapping using adversarials and two gradient-based attack algorithms.
Outcome:	The proposed attack objective - entity swapping - is easier to replace “human” with “robot” in the prompt “a human dancing in the rain.”

Copied to clipboard

Matt Grenander, Yue Dong, Jackie Chi Kit Cheung, Annie Louis

Summarization

Challenge:	Sentence position is a strong feature for news summarization, since the lead often summarizes the key points of the article.
Approach:	They propose two techniques to make neural systems sensitive to the importance of content in different parts of the article by using random shuffled sentences to pretrain the model.
Outcome:	The proposed techniques improve the performance of a competitive reinforcement learning based extractive system, with the auxiliary loss being more powerful than pretraining.

Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation (2024.findings-emnlp)

Copied to clipboard

G Shahariar, Jia Chen, Jiachen Li, Yue Dong

Can Textual Unlearning Solve Cross-Modality Safety Alignment? (2024.findings-emnlp)

Challenge:	Recent studies show that text-to-image models are vulnerable to adversarial perturbations .
Approach:	They investigate the impact of adversarial attacks on different POS tags within text prompts on T2I models.
Outcome:	The proposed model is vulnerable to adversarial perturbations with noun perturbations in text prompts.

Copied to clipboard

Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael Abu-Ghazaleh, M. Salman Asif, Yue Dong, Amit Roy-Chowdhury, Chengyu Song

HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models (2025.findings-emnlp)

Challenge:	integrating new modalities into large language models creates new attack surface . existing safety training techniques like SFT and RLHF are not feasible in multi-modal settings .
Approach:	They explore whether unlearning in the textual domain can be effective for cross-modality safety alignment.
Outcome:	The proposed approach reduces the Attack Success Rate (ASR) to less than 8% and preserves the utility.

Copied to clipboard

Trishna Chakraborty, Udita Ghosh, Xiaopan Zhang, Fahim Faisal Niloy, Yue Dong, Jiachen Li, Amit Roy-Chowdhury, Chengyu Song

LitVISTA: A Benchmark for Narrative Orchestration in Literary Text (2026.acl-long)

Challenge:	Large language models are increasingly being adopted as the cognitive core of embodied agents.
Approach:	They propose a systematic study of hallucinations in large language models . they aim to understand to what extent hallucinos occur, what types trigger them .
Outcome:	The proposed model can induce hallucinations up to 40 higher than base prompts . the model fails to resolve scene-task inconsistencies, the study finds .

Copied to clipboard

Mingzhe Lu, Yiwen Wang, Yanbing Liu, Qi You, Chong Liu, Ruize Qin, Haoyu Dong, Wenyu Zhang, JiaRui Zhang, Yue Hu, Yunpeng Li

Challenge:	Existing large language models focus on causal coherence, neglecting the complex story arcs and orchestration inherent in human narratives.
Approach:	They propose a high-dimensional framework for narrative orchestration that unifies human and model perspectives while jointly characterizing narrative function and structure in a common space.
Outcome:	The proposed framework unifies human and model perspectives while jointly characterizing narrative function and structure in a common space.

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)

Copied to clipboard

Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong

OpenFact: Factuality Enhanced Open Knowledge Extraction (2023.tacl-1)

Challenge:	Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages.
Approach:	They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English.
Outcome:	The proposed model outperforms open-source and Tibetan-focused models on diverse tasks.

Copied to clipboard

Linfeng Song, Ante Wang, Xiaoman Pan, Hongming Zhang, Dian Yu, Lifeng Jin, Haitao Mi, Jinsong Su, Yue Zhang, Dong Yu

TableCoder: Table Extraction from Text via Reliable Code Generation (2025.acl-industry)

Challenge:	Existing OIE systems organize knowledge into subject-relation-object (SRO) triplets, and they use templates to extract such knowledge triplet.
Approach:	They propose a framework to handle expressiveness and groundedness in OpenFact . they propose to use templates, extra constraints, and adopt human efforts to ensure that most triplets contain enough details.
Outcome:	The proposed framework improves expressiveness and groundedness of OpenFact . it is more accurate and denser than OPIEC-Linked, which is grounded to Wikidata .

Copied to clipboard

Haoyu Dong, Yue Hu, Huailiang Peng, Yanan Cao

Cautious Next Token Prediction (2025.findings-acl)

Challenge:	Structured table extraction from unstructured text is critical for automating data processing tasks across industries where accuracy and reliability are paramount.
Approach:	They propose a natural language-based method for extracting structured tables from text . they use Python classes or SQL statements to explicitly construct table structures .
Outcome:	The proposed method improves F1 scores and mitigates hallucinations . it integrates with standard SQL databases and Python workflows, ensuring seamless deployment .

Copied to clipboard

Yizhou Wang, Lingzhi Zhang, Yue Bai, Mang Tik Chiu, Zhengmian Hu, Mingyuan Zhang, Qihua Dong, Yu Yin, Sohrab Amirghodsi, Yun Fu

Challenge:	Existing methods for decoding autoregressive models are temperature scaling and nucleus sampling to balance diversity and coherence.
Approach:	They propose a training-free decoding strategy that uses a model with a low perplexity score to select the trial with the lowest perplexities as the most probable and reliable path.
Outcome:	The proposed approach outperforms existing standard decoding strategies consistently by a clear margin.

Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs? (2026.eacl-long)

Copied to clipboard

Kai Sun, Yin Huang, Srishti Mehra, Mohammad Kachuee, Xilun Chen, Renjie Tao, Zhaojiang Lin, Andrea Jessee, Nirav Shah, Alex L Betty, Yue Liu, Anuj Kumar, Wen-tau Yih, Xin Luna Dong

Fair Federated Learning with Biased Vision-Language Models (2024.findings-acl)

Challenge:	Existing literature on knowledge extraction for question answering questions whether it is still relevant for question answerrs.
Approach:	They extend an existing benchmark with knowledge extraction annotations and evaluate commercial and open-source LLMs of varying sizes.
Outcome:	The proposed model can achieve high QA accuracy, but can still benefit from knowledge extraction through augmentation with extracted triples and multi-task learning.

Copied to clipboard

Huimin Zeng, Zhenrui Yue, Yang Zhang, Lanyu Shang, Dong Wang

Structural Information Preserving for Graph-to-Text Generation (2020.acl-main)

Challenge:	Existing literature ignores the inherent group unfairness within CLIP and its ethical implications on FL applications.
Approach:	They propose a fairness-aware adaptation framework for CLIP in federated learning . they propose to leverage biased pre-trained VLMs to build fair FL frameworks .
Outcome:	The proposed framework addresses unique bias in FL, triggered by data heterogeneity . it trains a fair FL model with fairness-aware deep visual prompting (DVP) Extensive results on human face attribute recognition (FAR) applications show it outperforms state-of-the-art FL models .

Copied to clipboard

Linfeng Song, Ante Wang, Jinsong Su, Yue Zhang, Kun Xu, Yubin Ge, Dong Yu

Structured Data in NLP

Challenge:	Existing models that mess up or drop the core structural information of input graphs are lacking in graph-to-text generation.
Approach:	They propose to leverage richer training signals to guide a graph-to-text generation model by focusing on autoencoding losses and back-propagating the losses to better calibrate the model.
Outcome:	Experiments on two benchmarks show the proposed model over a state-of-the-art model . two types of autoencoding losses are used to back-propagate the model based on multitask training .

Faithful to the Document or to the World? Mitigating Hallucinations via Entity-Linked Knowledge in Abstractive Summarization (2022.findings-emnlp)

Copied to clipboard

Yue Dong, John Wieting, Pat Verga

Summarization

Challenge:	Existing abstractive summarization systems are hampered by content hallucinations in which models generate text that is not directly inferable from the source alone.
Approach:	They propose to use external knowledge to latently connect entities and concepts to latences to lend provenance to many of these unfaithful yet factual entities.
Outcome:	The proposed model can be used to improve the factuality of summarizations without simply making them more extractive.

A Hierarchical Neural Attention-based Text Classifier (D18-1)

Copied to clipboard

Koustuv Sinha, Yue Dong, Jackie Chi Kit Cheung, Derek Ruths

MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Challenge:	Existing hierarchical classification models are unable to handle large corpora and the number of categories increases with increasing corpus.
Approach:	They propose to use external knowledge to introduce a hierarchical neural attention-based classifier to help with the classification of documents.
Outcome:	The proposed model performs better than or comparable to state-of-the-art hierarchical models at significantly lower computational cost while maintaining high interpretability.

Copied to clipboard

Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, Pengtao Xie

Dialogue Systems & Conversational Agents

Challenge:	telemedicine is a medical practice that provides patient care remotely using video conferencing tools.
Approach:	They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance .
Outcome:	The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues.

DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Copied to clipboard

Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach:	They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome:	The proposed model outperforms baselines on three real-world datasets.

Text Generation with Text-Editing Models (2022.naacl-tutorials)

Copied to clipboard

Eric Malmi, Yue Dong, Jonathan Mallinson, Aleksandr Chuklin, Jakub Adamek, Daniil Mirylenka, Felix Stahlberg, Sebastian Krause, Shankar Kumar, Aliaksei Severyn

Vulnerabilities of Large Language Models to Adversarial Attacks (2024.acl-tutorials)

Challenge:	Text-editing models are a popular alternative to seq2seq for monolingual text generation tasks such as text summarization and style transfer.
Approach:	They propose to use text-editing models to predict edit operations applied to the source sequence and to generate outputs word-by-word from scratch.
Outcome:	This paper provides an overview of the text-edit based models and their current state-of-the-art approaches.

Copied to clipboard

Yu Fu, Erfan Shayegan, Md. Mamun Al Abdullah, Pedram Zaree, Nael Abu-Ghazaleh, Yue Dong

DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes (2025.findings-emnlp)

Challenge:	This tutorial focuses on the vulnerabilities of Large Language Models to adversarial attacks . the tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity .
Approach:	This tutorial lays the foundation by explaining safety-aligned LLMs and concepts in cybersecurity.
Outcome:	The tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity.

Copied to clipboard

Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu

ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation (2021.eacl-main)

Challenge:	Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding.
Approach:	They introduce DivScene, a large-scale dataset with 4,614 houses across 81 scene types and 5,707 kinds of target objects.
Outcome:	The proposed dataset provides a much greater diversity of target objects and scene types than existing datasets, enabling a comprehensive task evaluation.

Copied to clipboard

Qingxiu Dong, Xiaojun Wan, Yue Cao

Multimodal Language Models See Better When They Look Shallower (2025.emnlp-main)

Challenge:	Existing paraphrase datasets are mainly from news, novels, or social media platforms.
Approach:	They propose to build a large-scale paraphrase dataset using intra-paper and inter-paper methods . they use PDBERT as a general paraphrase discovering method to take advantage of paraphrased sentences .
Outcome:	The proposed dataset includes 33,981 paraphrase pairs from ACL and 316,063 pairs from arXiv . the major advantages of paraphrases lie in the prominent length and textual diversity .

Copied to clipboard

Haoran Chen, Junyan Lin, Xinghao Chen, Yue Fan, Jianfeng Dong, Xin Jin, Hui Su, Jinlan Fu, Xiaoyu Shen

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning (2025.emnlp-industry)

Challenge:	Existing studies show that multimodal large language models extract visual features from the final layers of a pretrained Vision Transformer.
Approach:	They propose a feature fusion method that strategically incorporates shallower layers . they propose MLLMs that extract visual features from the final layers of a pretrained Vision Transformer .
Outcome:	The proposed method outperforms deep layers on fine-grained visual tasks . it is the first comprehensive study of visual layer selection for MLLMs .

Copied to clipboard

Mohammad Kachuee, Teja Gollapudi, Minseok Kim, Yin Huang, Kai Sun, Xiao Yang, Jiaqi Wang, Nirav Shah, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong

Reasoning

Challenge:	Existing methods to improve factuality of large language models (LLMs) rely on human-engineered instructions.
Approach:	They propose a retrieval-augmented generation framework that trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages and instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without extensive human engineered instructions.
Outcome:	The proposed framework outperforms state-of-the-art solutions across 12 open-book RAG QA benchmarks and is being deployed in production.

DataSciBench: An LLM Agent Benchmark for Data Science (2026.findings-acl)

Copied to clipboard

Dan Zhang, Sining Zhoubian, Min Cai, Fengzu Li, Lekang Yang, Wei Wang, Tianjiao Dong, Ziniu Hu, Jie Tang, Yisong Yue

Challenge:	Existing benchmarks focus on single task, simple evaluation metrics, and readily available ground truth (GT) DataSciBench is built on curated, natural, and challenging prompts with complex evaluation criteria and uncertain GT.
Approach:	They propose a benchmark for evaluating Large Language Models in data science that integrates LLM-based self-consistency and human verification to ensure accuracy.
Outcome:	The proposed framework outperforms open-source models in all metrics and offers rigorous insights into LLM strengths and weaknesses.

EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing (P19-1)

Copied to clipboard

Yue Dong, Zichao Li, Mehdi Rezagholizadeh, Jackie Chi Kit Cheung

EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models (2024.findings-acl)

Challenge:	Current sentence simplification systems are variants of sequence-to-sequence models adopted from machine translation.
Approach:	They propose a sentence simplification model that learns explicit edit operations via a neural programmer-interpreter approach.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark text simplification corpora in terms of SARI (+0.95 WikiLarge, +1.89 WikiSmall, -1.41 Newsela)

Copied to clipboard

Muhammad Rashid, Jannat Meem, Yue Dong, Vagelis Hristidis

PEAR: Planner-Executor Agent Robustness Benchmark (2026.findings-eacl)

Challenge:	Large Language Models (LLMs) have demonstrated dominant performance in text re-ranking.
Approach:	They propose a suite of budget-constrained methods to perform text re-ranking using LLMs.
Outcome:	The proposed method outperforms other budget-aware methods on four datasets.

Copied to clipboard

Shen Dong, Mingxuan Zhang, Pengfei He, Li Ma, Bhavani Thuraisingham, Hui Liu, Yue Xing

On-the-Fly Attention Modulation for Neural Generation (2021.findings-acl)

Challenge:	Existing studies examine isolated attack surfaces or specific scenarios, leaving a lack of holistic understanding of MAS vulnerabilities.
Approach:	They propose a benchmark to evaluate the utility and vulnerability of planner–executor MAS.
Outcome:	The proposed benchmark evaluates planner–executor MAS on a widely adopted design.

Copied to clipboard

Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, Antoine Bosselut, Jackie Chi Kit Cheung, Yejin Choi

Reasoning

Challenge:	Degeneration of neural text is associated with insufficient learning of task-specific characteristics by the attention mechanism.
Approach:	They propose to use attention modulation to inject priors into inference to improve fluency, creativity, and commonsense reasoning in neural text generation models.
Outcome:	The proposed method improves fluency, creativity, and commonsense reasoning, and significantly reduces sentence-level repetition.

Learning with Rejection for Abstractive Text Summarization (2022.emnlp-main)

Copied to clipboard

Meng Cao, Yue Dong, Jingyi He, Jackie Chi Kit Cheung

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents (2021.acl-short)

Challenge:	Existing abstractive summarization systems produce non-factual summaries due to noise in the training dataset.
Approach:	They propose a training objective for abstractive summarization based on rejection learning that learns whether or not to reject potentially noisy tokens.
Outcome:	The proposed method significantly improves the factuality of generated summaries in automatic and human evaluations when compared to baseline models.

Copied to clipboard

Rui Meng, Khushboo Thaker, Lei Zhang, Yue Dong, Xingdi Yuan, Tong Wang, Daqing He

Training Medical QA Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questions (2025.findings-emnlp)

Challenge:	Faceted summarization provides briefings of a document from different perspectives.
Approach:	They propose a faceted summarization benchmark built on Emerald journal articles . they propose faceted models that bring structure into faceted documents .
Outcome:	The proposed benchmark is based on Emerald journal articles and covers a diverse range of domains.

Copied to clipboard

Yue Qiu, Yujan Ting, Pei Dong, Terrence Chen, Weijing Huang

Question Answering

Challenge:	Reinforcement learning (RL) for large language models typically requires clear reward signals, which are often unavailable for open-ended (OE) questions where answer evaluation is ambiguous without scalable expert labeling.
Approach:	They propose a mixed-data approach to training large language models with varying reward clarity . they combine Multiple-choice questions (MCQs) with OE questions for which they use simpler, potentially noisy rewards such as Jaccard similarity or LLM-based evaluators.
Outcome:	The mixed-data approach improves medical question-answering performance across model scales.

Train Once, Deploy Anywhere: Matryoshka Representation Learning for Multimodal Recommendation (2024.findings-emnlp)

Copied to clipboard

Yueqi Wang, Zhenrui Yue, Huimin Zeng, Dong Wang, Julian McAuley

ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT (2020.acl-main)

Challenge:	integrating rich multimodal knowledge into recommender systems remains a challenge . despite performance improvements, different recommendation scenarios often require varying granularities.
Approach:	They propose a framework that captures item features at different granularities and learns informative representations for efficient recommendation across multiple dimensions.
Outcome:	The proposed framework achieves superior performance over state-of-the-art models on multiple benchmark datasets.

Copied to clipboard

Linfeng Song, Kun Xu, Yue Zhang, Jianshu Chen, Dong Yu

AdaPrompt: Adaptive Model Training for Prompt-based NLP (2022.findings-emnlp)

Challenge:	Zero pronoun recovery and resolution aim at recovering the dropped pronounce and pointing out its anaphoric mentions.
Approach:	They propose to solve two tasks together to recover the dropped pronoun and point out its anaphoric mentions.
Outcome:	The proposed model outperforms previous state of the arts benchmarks on two benchmarks.

Copied to clipboard

Yulong Chen, Yang Liu, Li Dong, Shuohang Wang, Chenguang Zhu, Michael Zeng, Yue Zhang

A Survey on Open Information Extraction from Rule-based Model to Large Language Model (2024.findings-emnlp)

Challenge:	Prompt-based learning can tackle zero-shot and few-shot NLP tasks . authors propose a method that makes use of pre-trained language models .
Approach:	They propose to map NLP tasks into natural language prompts, which are then filled by pre-trained language models.
Outcome:	The proposed method outperforms standard prompt-based methods in few-shot settings.

Copied to clipboard

Liu Pai, Wenyang Gao, Wenjie Dong, Lin Ai, Ziwei Gong, Songfang Huang, Li Zongsheng, Ehsan Hoque, Julia Hirschberg, Yue Zhang

Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems (2021.naacl-industry)

Challenge:	Open Information Extraction (OpenIE) is a key NLP task aimed at extracting structured information from unstructured text sources.
Approach:	They propose to categorize OpenIE into rule-based, neural, and pre-trained large language models and discuss each within a chronological framework.
Outcome:	The paper categorizes OpenIE approaches into rule-based, neural, and pre-trained large language models, discussing each within a chronological framework.

Copied to clipboard

Tong Wang, Jiangning Chen, Mohsen Malmir, Shuyan Dong, Xin He, Han Wang, Chengwei Su, Yue Liu, Yang Liu

Dialogue Systems & Conversational Agents

Challenge:	In dialog systems, the Natural Language Understanding component makes the interpretation decision before the mentioned entities are resolved.
Approach:	They propose to leverage Entity Resolution (ER) features in NLU reranking to learn model weights . they propose a score distribution matching method to ensure the models are calibrated .
Outcome:	The proposed approach outperforms the baseline model on multiple domain evaluations.

Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation (2024.naacl-long)

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Yimeng Lu, Lanyu Shang, Yang Zhang, Dong Wang

Learning to Generalize for Cross-domain QA (2023.findings-acl)

Challenge:	Existing methods to generate counter-misinformation responses are often trained end-to-end without external knowledge, resulting in subpar text quality and excessively repetitive responses.
Approach:	They propose retrieval augmented response generation for online misinformation (RARG) that collects supporting evidence and generates counter-misinformation responses via reinforcement learning from human feedback.
Outcome:	The proposed method outperforms baselines with extensive experiments with in- and cross-domain datasets and consistently generates high-quality counter-misinformation responses.

Copied to clipboard

Yingjie Niu, Linyi Yang, Ruihai Dong, Yue Zhang

Question Answering

Challenge:	Existing methods for QA are hampered by increased training costs . current methods suffer significant performance degradation when applied to out-of-domain examples.
Approach:	They propose a method that combines prompting methods and linear probing with fine-tuning strategy, which does not entail additional cost.
Outcome:	The proposed method outperforms state-of-the-art baselines with an average increase in F1 score of 4.5%-7.9%.

MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning (2023.acl-long)

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Yang Zhang, Lanyu Shang, Dong Wang

Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization (2026.acl-long)

Challenge:	Existing methods for misinformation detection are limited by data scarcity . existing methods fail to detect early-stage misinformation on emerging topics .
Approach:	They propose a meta learning based approach for domain adaptive few-shot misinformation detection that leverages limited target examples to provide feedback and guide the knowledge transfer from the source to the target domain.
Outcome:	The proposed method improves performance on real-world datasets with reduced parameters.

Copied to clipboard

Yu Fu, Chen Luo, Josef Valvoda, Xin Zhang, Xuejing Lei, Xiao Pan, Hui Liu, Yue Dong

BanditSum: Extractive Summarization as a Contextual Bandit (D18-1)

Challenge:	Recent studies show that KV cache compression can increase hallucination scores in LLMs . modern LLM models support extremely long sequences, but their impact on model hallucinosity remains underexplored.
Approach:	They propose a decoding-phase strategy that selectively removes generated KV pairs from retrieval heads responsible for retrieving critical information from source context.
Outcome:	The proposed method reduces hallucination across multiple models and datasets while preserving computational efficiency.

Copied to clipboard

Yue Dong, Yikang Shen, Eric Crawford, Herke van Hoof, Jackie Chi Kit Cheung

Multi-Fact Correction in Abstractive Text Summarization (2020.emnlp-main)

Challenge:	Existing methods for extractive summarization are heuristically generated and require a set of binary labels to be selected.
Approach:	They propose a method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels.
Outcome:	The proposed method achieves better ROUGE scores than the state-of-the-art methods and significantly fewer update steps than competing approaches.

Copied to clipboard

Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, Jackie Chi Kit Cheung, Jingjing Liu

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization (2022.acl-long)

Challenge:	Existing abstractive summarization systems generate incorrect facts with respect to the source text.
Approach:	They propose a suite of two factual correction models that leverages question-answering knowledge to make corrections in system-generated summaries via span selection.
Outcome:	The proposed model improves factuality of news summarization without sacrificing summary quality.

Copied to clipboard

Meng Cao, Yue Dong, Jackie Cheung

Inverse Reinforcement Learning for Text Summarization (2023.findings-emnlp)

Challenge:	State-of-the-art abstractive summarization systems often generate hallucinations, i.e., content that is not directly inferable from the source document.
Approach:	They propose a detection approach that separates factual from non-factual hallucinations of entities by masked language models.
Outcome:	The proposed method outperforms baselines in accuracy and F1 scores and has a strong correlation with human judgments on factuality classification tasks.

Copied to clipboard

Yu Fu, Deyi Xiong, Yue Dong