Papers by Yang Zhong

TellWhisper: Tell Whisper Who Speaks When (2026.acl-long)

Challenge:	Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach:	They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome:	The proposed framework covers 61 risk categories across four distinct modality interactions.

Copied to clipboard

Yifan Hu, Peiji Yang, Zhisheng Wang, Yicheng Zhong, Rui Liu

Towards a Unified Multi-Dimensional Evaluator for Text Generation (2022.emnlp-main)

Challenge:	Existing approaches decouple temporal modeling and speaker modeling when addressing 'when' and 'who' . a new framework that couples temporal structure with speaker dynamics is proposed to address these limitations .
Approach:	They propose a framework that couples temporal and speaker identity within the speech encoder . they propose TS-RoPE, a time-speaker rotary positional encoding that partitions Query/Key channels into temporal, speaker subspaces and applies region-specific rotations to align "when" and "who" cues in selfattention.
Outcome:	The proposed framework couples temporal structure with speaker dynamics in speech encoder . it uses frame-level speaker activity to estimate speaker-activity estimates .

Copied to clipboard

Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, Pengfei Liu, Chenguang Zhu, Heng Ji, Jiawei Han

Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents (2026.acl-long)

Challenge:	Existing evaluation frameworks for natural language generation are dominated by similarity-based metrics.
Approach:	They propose a multi-dimensional evaluator for natural language generation that integrates multiple dimensions into one evaluer.
Outcome:	The proposed evaluator improves on three typical NLG tasks and improves with external knowledge.

Copied to clipboard

null Ymyang, Jiang Zhong, Li Jin, Xiao Sun, Jingwang Huang, null Gaojinpeng, Qing Liu, Yang Bai, Jingyuan Zhang, Rui Jiang, Qin Lei, Kaiwen Wei

Reducing Spurious Correlations for Answer Selection by Feature Decorrelation and Language Debiasing (2022.coling-1)

Challenge:	Existing benchmarks focus on simple image-text interactions, overlooking complex visual formats like charts.
Approach:	They propose a semi-automatic framework for generating evaluation samples through multi-modal keypoint extraction, knowledge graph construction, and qa pair synthesis.
Outcome:	The proposed framework generates 4,738 question-answering pairs across 8 domains from real-world documents.

Copied to clipboard

Zeyi Zhong, Min Yang, Ruifeng Xu

Robustness in NLP

Challenge:	Existing deep neural models rely on spurious correlations between prediction labels and input features, which in general suffer from robustness and generalization.
Approach:	They propose a feature decorrelation module to remove feature dependencies and reduce spurious correlations by learning a weight for each instance at the training phase.
Outcome:	The proposed method improves the robustness of the neural ANswer selection models from the sample and feature perspectives.

How to Align Multiple Signed Language Corpora for Better Sign-to-Sign Translations? (2025.naacl-long)

Copied to clipboard

Mert Inan, Yang Zhong, Vidya Ganesh, Malihe Alikhani

Multilinguality

Challenge:	despite the growing need for advanced signing technologies, signed language resources remain scarce.
Approach:	They propose a linguistically informed alignment algorithm that matches instances between signed languages . they compare similarities and differences across three signed languages to develop a model .
Outcome:	The proposed algorithm performs well on automatic metrics for sign-to-sign translation and generation.

Interpreting Twitter User Geolocation (2020.acl-main)

Copied to clipboard

Ting Zhong, Tianliang Wang, Fan Zhou, Goce Trajcevski, Kunpeng Zhang, Yi Yang

Mutual-Taught for Co-adapting Policy and Reward Models (2025.acl-long)

Challenge:	Existing methods for identifying user geolocation suffer from a lack of interpretability on the corresponding results.
Approach:	They adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting locations.
Outcome:	The proposed method provides meaningful explanations on prediction results and also uncovers the so-called "black-box" GNN-based models by investigating the effect of individual nodes.

Copied to clipboard

Tianyuan Shi, Canbin Huang, Fanqi Wan, Longguang Zhong, Ziyi Yang, Weizhou Shen, Xiaojun Quan, Ming Yan

Machine Translation

Challenge:	Experimental results show that this iterative approach leads to consistent improvements in both the policy model and reward model.
Approach:	They propose a method that iteratively improves both the policy model and reward model without requiring additional human annotation.
Outcome:	The proposed method improves both the policy model and reward model without human annotation.

On the Hallucination in Simultaneous Machine Translation (2024.acl-short)

Copied to clipboard

Meizhi Zhong, Kehai Chen, Zhengshan Xue, Lemao Liu, Mingming Yang, Min Zhang

Machine Translation

Challenge:	Currently, there are no studies which systematically analyze hallucination in SiMT.
Approach:	They conduct a comprehensive analysis of hallucination in simultaneous machine translation (SiMT) they find that halluciation is extremely severe, especially as latency increases .
Outcome:	The results show that it is possible to alleviate hallucination by decreasing the over usage of target-side information for SiMT.

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions (2023.emnlp-main)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

ThinkSwitcher: When to Think Hard, When to Think Fast (2025.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have produced models that exhibit remarkable performance across a variety of NLP tasks.
Approach:	They analyze a large-scale collection of user-GPT conversations to identify a significant gap between academic research in NLP and the needs of real-world NLP applications.
Outcome:	The proposed model outperforms existing models in a large-scale collection of user-GPT conversations and identifies a significant gap between the tasks that users frequently request from LLMs and the tasks commonly studied in academic research.

Copied to clipboard

Guosheng Liang, Longguang Zhong, Ziyi Yang, Xiaojun Quan

SARA: Salience-Aware Reinforced Adaptive Decoding for Large Language Models in Abstractive Summarization (2025.acl-long)

Challenge:	Large reasoning models excel at solving complex tasks by leveraging long chain-of-thought (CoT) reasoning.
Approach:	They propose a framework that enables a single LRM to dynamically switch between short and long CoT modes based on task complexity.
Outcome:	The proposed framework reduces computational cost by 20-30% while maintaining high accuracy on complex tasks.

Copied to clipboard

Nayu Liu, Junnan Zhu, Yiming Ma, Zhicong Lu, Wenlei Xu, Yong Yang, Jiang Zhong, Kaiwen Wei

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Challenge:	Existing decoding strategies neglect the explicit use of salient contextual information and rely on static hyperparameters to fix the balance between contextual and prior knowledge.
Approach:	They propose a salience-aware reinforced adaptive decoding (SARA) which incorporates salient contextual information and allows the model to determine reliance on source document's context, salient context, and model's prior knowledge based on pointwise mutual information.
Outcome:	The proposed model improves the quality and faithfulness of summaries across LLMs without modifying their weights.

Copied to clipboard

Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang

FaithLM: Towards Faithful Explanations for Large Language Models (2026.eacl-long)

Challenge:	Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach:	AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome:	Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .

Copied to clipboard

Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Andrew Wen, Mengnan Du, Xuanting Cai, Vladimir Braverman, Xia Hu

Explainability & Interpretability in NLP

Challenge:	Large language models (LLMs) produce natural language explanations, but they lack faithfulness and do not reflect the evidence the model uses to decide.
Approach:	They propose a model-agnostic framework that evaluates and improves the faithfulness of LLM explanations without token masking or task-specific heuristics.
Outcome:	The proposed framework improves faithfulness of large language models without masking or heuristics.

Neural CRF Model for Sentence Alignment in Text Simplification (2020.acl-main)

Copied to clipboard

Chao Jiang, Mounica Maddela, Wuwei Lan, Yang Zhong, Wei Xu

ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks (2025.acl-long)

Challenge:	Text simplification systems are based on the quality and quantity of complex-simple sentence pairs extracted by aligning sentences between parallel articles.
Approach:	They propose a neural CRF alignment model which leverages the sequential nature of sentences in parallel documents and utilizes a sentence pair model to capture semantic similarity.
Outcome:	The proposed model outperforms previous work on monolingual sentence alignment task by more than 5 points in F1.

Copied to clipboard

Yu Lin, Ruining Yang, Yunlong Mao, Qizhi Zhang, Jue Hong, Quanwei Cai, Ye Wu, Huiqi Liu, Zhiyu Chen, Bing Duan, Sheng Zhong

Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning (2024.findings-acl)

Challenge:	Recent studies show that obfuscation techniques for MLaaS are susceptible to embedding inversion attacks (EIAs).
Approach:	They propose a model obfuscation framework that protects client inputs from embedding inversion attacks by obliviously obbing models.
Outcome:	The proposed framework outperforms existing works in utility by 10% with a nearly 80% resistance rate against embedding inversion attacks.

Copied to clipboard

Qiming Bao, Alex Peng, Zhenyun Deng, Wanjun Zhong, Gael Gendron, Timothy Pistotti, Neset Tan, Nathan Young, Yang Chen, Yonghua Zhu, Paul Denny, Michael Witbrock, Jiamou Liu

Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)

Challenge:	Empirical evidence shows that our proposed method improves performance across seven downstream tasks.
Approach:	They propose a logic-driven data augmentation approach that converts text into AMR graphs and converts them back into text to create augmented data.
Outcome:	The proposed method leads on the ReClor leaderboard and improves on seven downstream tasks.

Copied to clipboard

Yang Xu, Yunlong Feng, Honglin Mu, Yutai Hou, Yitong Li, Xinghao Wang, Wanjun Zhong, Zhongyang Li, Dandan Tu, Qingfu Zhu, Min Zhang, Wanxiang Che

SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution (2026.findings-acl)

Challenge:	Existing methods suffer from key information loss and difficulty in adjusting the length of compressed sequences based on documentation lengths.
Approach:	They propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models.
Outcome:	The proposed approach achieves comparable performance to the upper-bound baseline under 16x compression ratio.

Copied to clipboard

Zhenyu He, Qingping Yang, Wei Shen, Xiaojian Zhong, Kechi Zhang, Chenxin An, Wenlei Shi, Tianle Cai, Di He, Jiaze Chen, Jingjing Xu

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)

Challenge:	SWE-Swiss-32B demonstrates strong generalization to other common LLM benchmarks.
Approach:	They propose a two-phase training recipe that decomposes issue resolution into three core skills: Localization, Repair, and Unit Test Generation.
Outcome:	The proposed model achieves a 60.2% score on the SWE-bench Verified benchmark and is in the top-tier performance bracket of much larger models.

Copied to clipboard

Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Qiang Liu, Zhouchen Lin, Xu-Yao Zhang, Wentao Zhang, Bin Dong

Reasoning

Challenge:	Existing benchmarks designed to evaluate the reasoning capabilities of large models are limited in scope and lack flexibility to adapt difficulty according to evolving reasoning capacities of models.
Approach:	They propose a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.
Outcome:	The proposed benchmark incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.

FuseChat: Knowledge Fusion of Chat Models (2025.emnlp-main)

Copied to clipboard

Fanqi Wan, Longguang Zhong, Ziyi Yang, Ruijun Chen, Xiaojun Quan

WIKIBIAS: Detecting Multi-Span Subjective Biases in Language (2021.findings-emnlp)

Challenge:	Large language models (LLMs) are costly and require significant computational resources and time.
Approach:	They propose a fuse-and-merge framework for the knowledge fusion of chat LLMs . they conduct pairwise knowledge fusing on source chat LRMs to create multiple target LLM .
Outcome:	The proposed framework is superior to baselines of various sizes.

Copied to clipboard

Yang Zhong, Jingfeng Yang, Wei Xu, Diyi Yang

Communication-Efficient Desire Alignment for Proactive Embodied Human–Agent Interaction (2026.acl-long)

Challenge:	a particular type of bias is subjective bias, which introduces improper attitudes or presents a statement with the presupposition of truth.
Approach:	They propose to annotate a Wikipedia edits corpus with 4,000 sentence pairs to detect subjective bias.
Outcome:	The proposed dataset can be used as a research benchmark and generalize to multiple domains.

Copied to clipboard

Yuanfei Wang, Xinju Huang, Fangwei Zhong, Yaodong Yang, Yizhou Wang, Yuanpei Chen, Hao Dong

Green & Sustainable NLP

Challenge:	Effective real-world human–agent interactions are long-term and repeated.
Approach:	They propose a simulation that uses a proxy user with value-driven preferences and natural language behavior to evaluate how agents adapt to users across interactions and satisfy their desires.
Outcome:	HA-Desire, a home assistance simulation, shows that agents can adapt to user needs and provide proactive assistance within limited communication.

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models (2025.acl-long)

Copied to clipboard

Xueyan Zhang, Jinman Zhao, Zhifei Yang, Yibo Zhong, Shuhao Guan, Linbo Cao, Yining Wang

Causal-Debias: Unifying Debiasing in Pretrained Language Models and Fine-tuning via Causal Invariant Learning (2023.acl-long)

Challenge:	Existing methods such as LoRA and VeRA use a low-rank approximation method that reduces the number of trainable parameters without compromising performance.
Approach:	They propose a parameter-efficient fine-tuning approach that leverages a low-rank approximation method that reduces the number of trainable parameters without compromising performance.
Outcome:	The proposed approach outperforms existing methods on GLUE and E2E benchmarks and is effective in instruction-tuning large language models and image classification models.

Copied to clipboard

Fan Zhou, Yuzhou Mao, Liu Yu, Yi Yang, Ting Zhong

Robustness in NLP

Challenge:	Existing methods to remove unwanted stereotypical associations from pretrained language models (PLMs) are often focused on removing unwanted stereotypes from PLMs.
Approach:	They propose a framework to remove unwanted stereotypical associations in pretrained language models . they propose bias-relevant factors are causal, while labelrelevant factors causal .
Outcome:	The proposed framework reduces stereotypical associations after PLMs are fine-tuned . the proposed framework mitigates bias from a causal invariant perspective .

Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization (2025.naacl-long)

Copied to clipboard

Yang Zhong, Diane Litman

Summarization

Challenge:	Existing summarization systems can generate fluent summaries, but their ability to produce factually consistent summary remains questionable.
Approach:	They propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by NLI models.
Outcome:	The proposed framework shows better performance over multiple benchmarks, focusing on long document summarization.

Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)

Copied to clipboard

Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu

VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning (2024.acl-demos)

Challenge:	Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations.
Approach:	They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability.
Outcome:	The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants .

Copied to clipboard

Cheng Niu, Yang Guan, Yuanhao Wu, Juno Zhu, Juntong Song, Randy Zhong, Kaihua Zhu, Siliang Xu, Shizhe Diao, Tong Zhang

Reasoning

Challenge:	generative artificial intelligence has exacerbated the challenge of distinguishing genuine news from fabricated stories.
Approach:	They propose a retrieval-augmented system that extracts the core facts from a given piece of news and conducts an internet-wide search to identify corroborating or conflicting reports.
Outcome:	The proposed system has demonstrated state-of-the-art accuracy in the realm of fake news detection.

Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding (2024.findings-emnlp)

Copied to clipboard

Liang Zhao, Xiachong Feng, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin, Ting Liu

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization (2021.naacl-main)

Challenge:	Existing methods to enhance length extrapolation of large language models have been developed, but a systematic survey is lacking.
Approach:	They propose to examine the effects of positional encoding on length extrapolation.
Outcome:	The proposed methods improve the extrapolation of large language models, but they are still lacking a systematic survey.

Copied to clipboard

Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir Radev

100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability? (2025.findings-acl)

Challenge:	Existing work on meeting summarization tasks is limited to short summaries that cover all the content of a meeting.
Approach:	They propose a query-based multi-domain meeting summarization task that generates a single short summary of meetings based on a transcript.
Outcome:	The proposed task is based on 1,808 query-summary pairs over 232 meetings in multiple domains.

Copied to clipboard

Van Yang, Hongye Jin, Shaochen Zhong, Song Jiang, Qifan Wang, Vipin Chaudhary, Xiaotian Han

Challenge:	Existing benchmarks for long-context capability are too synthetic and do not represent the real world usage of LLMs.
Approach:	They propose a length-controllable, real-life reflective benchmark that disentangles baseline knowledge from long-context capabilities.
Outcome:	Experiments show that the proposed benchmarks disentangle baseline knowledge from long-context capabilities.

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)

Copied to clipboard

Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu

RShield: A User-level Traceable Backdoor Watermark for LLMs in Embedding-as-a-Service (2026.findings-acl)

Challenge:	Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning.
Approach:	They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking.
Outcome:	The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup.

Copied to clipboard

Lingyun Xiang, Yufan Zhong, Chengfu Ou, Zhihua Xia, Chunfang Yang, Daojian Zeng, Zhangjie Fu

Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking (2023.findings-acl)

Challenge:	Existing backdoor watermarking techniques are limited to zero-bit detection . RShield enables reliable user-level attribution of large language models under model extraction attacks.
Approach:	They propose a multi-bit backdoor watermarking technique that enables reliable user-level attribution of large language models under model extraction attacks.
Outcome:	RShield achieves 100% multi-bit watermark recovery and high semantic fidelity under model extraction attacks compared to existing methods.

Copied to clipboard

Mohamed Elaraby, Yang Zhong, Diane Litman

Modeling Intensification for Sign Language Generation: A Computational Approach (2022.findings-acl)

Challenge:	Existing summarization models struggle to accurately capture the main arguments of long legal opinions, leading to suboptimal summaries.
Approach:	They propose a framework for abstractive summarization of long legal opinions that takes into account the argument structure of the document and reranks them based on alignment with the document's argument structure.
Outcome:	The proposed approach outperforms several strong baselines on a dataset of long legal opinions and outperformed existing models.

Copied to clipboard

Mert Inan, Yang Zhong, Sabit Hassan, Lorna Quandt, Malihe Alikhani

SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)

Challenge:	End-to-end sign language generation models do not accurately represent prosody in sign language.
Approach:	They propose to model intensification in a data-driven manner to improve prosody in generated sign languages by modeling temporal and spatial variations.
Outcome:	The proposed models improve the prosody of generated sign languages by using data-driven models.

Copied to clipboard

Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang

Revisiting Representation Degeneration Problem in Language Modeling (2020.findings-emnlp)

Challenge:	Large language models (LLMs) have many advantages but they also pose significant safety risks.
Approach:	They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions .
Outcome:	The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets.

Copied to clipboard

Zhong Zhang, Chongming Gao, Cong Xu, Rui Miao, Qinli Yang, Junming Shao

Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval (2022.findings-emnlp)

Challenge:	Language modeling is a fundamental task in natural language processing, applications include machine translation, image captioning and speech recognition.
Approach:	They propose a cosine regularization method to solve the representation degeneration problem by analyzing the limitations of the proposed method and then propose an alternative regularization technique to tackle the problem.
Outcome:	The proposed method is effective in language modeling and image captioning.

Copied to clipboard

Wei Zhong, Jheng-Hong Yang, Yuqing Xie, Jimmy Lin

Information Retrieval

Challenge:	a recent study has shown that dense retrieval methods are suboptimal for capturing contextual similarities in complex data.
Approach:	They propose to combine a structure search method and efficient bi-encoder dense retrieval models to capture contextual similarities.
Outcome:	The proposed model improves on token-level and passage-level dense retrieval tasks.

PREME: Preference-based Meeting Exploration through an Interactive Questionnaire (2023.findings-eacl)

Copied to clipboard

Negar Arabzadeh, Ali Ahmadvand, Julia Kiseleva, Yang Liu, Ahmed Hassan Awadallah, Ming Zhong, Milad Shokouhi

Challenge:	Recent studies show that providing meeting summaries does not align with current approaches to document summarization.
Approach:	They propose a framework for generating questionnaires for preference-based meeting exploration . they measure how much questions are answerable to ensure factual correctness .
Outcome:	The proposed framework provides a list of suggested questions reflecting user preferences . it measures how much questions are answerable to ensure factual correctness .

T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)

Copied to clipboard

Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, Zhenhe Wu, Jiang Zhong, Shuangyong Song, Xuelong Li

Structured Data in NLP

Challenge:	Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications.
Approach:	They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning.
Outcome:	The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation.

Compare to The Knowledge: Graph Neural Fake News Detection with External Knowledge (2021.acl-long)

Copied to clipboard

Linmei Hu, Tianchi Yang, Luhao Zhang, Wanjun Zhong, Duyu Tang, Chuan Shi, Nan Duan, Ming Zhou

Ethical NLP

Challenge:	Existing methods for fake news detection rely on linguistic and semantic features from news content and do not exploit external knowledge.
Approach:	They propose a graph neural model which compares news to knowledge base through entities for fake news detection.
Outcome:	The proposed model significantly outperforms state-of-the-art methods on two benchmark datasets.

AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models (2026.findings-acl)

Copied to clipboard

Feng Luo, Yu-Neng Chuang, Guanchu Wang, Hoang Anh Duy Le, Shaochen Zhong, Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, Xia Hu

Context Consistency between Training and Inference in Simultaneous Machine Translation (2024.acl-long)

Challenge:	Existing approaches to distilling large language models (LLMs) are inefficient and generate excessively long chain-of-thought reasoning even for inputs that admit concise solutions.
Approach:	They propose a distillation framework that empowers non-reasoning LLMs to think only when necessary.
Outcome:	The proposed framework reduces reasoning length up to 71% with minimal accuracy loss while preserving accuracy.

Copied to clipboard

Meizhi Zhong, Lemao Liu, Kehai Chen, Mingming Yang, Min Zhang

Machine Translation

Challenge:	Simultaneous machine translation (SiMT) aims to yield a partial translation with a monotonically growing source-side context.
Approach:	They propose a training approach that encourages consistent context usage between training and inference by optimizing translation quality and latency as bi-objectives and exposing the predictions to the model during the training.
Outcome:	The proposed system outperforms existing SiMT systems with context inconsistency for the first time.

SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications (D18-1)

Copied to clipboard

Zexuan Zhong, Jiaqi Guo, Wei Yang, Jian Peng, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang

Taming the Real-world Complexities in CPT E/M Coding with Large Language Models (2025.emnlp-industry)

Challenge:	Existing approaches to generate programs from natural language do not address program aliasing . semantically equivalent programs may have many syntactically different forms .
Approach:	They propose a semantics-based approach to generate regular expressions from natural language.
Outcome:	The proposed approach improves on three public datasets.

Copied to clipboard

Islam Nassar, Yang Lin, Yuan Jin, Rongxin Zhu, Chang Wei Tan, Zenan Zhai, Nitika Mathur, Thanh Tien Vu, Xu Zhong, Long Duong, Yuan-Fang Li

DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)

Challenge:	Evaluation and Management (E/M) coding is performed by physicians and trained human coders who review clinical encounter notes and electronic health record data to assign appropriate codes.
Approach:	They propose a framework that automates evaluation and management coding tasks using the Current Procedural Terminology (CPT) taxonomy.
Outcome:	The proposed framework achieves an increase in coding accuracy of more than 36% over a commercial CPT E/M coding system and almost 5% over our strongest single-prompt baseline.

Copied to clipboard

Shaokai He, Kaiwen Wei, Xinyi Zeng, Xiang Chen, Xue Yang, Zhenyang Li, Jiang Zhong, Yu Tian

Unsupervised Multi-Granularity Summarization (2022.findings-emnlp)

Challenge:	Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs .
Approach:	They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations .
Outcome:	The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation .

Copied to clipboard

Ming Zhong, Yang Liu, Suyu Ge, Yuning Mao, Yizhu Jiao, Xingxing Zhang, Yichong Xu, Chenguang Zhu, Michael Zeng, Jiawei Han

Information Extraction & Text Mining

Challenge:	Experimental results confirm the substantial superiority of GranuSum on multi-granularity summarization over strong baselines.
Approach:	They propose to rank events by their salience and annotate a benchmark for GranuSum that contains multiple summaries at different granularities for each document cluster.
Outcome:	The proposed framework is capable of producing multi-granular summaries in unsupervised manner over strong baselines.

A Tale of Evaluating Factual Consistency: Case Study on Long Document Summarization Evaluation (2025.findings-acl)

Copied to clipboard

Yang Zhong, Diane Litman

Advancing Large Language Model Attribution through Self-Improving (2024.emnlp-main)

Challenge:	Despite the recent progress for summarization models in producing fluent summaries, they still encounter challenges when long sequences of generated texts and inputs (over thousands of words) need to be evaluated.
Approach:	They conduct a systematic analysis of factual-consistency evaluation systems across four long-document datasets and examine the relationship between sentence-level and summary-level model performance.
Outcome:	The proposed models can achieve higher recall in error detection for older summaries, yet struggle with false positives and fine-grained error detection.

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Liang Zhao, Yuchun Fan, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

Extending Context Window of Large Language Models from a Distributional Perspective (2024.emnlp-main)

Challenge:	Teaching large language models to generate text with citations to evidence sources requires high-quality attribution data, which is costly and labor-intensive.
Approach:	They propose a framework for iteratively improving the attribution capability of large language models (LLMs) by attributing output to verifiable sources.
Outcome:	Experiments on three open-domain question-answering datasets show that START improves in aggregating information across multiple sources.

Copied to clipboard

Yingsheng Wu, Yuxuan Gu, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

MedDCR: Learning to Design Agentic Workflows for Medical Coding (2026.findings-acl)

Challenge:	Existing scaling methods for extending context window rely on empirical approaches and lack understanding of the internal distribution within RoPE resulting in suboptimal performance.
Approach:	They propose to optimize the context window extending task from the view of rotary angle distribution by minimizing disturbance between rotary angles to maintain consistency with the pre-training phase.
Outcome:	The proposed approach reduces by up to 72% of the distributional disturbance when extending LLaMA2’s context window to 8k, and reduces it by up 32% when extending to 16k.

Copied to clipboard

Jiyang Zheng, Islam Nassar, Thanh Vu, Xu Zhong, Yang Lin, Tongliang Liu, Long Duong, Yuan-Fang Li

Challenge:	Medical coding is the process of translating unstructured clinical notes into standardized diagnostic and procedural codes.
Approach:	They propose a closed-loop framework that treats workflow design as a learning problem.
Outcome:	The proposed framework outperforms state-of-the-art workflows on benchmark datasets and produces interpretable, adaptable workflows that better reflect real coding practice.

From Information to Insight: Leveraging LLMs for Open Aspect-Based Educational Summarization (2025.acl-long)

Copied to clipboard

Yang Zhong, Diane Litman

Summarization

Challenge:	a novel dataset summarizes student reflections on STEM lectures . ReflectASP eases the exploration of open-aspect-based summarization (OABS) despite the limitations of current datasets, it is still under-explored.
Approach:	They propose a dataset that summarizes student reflections on STEM lectures . they propose two refinement methods to improve summaries .
Outcome:	The proposed dataset summarizes student reflections on STEM lectures using automatic and human evaluations.

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)

Copied to clipboard

Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang

Programming Languages in NLP

Challenge:	Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows .
Approach:	They propose a repository-level evaluation benchmark to assess security of AI-generated code.
Outcome:	The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation.

Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Copied to clipboard

Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models (2025.coling-main)

Challenge:	Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach:	They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome:	The proposed system outperforms baselines in the open domain task-solving benchmark.

Copied to clipboard

Li Yang, Zhiding Xiao, Wenxin Huang, Xian Zhong

LLEOT: A Privacy-Enhancing Offsite Tuning Framework via Loss Landscape Elevation (2026.findings-acl)

Challenge:	Existing models struggle to maintain temporal, spatial, and narrative coherence across image sequences . existing models lack depth and engagement of human-authored stories .
Approach:	They propose a topic-driven narrative optimizer that integrates image descriptions, topic generation, and GPT-4-based refinements.
Outcome:	The proposed framework outperforms existing models in visual relevance, coherence, and fluency.

Copied to clipboard

Jin Zhong, Jinglin Liang, Tongtong Yang, Zijian Xie, Shuangping Huang, Hanlin Gu