Papers by Yi Zhu

Sequence Structure Aware Retriever for Procedural Document Retrieval: A New Dataset and Baseline (2025.findings-emnlp)

Challenge:	Lowrank adaptation and its variants introduce significant latency in multi-tenant settings, hindering their applications in the industry.
Approach:	They propose a framework to fine-tune LoRA modules on a large-scale instruction tuning dataset.
Outcome:	The proposed framework outperforms existing PEFT methods and significantly reduces inference latency.

Copied to clipboard

Zhenqi Ye, HaoPeng Ren, Yi Cai, Qingbao Huang, Jing Qin, Pinli Zhu, Songwen Gong

Information Retrieval

Challenge:	Existing retrieval methods neglect the execution sequence structures inherent in procedural documents.
Approach:	They propose a retrieval model which integrates procedural graphs with document representations.
Outcome:	The proposed model integrates procedural graphs with document representations to improve document retrieval.

WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings (2023.acl-long)

Copied to clipboard

Wenjie Zhuo, Yifan Sun, Xiaohan Wang, Linchao Zhu, Yi Yang

A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters (2021.acl-long)

Challenge:	Extensive experiments on seven semantic textual similarity tasks show our method achieves consistent improvement over the contrastive learning baseline and sets new states of the art.
Approach:	They propose a whitening-based contrastive learning method for sentence embedding learning which combines contrastive and shuffled group whitening.
Outcome:	The proposed method achieves better alignment and uniformity on seven semantic textual similarity tasks.

Copied to clipboard

Mengjie Zhao, Yi Zhu, Ehsan Shareghi, Ivan Vulić, Roi Reichart, Anna Korhonen, Hinrich Schütze

On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)

Challenge:	Few-shot crosslingual transfer outperforms zero-shot with pretrained encoders like multilingual BERT.
Approach:	They conduct an experimental study on 40 sets of sampled few shots for six diverse NLP tasks across up to 40 languages.
Outcome:	The proposed model outperforms state-of-the-art approaches on lexical features and a full model finetuning approach outperformed several state- of-the art approaches.

Copied to clipboard

Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu

JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions (2023.findings-acl)

Challenge:	Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited.
Approach:	They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO).
Outcome:	The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness.

Copied to clipboard

Mo Yu, Yi Gu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell, Chuang Gan

Reasoning

Challenge:	Existing benchmarks focus on a single reasoning type and ask human annotators to write candidate statements related to the particular type of commonsense.
Approach:	They propose a new commonsense reasoning dataset based on human’s Interactive Fiction (IF) gameplaywalkthroughs.
Outcome:	The proposed dataset is challenging to previous machine reading models and large language models with a significant 20%performance gap compared to human experts.

Knowledge Graph-Guided Retrieval Augmented Generation (2025.naacl-long)

Copied to clipboard

Xiangrong Zhu, Yuexiang Xie, Yi Liu, Yaliang Li, Wei Hu

Structured Data in NLP

Challenge:	Existing studies on RAG focus on semantic retrieval of isolated relevant chunks, which ignore their intrinsic relationships.
Approach:	They propose a framework that utilizes knowledge graphs to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results.
Outcome:	Extensive experiments on the HotpotQA dataset and its variants demonstrate the advantages of KG2RAG compared to existing RAG-based approaches in terms of response quality and retrieval quality.

Chinese Lexical Substitution: Dataset and Method (2023.emnlp-main)

Copied to clipboard

Jipeng Qiang, Kang Liu, Ying Li, Yun Li, Yi Zhu, Yun-Hao Yuan, Xiaocheng Hu, Xiaoye Ouyang

Low-Resource NLP

Challenge:	Existing benchmarks for lexical substitution (LS) are limited and limited in coverage . despite extensive research on Lexical Substitution in various languages, there is limited evidence for LS in Chinese.
Approach:	They propose to use human and machine collaboration to construct a Chinese LS dataset . they combine four unsupervised LS methods to generate candidate substitutes .
Outcome:	The proposed method outperforms existing benchmarks on the Chinese lexical substitution task.

A Systematic Study of Leveraging Subword Information for Learning Word Representations (N19-1)

Copied to clipboard

Yi Zhu, Ivan Vulić, Anna Korhonen

Representation Learning

Challenge:	Existing word representation models for morphologically rich languages use subword-level information, but their systematic comparative analysis across typologically diverse languages and tasks is still missing.
Approach:	They propose a framework for learning subword-informed word representations that allows for easy experimentation with different segmentation and composition components.
Outcome:	The proposed framework allows for easy experimentation with different segmentation and composition components, as well as advanced techniques based on position embeddings and self-attention.

MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning (2024.findings-emnlp)

Copied to clipboard

Jingfan Zhang, Yi Zhao, Dan Chen, Xing Tian, Huanran Zheng, Wei Zhu

PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026.findings-acl)

Challenge:	Low-rank adaptation and its mixture-of-experts (MOE) methods are highly effective but introduce significant latency in multi-tenant settings due to the LoRA modules and MOE routers added to multiple linear modules.
Approach:	They propose a low-rank adaptation variant that considers each LoRA module as an expert and employs a prompt-aware routing mechanism.
Outcome:	Extensive analysis on commonsense reasoning tasks and math reasoning tasks show that MiLoRA outperforms strong PEFT baselines with comparable tunable parameter budgets.

Copied to clipboard

Chengbing Wang, Wuqiang Zheng, Yang Zhang, Fengbin Zhu, Junyi Cheng, Yi Xie, Wenjie Wang, Fuli Feng

When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents (2026.acl-long)

Challenge:	Existing reward models evaluate empathy from a single perspective, overlooking bidirectional interaction nature of empathy.
Approach:	They propose a reward model that evaluates empathy from a single perspective . they propose PERM to integrate a bystander perspective to monitor overall interaction quality .
Outcome:	a new reward model outperforms state-of-the-art models on an emotional intelligence benchmark and an industrial daily conversation dataset.

Copied to clipboard

Liang-Bo Ning, Yuchen Zhu, Heqing Huang, Xin Wang, Yi Chang, Li Qing, Wenqi Fan

LIRE: listwise reward enhancement for preference alignment (2024.findings-acl)

Challenge:	Existing WebAgents suffer from computational cost attacks due to long reasoning processes and excessive computational cost.
Approach:	They propose a framework that generates adversarial prompts and a reinforcement learning-enhanced selector to identify the most effective perturbations.
Outcome:	The proposed framework exploits large language models to generate diverse adversarial prompts and a reinforcement learning–enhanced selector to identify the most effective perturbations.

Copied to clipboard

Mingye Zhu, Yi Liu, Lei Zhang, Junbo Guo, Zhendong Mao

Challenge:	prevailing approaches to preference alignment focus on pairwise comparisons, with limited exploration into multi-response scenarios.
Approach:	They propose a listwise reward enhancement approach that integrates offline rewards of multiple responses into a streamlined listwise framework.
Outcome:	The proposed approach outperforms existing methods on dialogue and summarization tasks with good transferability to out-of-distribution data.

Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation (2024.acl-long)

Copied to clipboard

Yi Liu, Xiangyu Liu, Xiangrong Zhu, Wei Hu

Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Sampling (2025.emnlp-main)

Challenge:	Existing studies neglect attribute correlations formed by the intertwining of different attributes.
Approach:	They propose a multi-aspect controllable text generation method with disentangled counterfactual augmentation that alleviates imbalanced attribute correlations during training by disentanglement.
Outcome:	The proposed method outperforms state-of-the-art methods in imbalanced and balanced attribute correlation scenarios.

Copied to clipboard

Zhenning Shi, Yijia Zhu, Yi Xie, Junhan Shi, Guorui Xie, Haotian Zhang, Yong Jiang, Congcong Miao, Qing Li

Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework (2025.emnlp-main)

Challenge:	Large language models suffer from overconfidence and computational inefficiency due to fixed computation budgets and miscalibrated confidence estimates.
Approach:	They propose a framework for computationally efficient, trustworthy reasoning under uncertainty using Diversity-Aware Self-Signal Dilution and Convergent Adaptive Weighted Sampling techniques.
Outcome:	The proposed framework reduces inference cost by 70% while maintaining accuracy levels while reducing inference costs.

Copied to clipboard

Hongyi Tang, Zhihao Zhu, Yi Yang

ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection (2026.findings-acl)

Challenge:	Existing methods for detecting pre-training data in large language models rely on superficial features like prediction confidence and loss, resulting in mediocre performance.
Approach:	They propose a new algorithm to analyze neuron activation patterns between training and non-training data in large language models to improve their performance.
Outcome:	The proposed algorithm outperforms existing methods across three benchmarks and multiple LLMs.

Copied to clipboard

Benjamin Shiue-Hal Chou, Yi Zhu, Surya Koppisetti

An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languages (2021.findings-emnlp)

Challenge:	Audio deepfake detection systems do not generalize well to realistic in-the-wild deepfakkes.
Approach:	They propose a novel In-Context Learning paradigm with comparison-guidance for Audio Deepfake detection framework that uses audio language models for training-free generalization to unseen deepfakes.
Outcome:	The proposed framework improves macro F1 over specialized detectors on in-the-wild datasets with up to 2 relative improvement over existing models.

Copied to clipboard

Xinyu Lu, Jipeng Qiang, Yun Li, Yunhao Yuan, Yi Zhu

Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents (2025.emnlp-main)

Challenge:	Existing methods to build parallel sentence simplification corpora are limited . SS is used to rephrase sentences into simpler forms for those with cognitive disabilities .
Approach:	They propose to build SS corpora from large-scale bilingual translation corpors using a parallel approach.
Outcome:	The proposed method outperforms the existing methods on WikiLarge and achieves state-of-the-art results.

Copied to clipboard

Xueqiao Zhang, Chao Zhang, Jingtao Xu, Yifan Zhu, Xin Shi, Yi Yang, Yawei Luo

Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction (2023.emnlp-main)

Challenge:	Existing approaches to RPAs focus on static role profiles, overlooking dynamic perceptual abilities inherent to humans.
Approach:	They propose a framework that combines adaptive temporal sampling with dynamic and static role profiles.
Outcome:	The proposed framework combines adaptive temporal sampling with dynamic and static role profiles.

Copied to clipboard

Chong Zhang, Ya Guo, Yi Tu, Huan Chen, Jinyang Tang, Huijia Zhu, Qi Zhang, Tao Gui

MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences (2021.naacl-main)

Challenge:	Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs).
Approach:	They propose a method to predict token sequences within visually-rich documents by a simple prediction head.
Outcome:	The proposed method can be used to predict token mentions as token sequences within documents.

Copied to clipboard

Jianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu, Azaan Rehman, Amir Zadeh, Soujanya Poria, Louis-Philippe Morency

MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures - A Comprehensive Framework (2025.findings-emnlp)

Challenge:	a novel graph-based neural model for multimodal sequential data is proposed . fusion is the process of blending information from multiple modalities, usually preceded by alignment .
Approach:	They propose a graph-based neural model that converts unaligned data into a modal-temporal graph . they use a dynamic pruning and read-out technique to efficiently process the graph fusion operation .
Outcome:	The proposed model performs state-of-the-art on multimodal sentiment analysis and emotion recognition benchmarks while utilizing significantly fewer model parameters.

Copied to clipboard

Yifan Zhu, Chao Zhang, Xin Shi, Xueqiao Zhang, Yi Yang, Yawei Luo

Robustness in NLP

Challenge:	Large Language Models (LLMs)-based Multi-Agent Systems (MAS) exhibit remarkable problem-solving and task planning capabilities across diverse domains .
Approach:	They propose a security research framework for LLM-based multi-agent systems . they propose corresponding defense strategies to address MAS security risks .
Outcome:	The proposed framework amplifies the severity of security risks under MAS attacks . it offers an automated construction process for different MAS setups and an interaction paradigm .

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

Tailoring Instructions to Student’s Learning Levels Boosts Knowledge Distillation (2023.acl-long)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Yuxin Ren, Zihan Zhong, Xingjian Shi, Yi Zhu, Chun Yuan, Mu Li

Text Augmented Spatial Aware Zero-shot Referring Image Segmentation (2023.findings-emnlp)

Challenge:	Recent success of natural language processing (NLP) is driven by the adoption of large-scale pretrained language models.
Approach:	They propose a method to determine the impact of distillation influence on student generalization ability by prioritizing samples likely to enhance the student's generalization abilities.
Outcome:	The proposed method outperforms 10 common knowledge distillation baselines on 6 text classification tasks in the GLUE benchmark.

Copied to clipboard

Yucheng Suo, Linchao Zhu, Yi Yang

Visual Data in NLP

Challenge:	Existing zero-shot referring image segmentation methods focus on global-level alignment of image-text pairs, neglecting fine-grained matching between referring sentence and local image regions.
Approach:	They propose a zero-shot referring image segmentation task that is training-free . they use a mask proposal network and a text-augmented spatial-correction score .
Outcome:	The proposed method outperforms state-of-the-art zero-shot referring image segmentation methods.

RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought (2025.acl-long)

Copied to clipboard

Yi Lu, Jiawang Cao, Yongliang Wu, Bozheng Li, Licheng Tang, Yangguang Ji, Chong Wu, Jay Wu, Wenbo Zhu

Guiding Medical Vision-Language Models with Diverse Visual Prompts: Framework Design and Comprehensive Exploration of Prompt Variations (2025.naacl-long)

Challenge:	Recent advances in multi-modal learning have enhanced MLLMs' ability to reason about visual content.
Approach:	They propose a framework that unifies multi-step multimodal reasoning with grounded visual understanding.
Outcome:	The proposed framework surpasses state-of-the-art methods by +6.5 gIoU and +9.2 cIou on ReasonSeg and achieves 49.7 mAP on SegInW under zero-shot settings.

Copied to clipboard

Kangyu Zhu, Ziyuan Qin, Huahui Yi, Zekun Jiang, Qicheng Lao, Shaoting Zhang, Kang Li

TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)

Challenge:	Current vision-language models lack the ability to focus on specific areas designated by humans . a new framework that integrates medical entity extraction, visual prompt generation, and dataset adaptation is proposed to improve visual prompt-guided fine-tuning.
Approach:	They propose to use visual prompts to guide and enhance formation of region-specific attention.
Outcome:	The proposed framework outperforms state-of-the-art large vision-language models on medical datasets.

Copied to clipboard

Bei Li, Yi Jing, Xu Tan, Zhen Xing, Tong Xiao, Jingbo Zhu

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation (2022.acl-long)

Challenge:	Prior work has focused on treating subwords as basic units in developing such systems.
Approach:	They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences.
Outcome:	The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks.

Copied to clipboard

Bei Li, Quan Du, Tao Zhou, Yi Jing, Shuhan Zhou, Xin Zeng, Tong Xiao, JingBo Zhu, Xuebo Liu, Min Zhang

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)

Challenge:	Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE).
Approach:	They propose a residual block of layers in Transformer that can be described as a higher-order solution to ODE.
Outcome:	The proposed architecture can gain large improvements over strong baselines at a slight cost in inference efficiency.

Copied to clipboard

Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen, Baichuan Zhou, Shenzhe Zhu, Yi Lu, Haozhe Wang, Chi Ruan, Benjamin Schneider, Weixu Zhang, Xiang Li, Andy Zheng, Yuyu Zhang, Ping Nie, Wenhu Chen

ParaLS: Lexical Substitution via Pretrained Paraphraser (2023.acl-long)

Challenge:	Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge.
Approach:	They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance.
Outcome:	Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points.

Copied to clipboard

Jipeng Qiang, Kang Liu, Yun Li, Yunhao Yuan, Yi Zhu

Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections (2020.lrec-1)

Challenge:	Lexical substitution (LS) is an extremely powerful technology that can be used as a backbone of various NLP applications such as writing assistance.
Approach:	They propose two simple decoding strategies that focus on the variations of the target word during decoding to generate substitutes from a paraphraser.
Outcome:	The proposed methods outperform state-of-the-art LS methods based on pre-trained language models on three benchmarks.

Copied to clipboard

Yi-An Lai, Xuan Zhu, Yi Zhang, Mona Diab

Information Retrieval

Challenge:	Existing descriptive statistics are inadequate to summarize text collections by quantitative measures.
Approach:	They propose a set of characteristic metrics that quantitatively measure the dispersion, sparsity, and uniformity of a text collection.
Outcome:	The proposed metrics are highly correlated with text classification performance of a renowned model, which could inspire future applications.

Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification (2021.eacl-main)

Copied to clipboard

Yi Zhu, Ehsan Shareghi, Yingzhen Li, Roi Reichart, Anna Korhonen

Information Extraction & Text Mining

Challenge:	Semi-supervised learning and multilingual pretraining have been shown to be effective for task-specific labelled data shortages.
Approach:	They propose to combine semi-supervised deep generative models and multi-lingual pretraining to form a pipeline for document classification task.
Outcome:	The proposed method outperforms state-of-the-art models in low-resource settings across several languages and outperformed existing models in English.

RelCLIP: Adapting Language-Image Pretraining for Visual Relationship Detection via Relational Contrastive Learning (2022.emnlp-main)

Copied to clipboard

Yi Zhu, Zhaoqing Zhu, Bingqian Lin, Xiaodan Liang, Feng Zhao, Jianzhuang Liu

FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMs (2025.findings-emnlp)

Challenge:	Existing visual relationship detection models only use numeric ids of relation labels for training, but ignore semantic correlation between labels.
Approach:	They propose a visual Relationship prediction framework that transfers natural language knowledge from Contrastive Language-Image Pre-training models to enhance the relationship prediction.
Outcome:	The proposed framework improves visual relationship prediction by matching semantic correlations with relation triplets.

Copied to clipboard

Yingjia Wan, Haochen Tan, Xiao Zhu, Xinyu Zhou, Zhiwei Li, Qingsong Lv, Changxuan Sun, Jiaqi Zeng, Yi Xu, Jianqiao Lu, Yinhong Liu, Zhijiang Guo

Chinese Idiom Paraphrasing (2023.tacl-1)

Challenge:	Prior evaluation pipelines fail to evaluate factuality of long-form LLMs due to inefficiency and costly human assessment.
Approach:	They propose a fast and strong evaluation pipeline that can evaluate factuality of long-form LLMs . they propose 'faStFact' to reduce cost of web searching and inference calling .
Outcome:	The proposed evaluation pipeline achieves highest alignment with human evaluation and efficiency among existing baselines.

Copied to clipboard

Jipeng Qiang, Yang Li, Chaowei Zhang, Yun Li, Yi Zhu, Yunhao Yuan, Xindong Wu

Grounded Multimodal Procedural Entity Recognition for Procedural Documents: A New Dataset and Baseline (2024.lrec-main)

Challenge:	Chinese idioms are hard to understand by children and non-native speakers due to their non-compositionality and metaphorical meaning.
Approach:	They propose a task to rephrase idiom-containing sentences to non-idiomatic ones under the premise of preserving the original sentence’s meaning.
Outcome:	The proposed method has better performance than baselines based on the established dataset.

Copied to clipboard

Haopeng Ren, Yushi Zeng, Yi Cai, Zhenqi Ye, Li Yuan, Pinli Zhu

Information Extraction & Text Mining

Challenge:	Existing methods to extract procedural knowledge from documents focus on text-only settings, which is insufficient for entity disambiguation.
Approach:	They propose a model to detect the entity and the corresponding bounding box groundings in images.
Outcome:	The proposed model detects the entity and the corresponding bounding box groundings in image (i.e., visual entities) it is based on a dataset of a WikiHow 1 and EHow 2 document and the results are compared with existing models.

Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection (2022.findings-emnlp)

Copied to clipboard

Chenglong Wang, Yi Lu, Yongyu Mu, Yimin Hu, Tong Xiao, Jingbo Zhu

Abstract then Play: A Skill-centric Reinforcement Learning Framework for Text-based Games (2023.findings-acl)

Challenge:	Existing studies on knowledge distillation have shown that not all knowledge is necessary for learning a good student model.
Approach:	They propose an actor-critic approach to selecting appropriate knowledge to transfer during the process of knowledge distillation.
Outcome:	The proposed method outperforms several strong knowledge distillation baselines significantly on the GLUE datasets.

Copied to clipboard

Anjie Zhu, Peng-Fei Zhang, Yi Zhang, Zi Huang, Jie Shao

Challenge:	Existing reinforcement learning frameworks fail to decompose the task and abstract the action autonomously.
Approach:	They propose a skill-centric reinforcement learning framework capable of abstracting the action in an end-to-end manner.
Outcome:	Empirical experiments on the Jericho environment validate the proposed framework against state-of-the-art baselines.

Bayesian Learning for Neural Dependency Parsing (N19-1)

Copied to clipboard

Ehsan Shareghi, Yingzhen Li, Yi Zhu, Roi Reichart, Anna Korhonen

Syntactic Text Processing

Challenge:	Several approaches for dependency parsing in the small data regime have been proposed.
Approach:	They propose to use stochastic gradient Langevin dynamics to generate samples from the approximated posterior to overcome the computational and statistical costs of the approximate inference step.
Outcome:	The proposed model outperforms the biaffine model on 6 languages with less than 5k training instances and improves across five languages.

Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding (2024.emnlp-main)

Copied to clipboard

Chong Zhang, Yi Tu, Yixi Zhao, Chenshu Yuan, Huan Chen, Yue Zhang, Mingxu Chai, Ya Guo, Huijia Zhu, Qi Zhang, Tao Gui

TARN-VIST: Topic Aware Reinforcement Network for Visual Storytelling (2024.lrec-main)

Challenge:	Existing models of layout reading order do not convey the complete reading order information in the layout.
Approach:	They propose to model layout reading order as ordering relations over layout elements . they propose a reading-order-relation-enhancing pipeline to improve model performance .
Outcome:	The proposed model outperforms existing models on a visual-rich document dataset and on eight cross-domain VrD-IE/QA tasks without targeted optimization.

Copied to clipboard

Weiran Chen, Xin Li, Jiaqi Su, Guiqian Zhu, Ying Li, Yi Ji, Chunping Liu

Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank (C18-1)

Challenge:	Existing methods for visual storytelling ignore latent topic information.
Approach:	They propose a topic-aware reinforcement network for VIsual StoryTelling that takes topic information into account to generate a coherent story.
Outcome:	The proposed method outperforms most of the competing models across multiple evaluation metrics.

Copied to clipboard

Xiaomin Chu, Feng Jiang, Yi Zhou, Guodong Zhou, Qiaoming Zhu

Gloss-Free End-to-End Sign Language Translation (2023.acl-long)

Challenge:	Discourse parsing is a challenging task and plays a critical role in discourse analysis.
Approach:	They propose a macro discourse structure presentation schema to present the macro level discourse structure analysis.
Outcome:	The proposed corpus is based on two tasks of macro discourse structure analysis, including structure identification and nuclearity recognition.

Copied to clipboard

Kezhou Lin, Xiaohan Wang, Linchao Zhu, Ke Sun, Bang Zhang, Yi Yang

Machine Translation

Challenge:	a study of sign language translation without gloss annotations focuses on the problem of gloss annotation . gloss annotation is hard to acquire, especially in large quantities, and limits the domain coverage of translation datasets .
Approach:	They propose a gloss-free end-to-end sign language translation framework to solve this problem . gloss annotations are hard to acquire, especially in large quantities, they argue .
Outcome:	The proposed framework improves sign language translation performance on large-scale datasets . gloss annotations are hard to acquire, especially in large quantities .

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model (2025.emnlp-main)

Copied to clipboard

Zhongyi Zhou, Yichen Zhu, Minjie Zhu, Junjie Wen, Ning Liu, Zhiyuan Xu, Weibin Meng, Yaxin Peng, Chaomin Shen, Feifei Feng, Yi Xu

Recognizing Conflict Opinions in Aspect-level Sentiment Classification with Dual Attention Networks (D19-1)

Challenge:	Recent advances in vision-language-action models prioritize robotic action mastery . however, models trained on visual-text pairs struggle to interpret multimodal data .
Approach:	They propose a framework that integrates multimodal data after initial control mastery and a Mixture-of-Experts architecture to minimize task interference.
Outcome:	The proposed framework surpasses state-of-the-art vision-language-action (VLA) methods on multimodal understanding benchmarks and achieves six times higher performance on visual question-answering datasets.

Copied to clipboard

Xingwei Tan, Yi Cai, Changxi Zhu

Sentiment Analysis

Challenge:	Existing models ignore conflict opinions because they are sparse in the datasets.
Approach:	They propose a multi-label classification model with dual attention mechanism to address these problems by excluding conflict opinions from existing models.
Outcome:	The proposed model addresses the problem of exclusion of conflict opinions from the datasets.

PARA: Parameter-Efficient Fine-tuning with Prompt-Aware Representation Adjustment (2024.emnlp-industry)

Copied to clipboard

Zequan Liu, Yi Zhao, Ming Tan, Wei Zhu, Aaron Tian

DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization (2025.findings-emnlp)

Challenge:	Existing methods for parameter-efficient fine-tuning excel in the context of single-backbone multi-tenant applications.
Approach:	They propose to integrate a lightweight vector generator within each Transformer layer to improve prompt-aware representation adjustment.
Outcome:	The proposed method surpasses current benchmarks in terms of performance despite having a similar number of adjustable parameters.

Copied to clipboard

Chao Zhang, Xin Shi, Xueqiao Zhang, Yifan Zhu, Yi Yang, Yawei Luo

VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft (2024.findings-acl)

Challenge:	Existing ESC data entangles psychological strategies and response content, making it difficult to construct high-quality preference pairs.
Approach:	They propose a Decoupled ESC framework that decomposes the ESC task into two sequential subtasks: strategy planning and empathic response generation.
Outcome:	The proposed framework outperforms baselines, reducing preference bias and improving response quality.

Copied to clipboard

Yubo Dong, Xukun Zhu, Zhengzhe Pan, Linchao Zhu, Yi Yang

Structured Data in NLP

Challenge:	Multi-agent collaboration using LLMs is a challenging research topic that aims to enable multiple autonomous agents to coordinate their actions and achieve a common goal.
Approach:	They propose a benchmark for multi-agent collaboration in the Minecraft environment and introduce a Directed Acyclic Graph Multi-Agent Framework to resolve complex inter-ag dependencies.
Outcome:	The proposed framework outperforms existing ModelVerse, reducing hallucinations and improving task decomposition efficacy.

MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)

Copied to clipboard

Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, yi Chen, Boran Wang, Yingjian Zhu, Hongzhu Yi, Hong-Ming Yang, Han Hu, Cheng-Lin Liu, Xu-Yao Zhang

Reasoning

Challenge:	Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited.
Approach:	They propose a Meta-Reasoning informed alignment framework that quantifies state-transition probabilities along the model’s thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments.
Outcome:	Empirical evaluations of four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning.

Collaborative Document Simplification Using Multi-Agent Systems (2025.coling-main)

Copied to clipboard

Dengzhao Fang, Jipeng Qiang, Xiaoye Ouyang, Yi Zhu, Yunhao Yuan, Yun Li

Post-Hoc Watermarking for Robust Detection in Text Generated by Large Language Models (2025.coling-main)

Challenge:	Document simplification requires complex factors such as technical terminology, metaphors, and overall coherence.
Approach:	They propose a multi-agent framework for document simplification based on large language models that emulates the collaborative process of a human expert team through the roles played by multiple agents.
Outcome:	The proposed framework emulates the collaborative process of a human expert team through the roles played by multiple agents, addressing the intricate demands of document simplification.

Copied to clipboard

Jifei Hao, Jipeng Qiang, Yi Zhu, Yun Li, Yunhao Yuan, Xiaoye Ouyang

NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment (2026.eacl-long)

Challenge:	Existing methods for document simplification address complex factors such as technical terminology, metaphors, and overall coherence.
Approach:	They propose a multi-agent framework AgentSimp for document simplification based on large language models that simulates collaboration among agents through roles played by multiple agents.
Outcome:	The proposed framework produces simplified documents that are more thoroughly simplified and more coherent across various articles and styles.

Copied to clipboard

Antonia Karamolegkou, Angana Borah, Eunjung Cho, Sagnik Ray Choudhury, Martina Galletti, Pranav Gupta, Oana Ignat, Priyanka Kargupta, Neema Kotonya, Hemank Lamba, Sun-Joo Lee, Arushi Mangla, Ishani Mondal, Fatima Zahra Moudakir, Deniz Nazar, Poli Nemkova, Dina Pisarevskaya, Naquee Rizwan, Nazanin Sabri, Keenan Samway, Dominik Stammbach, Anna Steinberg Schulten, David Tomás, Steven R Wilson, Bowen Yi, Jessica H Zhu, Arkaitz Zubiaga, Anders Søgaard, Alexander Fraser, Zhijing Jin, Rada Mihalcea, Joel R. Tetreault, Daryna Dementieva

Learning the Beauty in Songs: Neural Singing Voice Beautifier (2022.acl-long)

Challenge:	This paper surveys work in "NLP for Social Good" across nine domains relevant to global development and risk agendas.
Approach:	This paper analyzes work in "NLP for Social Good" across nine domains relevant to global development and risk agendas.
Outcome:	The paper analyzes work in "NLP for Social Good" across nine domains relevant to global development and risk agendas.

Copied to clipboard

Jinglin Liu, Chengxi Li, Yi Ren, Zhiying Zhu, Zhou Zhao

Speech & Audio in NLP

Challenge:	Existing techniques for pitch correction are limited to intonation but ignore the overall aesthetic quality.
Approach:	They propose a novel time-warping approach for pitch correction to synchronize the amateur recording with the template pitch curve.
Outcome:	The proposed model improves intonation and vocal tone while keeping content and vocal timbre.

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization (2024.emnlp-main)

Copied to clipboard

Mingye Zhu, Yi Liu, Quan Wang, Junbo Guo, Zhendong Mao

Challenge:	Recent advances in preference alignment have significantly improved Large Language Models' ability to generate texts that align with human preferences and values.
Approach:	They propose a constrained optimization approach to detect and mitigate update regression with focal attention.
Outcome:	The proposed approach detects and mitigates update regression with focal attention while maintaining excellent overall performance.

OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)

Copied to clipboard

He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou

Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition (2025.findings-emnlp)

Challenge:	a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say .
Approach:	They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible .
Outcome:	The proposed framework achieves state-of-the-art performance among open-source projects.

Copied to clipboard

Yi Liu, Xiangrong Zhu, Xiangyu Liu, Wei Wei, Wei Hu

Natural Language Interfaces

Challenge:	Existing methods for knowledge editing fail to work in multi-hop question answering due to 'edit skipping' edit skipping occurs due to the mismatch between the granularity of LLMs in problem-solving and the facts in the edited memory.
Approach:	They propose a retrieval-augmented generation-based method that edits knowledge without modifying parameters without retraining LLMs.
Outcome:	The proposed method outperforms state-of-the-art methods for KE in multi-hop question answering.

Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models (2024.findings-naacl)

Copied to clipboard

Rui Wang, Fei Mi, Yi Chen, Boyang Xue, Hongru Wang, Qi Zhu, Kam-Fai Wong, Ruifeng Xu

Seq2Path: Generating Sentiment Tuples as Paths of a Tree (2022.findings-acl)

Challenge:	Large Language Models (LLMs) suffer catastrophic forgetting when tailored to specific domains . authors present a novel approach to manage multi-domain LLM adaptation .
Approach:	They propose a strategy to manage multi-domain LLM adaptation using self-distillation and role integration.
Outcome:	The proposed model alleviates catastrophic forgetting and inter-domain confusion while maintaining robust general capabilities.

Copied to clipboard

Yue Mao, Yi Shen, Jingchao Yang, Xiaoying Zhu, Longjun Cai

Sentiment Analysis

Challenge:	Existing generative methods for extracting sentiment tuples do not have orders between the t-uples . a novel parallel generative framework for ABSA is proposed .
Approach:	They propose a parallel generative framework to generate sentiment tuples as paths of a tree . they train the model with an independent target and introduce a discriminative token .
Outcome:	The proposed method achieves state-of-the-art on AOPE, ASTE, TASD, UABSA, ACOS . it trains with the loss of ordinary Seq2Seq averaged over paths, and inferences automatically select valid paths.

Parsing Tweets into Universal Dependencies (N18-1)

Copied to clipboard

Yijia Liu, Yi Zhu, Wanxiang Che, Bing Qin, Nathan Schneider, Noah A. Smith

Syntactic Text Processing

Challenge:	a new tweet treebank for English is designed to analyze tweets with universal dependencies (UD).
Approach:	They extend the universal dependencies guidelines to include special constructions in tweets that affect tokenization, part-of-speech tagging, and labeled dependencies.
Outcome:	The proposed method outperforms state-of-the-art parsers on other treebanks in accuracy and speed.

AI4Reading: Chinese Audiobook Interpretation System Based on Multi-Agent Collaboration (2025.acl-demo)

Copied to clipboard

Minjiang Huang, Jipeng Qiang, Yi Zhu, Chaowei Zhang, Xiangyu Zhao, Kui Yu

FragRel: Exploiting Fragment-level Relations in the External Memory of Large Language Models (2024.findings-acl)

Challenge:	Interpretative audiobooks are becoming more popular, but their manual creation process remains time-consuming and resource-intensive.
Approach:	They propose a multi-agent collaboration system that leverages large language models and speech synthesis technology to generate podcast-like audiobook interpretations.
Outcome:	The proposed system is open source and open to the public.

Copied to clipboard

Xihang Yue, Linchao Zhu, Yi Yang