Papers by Zhenyu Zhang

Dialog-Post: Multi-Level Self-Supervised Objectives and Hierarchical Model for Dialogue Post-Training (2023.acl-long)

Challenge:	Existing approaches to multimodal representation learning focus on directional alignment and embedding magnitudes (L2-norm) however, these methods often fail to account for the intrinsic role of L2-norm in the contrastive process.
Approach:	They propose a plug-and-play framework that optimizes L2-norm alignment and Directional consistency jointly.
Outcome:	The proposed framework achieves consistent and significant performance gains over established baselines across 95 tasks using UniIR and VLM2Vec-V2 frameworks.

Copied to clipboard

Zhenyu Zhang, Lei Shen, Yuming Zhao, Meng Chen, Xiaodong He

Dialogue Systems & Conversational Agents

Challenge:	a new method for dialogue representation and understanding is proposed . pre-trained language models (PLMs) are inappropriate for dialogue understanding tasks .
Approach:	They propose a method that trains pre-trained language models to fit dialogues . they use a hierarchical segment-wise self-attention network to model dialogues more comprehensively .
Outcome:	The proposed method outperforms existing models and achieves a 3.3% improvement on average.

Label Anchored Contrastive Learning for Language Understanding (2022.naacl-main)

Copied to clipboard

Zhenyu Zhang, Yuming Zhao, Meng Chen, Xiaodong He

Causal-ESC: Reliable Policy Learning for Emotional Support Conversation via Causal Inference (2026.acl-long)

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

Copied to clipboard

Xv Wang, Wang Zhenyu, Guanyu Zheng, Rui Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing approaches to Emotional Support Conversation (ESC) are mechanistically opaque and lacks a causal mechanism between dialogue features and effective empathic strategies.
Approach:	They propose a framework that uses Doubly Robust learning to model causal effects of utterance features on strategy selection.
Outcome:	The proposed framework outperforms state-of-the-art baselines in empathy and helpfulness and provides a theoretically grounded, interpretable solution to the mechanistic interpretability dilemma in affective computing.

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs (2026.acl-long)

Copied to clipboard

Zhenyu Liu, Xuanyu Zhang, Yunxin li, Qixun Teng, Shenyuan Jiang, Haolan Chen, Mingjun Zhao, Fanbo Meng, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG (2025.findings-naacl)

Challenge:	despite significant progress, full-duplex SLMs are constrained by severe modality interference, authors say . modality interferes with acoustic and semantic modeling, making them unintelligent and unnatural . authors propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers .
Approach:	They propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel.
Outcome:	The proposed method significantly advances the state of the art on full-duplex benchmarks . it decouples conflicting modalities in deep layers while preserving cross-modality coherence .

Copied to clipboard

Xinping Zhao, Yan Zhong, Zetian Sun, Xinshuo Hu, Zhenyu Liu, Dongfang Li, Baotian Hu, Min Zhang

Green & Sustainable NLP

Challenge:	Retrieval-Augmented Generation (RAG) is widely adopted in Large Language Models, but is flat and has limitations such as a significant burden on one retriever and constant granularity limits the ceiling of retrieval performance.
Approach:	They propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency.
Outcome:	The proposed paradigm achieves comparable retrieval performance while the time overhead is reduced by nearly 40%.

Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics (2026.acl-long)

Copied to clipboard

Yilong Chen, Junyuan Shang, Yuchen Feng, Zhenyu Zhang, Naibin Gu, Ziqi Wang, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang

Challenge:	Mixture-of-Experts (MoE) is a cornerstone for scaling LLMs, yet its training dynamics remain poorly understood, often leading to sub-optimal specialization.
Approach:	They propose to use Helmholtz Free Energy and Router Entropy to study the MoE lifecycle and identify a universal Three-Stage Phase Transition .
Outcome:	The proposed model reduces perplexity and improves expert distinctiveness, offering a principled path toward thermodynamically aligned computation.

Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning (2026.eacl-long)

Copied to clipboard

Qifan Yu, Zhenyu He, Sijie Li, Zhou Xun, Jun Zhang, Jingjing Xu, Di He

“I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents (2025.emnlp-main)

Challenge:	Chain-of-Thought prompting is a powerful technique for enhancing language model’s reasoning capabilities, but generating long and correct CoT trajectories is challenging.
Approach:	They propose to align the steps of Chain-of-Thought reasoning with loop iterations and apply intermediate supervision during the training of Looped Transformers.
Outcome:	The proposed method generates accurate reasoning chains for complex problems exceeding training length, and improves performance of the auto-regressive model.

Copied to clipboard

Jianshuo Dong, Yutong Zhang, Liu Yan, Zhenyu Zhong, Tao Wei, Ke Xu, Minlie Huang, Chao Zhang, Han Qiu

Improving Attributed Text Generation of Large Language Models via Preference Learning (2024.findings-acl)

Challenge:	Large language models (LLMs) exhibit prompt leakage vulnerabilities, raising intellectual property and confidentiality concerns.
Approach:	They use probing techniques to capture LLMs’ intent-related internal representations and show that they internalize prompt leakage intents in their hidden states before generating tokens.
Outcome:	The proposed probes achieve 90%+ AUROC across all tested models, even when applied to new system prompts and attacks.

Copied to clipboard

Dongfang Li, Zetian Sun, Baotian Hu, Zhenyu Liu, Xinshuo Hu, Xuebo Liu, Min Zhang

StructuThink: Reasoning with Task Transition Knowledge for Autonomous LLM-Based Agents (2025.findings-emnlp)

Challenge:	Large language models have been widely adopted in natural language processing, yet they produce unreliable content.
Approach:	They propose to model the attribution task as preference learning and introduce an automatic preference optimization framework that synthesizes attribution preference data.
Outcome:	The proposed method achieves state-of-the-art citation F1 with higher answer quality than existing methods.

Copied to clipboard

Haiyu Zhao, Zhenyu Guo, Chunhong Zhang, Ziyu Zhou, Zheng Hu

SceneGenAgent: Precise Industrial Scene Generation with Coding Agent (2025.acl-long)

Challenge:	StructuThink framework enhances LLMs' ability to ground decisions in domain-specific scenarios.
Approach:	They propose a knowledge-structured reasoning framework that enhances LLM-based agents with explicit decision constraints.
Outcome:	The proposed framework achieves higher task success rates and more efficient action sequences than baseline methods.

Copied to clipboard

Xiao Xia, Dan Zhang, Zibo Liao, Zhenyu Hou, Tianrui Sun, Jing Li, Ling Fu, Yuxiao Dong

Accelerating Dense LLMs via L0-regularized Mixture-of-Experts (2025.acl-short)

Challenge:	Recent work on scene generation focuses on generating 3D scenes from textual descriptions . however, the task of generating industrial scenes with LLMs is complex and requires precise measurements and positioning .
Approach:	They propose an LLM-based agent for generating industrial scenes through C# code.
Outcome:	Experiments show that LLMs powered by SceneGenAgent exceed their original performance . the agent achieves 81.0% success rate in real-world industrial scene generation tasks .

Copied to clipboard

Zhenyu Zhang, JiuDong Yang, Taozhaowen Taozhaowen, Meng Chen

LongReward: Improving Long-context Large Language Models with AI Feedback (2025.acl-long)

Challenge:	Existing methods for accelerating large language models (LLMs) suffer from slow and costly inference.
Approach:	They propose a lightweight MoE approach using cluster confusion matrix and dynamic batching to accelerate dense LLMs.
Outcome:	The proposed method achieves 2.5x speedup over dense models while maintaining competitive performance.

Copied to clipboard

Jiajie Zhang, Zhongni Hou, Xin Lv, Shulin Cao, Zhenyu Hou, Yilin Niu, Lei Hou, Yuxiao Dong, Ling Feng, Juanzi Li

From What to Why: Improving Relation Extraction with Rationale Graph (2021.findings-acl)

Challenge:	In recent years, significant advancements have been achieved in the development of long-context large language models (LLMs).
Approach:	They propose a method that utilizes an off-the-shelf LLM to provide rewards for long-context model responses from four human-valued dimensions: helpfulness, logicality, faithfulness, and completeness.
Outcome:	The proposed method improves models’ long-context performance and enhances their ability to follow short instructions.

Copied to clipboard

Zhenyu Zhang, Bowen Yu, Xiaobo Shu, Xue Mengge, Tingwen Liu, Li Guo

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond (2025.acl-industry)

Challenge:	Existing neural relation extraction models are limited by entity type and textual context.
Approach:	They propose a novel RAtionale Graph to organize co-occurrence constraints among entity types, triggers and relations in a holistic graph view.
Outcome:	The proposed method outperforms baselines significantly and achieves state-of-the-art performance on document-level and sentence-level RE benchmarks.

Copied to clipboard

Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Tanglifu Tanglifu, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang

Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment (2024.emnlp-main)

Challenge:	Experimental results show that opensource curriculum training is more effective when distinct datasets are available for different training stages.
Approach:	They propose an opensource suite for training long reasoning models using publicdata and models.
Outcome:	The proposed model outperforms DeepSeek-R1-DistillQwen-32B models in math reasoning.

Copied to clipboard

Zhenyu Liu, Dongfang Li, Xinshuo Hu, Xinping Zhao, Yibin Chen, Baotian Hu, Min Zhang

A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)

Challenge:	Recent studies have explored the working mechanisms of In-Context Learning (ICL) however, they mainly focus on classification and simple generation tasks, limiting their broader application to more complex generation tasks in practice.
Approach:	They propose an efficient Progressive In-Context Alignment method that embeds the task function learned from demonstrations into the separator token representation.
Outcome:	The proposed method surpasses vanilla ICL and achieves comparable performance to other alignment tuning methods.

Copied to clipboard

Hanyu Lai, Xiao Liu, Junjie Gao, Jiale Cheng, Zehan Qi, Yifan Xu, Shuntian Yao, Dan Zhang, Jinhua Du, Zhenyu Hou, Xin Lv, Minlie Huang, Yuxiao Dong, Jie Tang

LEMON: Reviving Stronger and Smaller LMs from Larger LMs with Linear Parameter Fusion (2024.acl-long)

Challenge:	Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages.
Approach:	They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies.
Outcome:	The proposed model can be used to understand and generate human natural languages.

Copied to clipboard

Yilong Chen, Junyuan Shang, Zhenyu Zhang, Shiyao Cui, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu

Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models (2026.acl-long)

Challenge:	Existing methods to train a stronger and smaller model with the help of large models are limited by the model size and performance.
Approach:	They propose to learn competent initial points for smaller models by fusing parameters from larger models and introduce controllable receptive fields to model prior parameter characteristics.
Outcome:	The proposed method outperforms baselines in terms of effectiveness and efficiency.

Copied to clipboard

Zhenyu Li, Zuchao Li, Ping Wang, Lefei Zhang, Haojun Ai

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction (2025.acl-long)

Challenge:	Long-video understanding is bottlenecked by the high cost of processing massive visual tokens.
Approach:	They propose a decoupled framework for query-guided visual token pruning . their method reduces visual tokens by 90% and accelerates inference by 98% .
Outcome:	The proposed framework reduces visual tokens by 90% and accelerates inference while retaining over 98% of baseline performance on average.

Copied to clipboard

Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, Zhaoxuan Tan, Chao Shen, Meng Jiang

CPTCoder: A Reliable LLM System for Medical Procedure Code Prediction (2026.acl-demo)

Challenge:	Existing Best-of-N decoding methods often lead to incorrect solutions . a novel method is proposed to help large language models identify and revise incorrect steps in their generated reasoning paths.
Approach:	They propose a method that helps large language models identify and revise incorrect steps in their generated reasoning paths.
Outcome:	The proposed method outperforms the state-of-the-art Best-ofN decoding method by +2.4 and reduces token consumption by 77.8%.

Copied to clipboard

Benlu Wang, Ziyao Shangguan, Kyle Tegtmeyer, Zhenyu Zhang, Sophie Chheang, Arman Cohan

Challenge:	Clinical procedure coding is an extreme multi-label classification problem . CPTCoder predicts standardized medical procedure codes from clinical text .
Approach:	a new human-in-the-loop system predicts standardized medical procedure codes from clinical text.
Outcome:	CPTCoder outperforms baseline system by 12 and 5 points in a clinical procedure classification problem.

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline (2024.findings-emnlp)

Copied to clipboard

Yifan Xu, Xiao Liu, Xinghan Liu, Zhenyu Hou, Yueyan Li, Xiaohan Zhang, Zihan Wang, Aohan Zeng, Zhengxiao Du, Zhao Wenyi, Jie Tang, Yuxiao Dong

Numerical Reasoning

Challenge:	Large language models (LLMs) have shown excellent mastering of human language but struggle in real-world applications that require mathematical problem-solving.
Approach:	They propose a pipeline to train a general Math-Critique model from the LLM itself to provide feedback signals and employ rejective fine-tuning and direct preference optimization over the Llm's own generations for data collection.
Outcome:	The proposed pipeline outperforms existing LLMs that could be two times larger.

Coarse-to-Fine Pre-training for Named Entity Recognition (2020.emnlp-main)

Copied to clipboard

Xue Mengge, Bowen Yu, Zhenyu Zhang, Tingwen Liu, Yue Zhang, Bin Wang

Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph (2022.acl-long)

Challenge:	Named Entity Recognition (NER) is a task of discovering information entities and identifying their corresponding categories.
Approach:	They propose a NER-specific framework to inject coarse-to-fine named entity knowledge into pre-trained models by using a remote supervision strategy.
Outcome:	The proposed framework achieves significant improvements against several pre-trained base-lines, demonstrating its effectiveness in label-few and low-resource scenarios.

Copied to clipboard

Yanzeng Li, Jiangxia Cao, Xin Cong, Zhenyu Zhang, Bowen Yu, Hongsong Zhu, Tingwen Liu

Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation (2020.findings-emnlp)

Challenge:	Experimental results show that pre-trained Chinese language models ignore linguistics knowledge to learn representations.
Approach:	They propose a task-free enhancement module to integrate linguistics knowledge into Chinese pre-trained language models.
Outcome:	The proposed model improves Chinese pre-trained language models on 6 tasks with 10 benchmark datasets.

Copied to clipboard

Shiyao Cui, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Xuebin Wang, Jinqiao Shi

Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction (2020.coling-main)

Challenge:	Event detection (ED) is a key subtask of information extraction.
Approach:	They propose an architecture that exploits syntactic structure and typed dependency label information to perform event detection.
Outcome:	The proposed architecture exploits syntactic structure and typed dependency label information to perform ED.

Copied to clipboard

Bowen Yu, Xue Mengge, Zhenyu Zhang, Tingwen Liu, Wang Yubin, Bin Wang

Beyond Static Persona Consistency: Dynamic Persona Coherence in LLM Role-Playing (2026.acl-long)

Challenge:	Existing approaches to remove noise from dependency trees are not optimal due to complexity and variability of natural language.
Approach:	They propose a dynamically pruned Graph Convolutional Network (DP-GCN) that prunes the dependency tree with rethinking in an end-to-end scheme.
Outcome:	The proposed model achieves impressive results compared to strong competitors.

Copied to clipboard

Yirui QI, Xiaoming Zhang, Ruilin Zeng, Mengyao Liu, Ziyi Zhou, Dezhuang Miao, Bingyu Yan, Zhenyu Guan

Challenge:	Existing LLMs conflate identity consistency with emotional rigidity . Existing models exhibit either robotic repetition or persona drift .
Approach:	They propose a framework that decouples Identity-Layer Stability from Adaptive-Layer Appropriateness to achieve persona coherence repair.
Outcome:	Experiments on GPT-4o, Claude-3.5-Sonnet, and DeepSeek-V3.2 show consistent improvements (+16–84% gains)

Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking (2025.acl-long)

Copied to clipboard

Yilong Chen, Junyuan Shang, Zhenyu Zhang, Yanxi Xie, Jiawei Sheng, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang

NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time (2024.acl-long)

Challenge:	Large language models face inherent performance bottlenecks under parameter constraints . challenging tokens induce abrupt gradient spikes across layers, exposing stress points .
Approach:	They propose an inner thinking transformer that reimagines layer computations as implicit thinking steps.
Outcome:	Empirical results show that ITT outperforms Transformer/Loop variants in 11 benchmarks.

Copied to clipboard

Yilong Chen, Guoxia Wang, Junyuan Shang, Shiyao Cui, Zhenyu Zhang, Tingwen Liu, Shuohuan Wang, Yu Sun, Dianhai Yu, Hua Wu

LaMemo: Language Modeling with Look-Ahead Memory (2022.naacl-main)

Challenge:	Large Language Models (LLMs) with extended context windows are expensive and infeasible on fixed memory hardware due to the surprisingly large memory consumption of KV Cache.
Approach:	They propose a general framework for long-context KV cache eviction that achieves more optimal and efficient evict in a single operation during the encoding phase.
Outcome:	The proposed framework improves performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to 5 with over 95% performance maintenance.

Copied to clipboard

Haozhe Ji, Rongsheng Zhang, Zhenyu Yang, Zhipeng Hu, Minlie Huang

FocusLLM: Precise Understanding of Long Context by Dynamic Condensing (2025.acl-long)

Challenge:	Existing approaches to model long-term dependencies are limited to long texts with thousands of words.
Approach:	They propose a look-ahead memory that augments the recurrence memory by attending to the right-side tokens and interpolating with the old memory states to maintain long-term information in the history.
Outcome:	Experiments on widely used language modeling benchmarks show that LaMemo outperforms baseline models with recurrence memory.

Copied to clipboard

Zhenyu Li, Yike Zhang, Tengyu Pan, Yutao Sun, Zhichao Duan, Junjie Fang, Rong Han, Zixuan Wang, Jianyong Wang

Challenge:	Existing context condensing methods cannot accurately understand the full context, as there is a considerable amount of information loss in the condensed process.
Approach:	They propose a framework to extend the fixed context length of any decoder-only LLM by distilling crucial information from long sequences.
Outcome:	The proposed framework extends the fixed context length of any decoder-only LLM, allowing it to focus on relevant information from very long sequences.

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

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

E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models (2025.coling-main)

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

Zhenyu Zhang, Bingguang Hao, Jinpeng Li, Zekai Zhang, Dongyan Zhao

Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations (2026.findings-acl)

Challenge:	E-Bench is a framework for easy-to-use research on large language models.
Approach:	They propose to evaluate the ease-of-use of large language models and construct an E-Bench . they simulate human use from synonymous and typographical perturbations .
Outcome:	The proposed model is able to resist synonymous expressions and typos and improves performance.

Copied to clipboard

Xiaoxu Ma, Xiangbo Zhang, Zhenyu Weng

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)

Challenge:	Existing questionnaire-based evaluation methods exhibit limited stability and offer little explainability, as their results are sensitive to minor variations in prompt phrasing or role-play configurations.
Approach:	They propose an internal-activation-based approach for stable and explainable personality trait evaluation in Large Language Models by interpolating a persona vector associated with a target personality trait from the model's internal activations.
Outcome:	The proposed approach yields significantly more stable personality trait evaluations than existing methods, even under questionnaire and role-play variants.

Copied to clipboard

Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic Consistency (2023.acl-long)

Challenge:	Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation.
Approach:	They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances .
Outcome:	The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks.

Copied to clipboard

Zhenyu Lei, Herun Wan, Wenqian Zhang, Shangbin Feng, Zilong Chen, Jundong Li, Qinghua Zheng, Minnan Luo

Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning (2021.findings-emnlp)

Challenge:	Existing methods to identify bots rely on text or networks alone . text-graph interactions and semantic consistency are essential improvements to combat bot evolution.
Approach:	They propose to combine text-graph interaction and semantic Consistency to model Twitter bots' behavior based on attention weights and a text-graphic interaction module to enable information exchange across modalities in the learning process.
Outcome:	The proposed framework outperforms state-of-the-art methods on two widely adopted datasets and the results are consistent with previous work.

Copied to clipboard

Xinghua Zhang, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Jiawei Sheng, Xue Mengge, Hongbo Xu

Towards Generalized Open Information Extraction (2022.findings-emnlp)

Challenge:	Named entity recognition (NER) is a method of detecting entity spans and classifying them into predefined categories.
Approach:	They propose a method to iteratively perform noisy label refinery by using self-collaborative denoising learning.
Outcome:	The proposed learning paradigm exploits reliable labels and communicates with unreliable annotations by collaborative denoising.

Copied to clipboard

Bowen Yu, Zhenyu Zhang, Jingyang Li, Haiyang Yu, Tingwen Sun, Jian Liu, Yongbin Li, Bin Wang

KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News Media (2022.naacl-main)

Challenge:	Open Information Extraction (OpenIE) models are evaluated on in-domain test sets aside from the training corpus, which violates the initial task principle of domain-independence.
Approach:	They propose to generalize OpenIE over unseen target domains with different data distributions from source training domains.
Outcome:	The proposed method beats the previous methods in both in- and out-of-domain settings by 6.0% in F1 score absolutely.

Copied to clipboard

Wenqian Zhang, Shangbin Feng, Zilong Chen, Zhenyu Lei, Jundong Li, Minnan Luo

HFT: Half Fine-Tuning for Large Language Models (2025.acl-long)

Challenge:	Existing approaches focus on leveraging textual content to identify stances, while they fail to reason with background knowledge or leverage the rich semantic and syntactic textual labels in news articles.
Approach:	They propose a political perspective detection approach that leverages news text to enable multi-hop knowledge reasoning and incorporates textual cues as paragraph-level labels.
Outcome:	The proposed approach outperforms state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang, Weiran Xu, Yu Sun, Hua Wu

KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding (2023.acl-long)

Challenge:	Large language models (LLMs) with one or more fine-tuning phases can unlock various capabilities, but can be catastrophic forgetting during sequential training.
Approach:	They propose a method to regularly reset partial parameters to mitigate forgetting issues by using half fine-tuning instead of full fine-uning.
Outcome:	The proposed approach reduces the risk of catastrophic forgetting during training and the parametric knowledge lost during training may be overwhelmed by incoming training data.

Copied to clipboard

Shangbin Feng, Zhaoxuan Tan, Wenqian Zhang, Zhenyu Lei, Yulia Tsvetkov

Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models (2026.acl-long)

Challenge:	Existing approaches to infuse knowledge graphs with pre-trained LMs are limited by the input sequence length.
Approach:	They propose a language model that leverages knowledge in local, document-level, and global contexts for long document understanding.
Outcome:	The proposed model achieves state-of-the-art on three long document understanding tasks across 6 datasets/settings.

Copied to clipboard

Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang

MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments (2026.acl-long)

Challenge:	Applying model-agnostic explanations to Large Language Models is hindered by prohibitive computational costs rendering them dormant for real-world applications.
Approach:	They propose a budget-friendly proxy framework that leverages efficient models to approximate the decision boundaries of expensive Large Language Models.
Outcome:	The proposed framework achieves over 90% fidelity with only 9.5% of the oracle’s cost and is open-source to facilitate future research.

Copied to clipboard

Quyu Kong, Xu Zhang, Zhenyu Yang, Nolan Gao, Chen Liu, Panrong Tong, Chenglin Cai, Hanzhang Zhou, Jianan Zhang, Liangyu Chen, Zhidan Liu, Steven Hoi, Yue Wang

Submodular-based In-context Example Selection for LLMs-based Machine Translation (2024.lrec-main)

Challenge:	AndroidWorld is the dominant mobile GUI agent evaluation benchmark, but its success rates are low . despite reproducible emulator environment, it lacks key application categories such as e-commerce and enterprise communication.
Approach:	They propose a benchmark for mobile GUI agents that reflects real-world usage through long-horizon, cross-application workflows.
Outcome:	The proposed framework achieves over 90% success rates, while AndroidWorld is the dominant benchmark.

Copied to clipboard

Baijun Ji, Xiangyu Duan, Zhenyu Qiu, Tong Zhang, Junhui Li, Hao Yang, Min Zhang

Machine Translation

Challenge:	Prior studies have focused on the role of well-chosen examples in in-context learning .
Approach:	They propose to use multiple translational factors for in-context example selection by using monotone submodular function maximization.
Outcome:	The proposed approach outperforms random selection and robust single-factor baselines across various NLP tasks.

Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion (2024.emnlp-demo)

Copied to clipboard

Xinping Zhao, Jindi Yu, Zhenyu Liu, Jifang Wang, Dongfang Li, Yibin Chen, Baotian Hu, Min Zhang

Revisiting the Reliability of Language Models in Instruction-Following (2026.acl-long)

Challenge:	Existing studies show that LLMs can confidently state non-existent facts rather than answering "I don't know".
Approach:	They propose a multi-source evidence fusion enhanced hallucination detection and correction framework that fuses evidence from multiple sources and iteratively revises the hallucinous content.
Outcome:	The proposed framework detects whether the generated content contains factual errors, provides the rationale behind the judgment, and iteratively revises the hallucinated content.

Copied to clipboard

Jianshuo Dong, Yutong Zhang, Liu Yan, Zhenyu Zhong, Tao Wei, Chao Zhang, Han Qiu

Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning (2021.emnlp-main)

Challenge:	Several benchmarks have been proposed to measure instruction-following accuracy, but these scores do not translate to reliable services in real-world use.
Approach:	They propose a new metric reliable@k and develop an automated pipeline to generate cousin prompts.
Outcome:	The proposed model can be instantiated with cousin prompts and generates high-quality cousin prompt data.

Copied to clipboard

Xinghua Zhang, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Jiawei Sheng, Xue Mengge, Hongbo Xu

Large Language Models Can Self-Correct with Key Condition Verification (2024.emnlp-main)

Challenge:	Named entity recognition (NER) is a method of detecting entity spans and classifying them into predefined categories.
Approach:	They propose a method to iteratively perform noisy label refinery by using self-collaborative denoising learning.
Outcome:	The proposed learning paradigm exploits reliable labels and communicates with unreliable annotations by collaborative denoising.

Copied to clipboard

Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, Zhaoxuan Tan, Chao Shen, Meng Jiang

Ted-Tok: Maintaining an Evolving Vocabulary for Lifelong Learning (2026.acl-long)

Challenge:	Existing methods to correct reasoning without external feedback have not been used in large language models.
Approach:	They propose an iterative verify-then-correct framework to progressively identify and correct (probably) false responses, named ProCo.
Outcome:	The proposed method improves the accuracy of LLMs on three reasoning tasks.

Copied to clipboard

Jiameng Huang, Zhi Zhang, Zhenyu He, Jiacheng Sun, Di He

Syntactic Text Processing

Challenge:	a static tokenizer fragments newly emerging lexical items as language evolves . as language grows, a dynamic tokenizer reduces compression efficiency and performance .
Approach:	They propose a Temporal Drift Tokenizer that maintains an evolving vocabulary that adapts to emerging linguistic patterns over time.
Outcome:	The proposed tokenizer maintains an evolving vocabulary that adapts to emerging linguistic patterns over time.

Document-level Relation Extraction with Dual-tier Heterogeneous Graph (2020.coling-main)

Copied to clipboard

Zhenyu Zhang, Bowen Yu, Xiaobo Shu, Tingwen Liu, Hengzhu Tang, Wang Yubin, Li Guo

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping (2026.findings-acl)

Challenge:	Existing methods focus on extracting relations from single sentence . document-level relation extraction requires a comprehension of the whole document .
Approach:	They propose a graph-based model with Dual-tier Heterogeneous Graph (DHG) for document-level relation extraction.
Outcome:	The proposed model achieves state-of-the-art performance on two widely used datasets.

Copied to clipboard

Yao Chen, Yilong Chen, Yinqi Yang, Junyuan Shang, Zhenyu Zhang, Zefeng Zhang, Shuaiyi Nie, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang, Tingwen Liu

BeamLoRA: Beam-Constraint Low-Rank Adaptation (2025.acl-long)

Challenge:	Existing approaches to increasing effective depth of LLMs rely on parameter reuse, extending computation through recursive execution.
Approach:	They propose a training-time sparse depth allocation framework that progressively increases depth for a small subset of parameters as training evolves.
Outcome:	The proposed model outperforms existing approaches to increasing the effective depth of language models while reducing training FLOPs overhead from approximately 16–20% to only 1–3% relative to a standard Transformer backbone.

Copied to clipboard

Naibin Gu, Zhenyu Zhang, Xiyu Liu, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging (2025.acl-long)

Challenge:	Low-Rank Adaptation (LoRA) is one of the most efficient parameter-efficient fine-tuning methods.
Approach:	They propose to conceptualize each LoRA module as a beam where each rank corresponds to a potential sub-solution.
Outcome:	The proposed method improves performance on three base models and 12 datasets.

Copied to clipboard

Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang, Yu Sun, Hua Wu, Sen Su

ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)

Challenge:	Existing methods for tuning large language models from dense to MoE face significant data requirements and require large-scale post-training.
Approach:	They propose an upcycling instruction tuning approach for tuning a dense pre-trained model into a MoE instruction model using genetic algorithm and parameter merging.
Outcome:	The proposed approach improves the performance of large language models with a small amount of seed data and improves their scaling.

Copied to clipboard

Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang