Papers by Zhenyu Wang

Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings (2025.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

Tengyu Pan, Zhichao Duan, Zhenyu Li, Bowen Dong, Ning Liu, Xiuxing Li, Jianyong Wang

Representation Learning

Challenge:	Text embedding models are used for various natural language processing tasks such as sentiment analysis, text clustering, and content-based information retrieval.
Approach:	They propose a synthesis framework that leverages large language models to generate diverse negative samples with varying levels of similarity with the query.
Outcome:	The proposed framework achieves state-of-the-art performance surpassing existing synthesis strategies with synthetic data and when combined with public retrieval datasets.

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

Copied to clipboard

Xv Wang, Wang Zhenyu, Guanyu Zheng, Rui Zhang

AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling (2026.findings-acl)

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.

Copied to clipboard

Wang Zhenyu, Geyan Ye, Wei Liu, Man Tat Alexander Ng

Multimodality

Challenge:	Existing methods for virtual cell genetic perturbation modeling suffer from unconstrained reasoning, uninterpretable predictions, and retrieval signals that are weakly aligned with regulatory topology.
Approach:	They propose an Augmented Reasoning Over a Multimodal Architecture for virtual cell genetic perturbation modeling.
Outcome:	The proposed model outperforms existing methods across multiple cell lines and remains robust under zero-shot evaluation on unseen cells.

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.

Adaptive Attentional Network for Few-Shot Knowledge Graph Completion (2020.emnlp-main)

Copied to clipboard

Jiawei Sheng, Shu Guo, Zhenyu Chen, Juwei Yue, Lihong Wang, Tingwen Liu, Hongbo Xu

Large Language Models in Bioinformatics: A Survey (2025.findings-acl)

Challenge:	Recent attempts to learn static representations of entities and references ignore their dynamic properties.
Approach:	They propose to learn static representations of entities and references ignoring their dynamic properties . a neighbor encoder learns entities' roles while a query-aware aggregator learns references' contributions .
Outcome:	The proposed approach achieves state-of-the-art results with different few-shot sizes.

Copied to clipboard

Zhenyu Wang, Zikang Wang, Jiyue Jiang, Pengan Chen, Xiangyu Shi, Yu Li

Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) are revolutionizing bioinformatics, enabling advanced analysis of DNA, RNA, proteins, and single-cell data.
Approach:	They examine the evolution of Large Language Models (LLMs) in bioinformatics and precision medicine by focusing on genomic sequence modeling, RNA structure prediction, protein function inference, and single-cell transcriptomics.
Outcome:	The proposed models are capable of predicting RNA structure and function and predicting single-cell transcriptomics.

Copied to clipboard

Geng Tu, Jun Wang, Zhenyu Li, Shiwei Chen, Bin Liang, Xi Zeng, Min Yang, Ruifeng Xu

Multimodality

Challenge:	Multimodal Emotion Recognition in Conversations models struggle due to lack of Common Sense Knowledge (CSK).
Approach:	They propose a multimodal approach to integrate multiple knowledge into the edge representations by integrating textual and visual CSK.
Outcome:	The proposed model outperforms state-of-the-art methods on two popular datasets.

DKME: Rethinking Coupled Knowledge Memory for Lifelong Model Editing of Large Language Models (2026.findings-acl)

Copied to clipboard

Guanyu Zheng, Wang Zhenyu, He Tingting, Xv Wang, Haochang Wang, Yaokai Huang, Tiejun Zhao

M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory (2025.findings-acl)

Challenge:	Existing memory-based editors suffer from catastrophic forgetting as edits accumulate.
Approach:	They propose a method which injects factual updates into large language models without retraining or finetuning into existing memory-based editors.
Outcome:	Experiments on HalluEditBench, CKnowEdit, and WikiDatacounterfact show that the proposed model achieves a more favorable trade-off between editing success and locality compared to baselines while maintaining more stable performance as the edit scale increases.

Copied to clipboard

YanfangZhou YanfangZhou, Xiaodong Li, Yuntao Liu, Yongqiang Zhao, Xintong Wang, Zhenyu Li, Jinlong Tian, Xinhai Xu

Linguistics & Cognitive NLP

Challenge:	Open-world planning poses a challenge due to complex environments and task diversity . recent work shows that large language models (LLMs) lack the ability to connect to agents' experiences .
Approach:	They propose an open-world multi-memory planning agent that combines large language models with human-like multi-mesh systems to leverage their strengths.
Outcome:	The proposed agent outperforms state-of-the-art agents on 50 Minecraft tasks in zero-shot learning.

JointCoder: Exploring Automated ICD Coding on Real-World Chinese EHRs with a Multi-Agent Framework (2026.acl-demo)

Copied to clipboard

Kangjun Liu, Zhenyu Li, Jianlei Wang, Hongjiao Guan, Ying Lian, Guoqiang Chen, Tao Xin, Wenpeng Lu

Challenge:	Existing automated ICD coding systems face several fundamental challenges due to the limited availability of publicly available Chinese ICD datasets.
Approach:	They propose to use a Chinese ICD coding dataset and a multi-agent framework to reformulate ICD as a joint disease-procedure coding task.
Outcome:	The proposed system outperforms state-of-the-art methods on real-world Chinese ICD coding datasets and 1.7B-parameter models.

Maximum Score Routing For Mixture-of-Experts (2025.findings-acl)

Copied to clipboard

Bowen Dong, Yilong Fan, Yutao Sun, Zhenyu Li, Tengyu Pan, Zhou Xun, Jianyong Wang

Green & Sustainable NLP

Challenge:	Traditional mixture-of-experts (MoE) networks impose an expert capacity constraint to ensure GPU-friendly computation.
Approach:	They propose a routing paradigm that dynamically allocates input tokens to top-k experts through differentiable sparse transformations, enabling scalable model capacity while preserving computational efficiency.
Outcome:	The proposed model achieves lower training losses and higher evaluation scores at equivalent FLOPs compared to constrained and unconstrained baselines.

Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy (2021.emnlp-main)

Copied to clipboard

Yangyang Zhao, Zhenyu Wang, Changxi Zhu, Shihan Wang

Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modeling (2022.findings-emnlp)

Challenge:	Existing methods for training dialogue policies rely on a single learning system, but it requires many rounds of interaction.
Approach:	They propose a complementary policy learning framework which exploits the complementary advantages of the episodic memory (EM) policy and the deep Q-network (DQN) policy.
Outcome:	The proposed framework outperforms existing methods relying on a single learning system on three dialogue datasets.

Copied to clipboard

Zhichao Duan, Xiuxing Li, Zhenyu Li, Zhuo Wang, Jianyong Wang

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

Challenge:	Document-level relation extraction (DocRE) aims to identify semantic labels among entities within a document.
Approach:	They propose a document-level relation extraction framework that captures and exploits instructive information by adding extra syntactic information into text representations.
Outcome:	The proposed framework outperforms existing methods on three benchmark datasets.

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

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

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

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

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

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

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

Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking (2025.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

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

Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-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

Zhenyu Lei, Zhen Tan, Song Wang, Yaochen Zhu, Zihan Chen, Yushun Dong, Jundong Li

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

Challenge:	Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data.
Approach:	They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students.
Outcome:	Experiments show that QR-Distill is superior to traditional methods.

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.

A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning (2022.findings-naacl)

Copied to clipboard

Yang Zhao, Hua Qin, Wang Zhenyu, Changxi Zhu, Shihan Wang

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents (2026.acl-long)

Challenge:	Existing training paradigms for dialogue policy learning with brute-force random sampling are expensive and lack reliable evaluation of difficulty scores.
Approach:	They propose a flexible adaptive curriculum learning framework that integrates curriculum learning with a generic global curriculum.
Outcome:	The proposed framework improves learning performance and efficiency on three public dialogue datasets.

Copied to clipboard

Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Yian Wang, Qingyun Li, Yu Qiao, Zun Wang, Zichen Ding

Robustness in NLP

Challenge:	Vision-Language Models (VLMs) lack visual-aware tutorial retrieval and historical visual context curation and pruning.
Approach:	They propose a framework that integrates an orchestrator and a Reflection-Memory Agent for robust automation.
Outcome:	Experimental results show that OS-Symphony delivers substantial performance gains across model scales.

PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)

Copied to clipboard

Chen Xu, Yu ji, Zhenyu Lv, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang, Tian Lan, Zhihua Wang, Juan Wang, Xunde Dong, Fuze Tian, Qunxi Dong, Bin Hu

Token-Budget-Aware LLM Reasoning (2025.findings-acl)

Challenge:	Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback.
Approach:	They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states.
Outcome:	The proposed model outperforms baselines in faithfulness and pedagogical value.

Copied to clipboard

Tingxu Han, Zhenting Wang, Chunrong Fang, Shiyu Zhao, Shiqing Ma, Zhenyu Chen

Harnessing Large Language Models for Disaster Management: A Survey (2025.findings-acl)

Challenge:	Existing methods to enhance reasoning capabilities of large language models incur significant overhead in token usage, leading to increased costs.
Approach:	They propose a token-budget-aware LLM reasoning framework that adjusts the number of reasoning tokens based on the reasoning complexity of each problem.
Outcome:	The proposed method reduces token costs in CoT reasoning with only a slight performance reduction.

Copied to clipboard

Zhenyu Lei, Yushun Dong, Weiyu Li, Rong Ding, Qi R. Wang, Jundong Li

Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching (2025.coling-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, including their emerging role in mitigating threats to human life, infrastructure, and the environment during natural disasters.
Approach:	They propose a taxonomy that categorizes existing LLMs based on disaster phases and application scenarios to provide valuable insights for the research community and practitioners .
Outcome:	The proposed taxonomy categorizes existing LLMs based on disaster phases and application scenarios.

Copied to clipboard

Tianshu Wang, Xiaoyang Chen, Hongyu Lin, Xuanang Chen, Xianpei Han, Le Sun, Hao Wang, Zhenyu Zeng

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)

Challenge:	Entity matching (EM) is a critical step in entity resolution (ER).
Approach:	They propose a method that incorporates record interactions from different perspectives.
Outcome:	The proposed framework improves on 8 ER datasets and 10 LLMs and achieves higher efficiency and effectiveness.

Copied to clipboard

Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu

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

Challenge:	Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability.
Approach:	They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks.
Outcome:	The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity.

Copied to clipboard

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

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

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

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

SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling (2025.findings-acl)

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

Haoran Wang, Zhenyu Hou, Yao Wei, Jie Tang, Yuxiao Dong

Challenge:	Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE).
Approach:	They propose to build an LLM-based software engineering agent that synthesizes test cases and scales up agent trajectories to build training data.
Outcome:	The proposed model outperforms state-of-the-art models on the SWE-bench-Verified benchmark.

From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning (2025.findings-emnlp)

Copied to clipboard

Zihan Chen, Song Wang, Xingbo Fu, Chengshuai Shi, Zhenyu Lei, Cong Shen, Jundong Li

Low-Resource NLP

Challenge:	In-context learning (ICL) enables large language models to perform novel tasks without parameter updates by conditioning on a few input-output examples.
Approach:	They propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling.
Outcome:	The proposed pipeline reduces reliance on LLMs for data labeling . it leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances.

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

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

CROSSAGENTIE: Cross-Type and Cross-Task Multi-Agent LLM Collaboration for Zero-Shot Information Extraction (2025.findings-acl)

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

Meng Lu, Yuzhang Xie, Zhenyu Bi, Shuxiang Cao, Xuan Wang

Low-Resource NLP

Challenge:	Large language models struggle with producing structured output while maintaining accuracy in zero-shot information extraction (IE)
Approach:	They propose a multi-agent framework that enhances zero-shot IE through multi-task collaboration.
Outcome:	CROSSAGENTIE outperforms state-of-the-art models in structured prediction . the framework significantly reduces inference cost while preserving accuracy .

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

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets (2026.findings-acl)

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

Yuan Xiao, Jiaming Wang, Yuchen Chen, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang, Jin Song Dong, Zhenyu Chen

Programming Languages in NLP

Challenge:	Existing methods for dataset poisoning require full-dataset poison, which breaks code compilability.
Approach:	They propose a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths.
Outcome:	The proposed method contaminates 10% of the dataset while maintaining 100% compilability and functional correctness.

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

Debiasing LLMs by Masking Unfairness-Driving Attention Heads (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

Tingxu Han, Wei Song, Ziqi Ding, Ziming Li, Chunrong Fang, Yuekang Li, Dongfang Liu, Zhenyu Chen, Zhenting Wang

An Efficient Dialogue Policy Agent with Model-Based Causal Reinforcement Learning (2025.coling-main)

Challenge:	Existing work probes when biased outputs appear, but gives little insight into the mechanisms that generate them, leaving existing mitigations largely fragile.
Approach:	They propose a lightweight debiasing framework that detects bias heads and selectively masks only those heads that activate under DA and CoT.
Outcome:	The proposed framework reduces unfairness by 391.9%- 534.5% in both one- and two-turn dialogues.

Copied to clipboard

Kai Xu, Zhenyu Wang, Yangyang Zhao, Bopeng Fang

DEBATE, TRAIN, EVOLVE: Self‐Evolution of Language Model Reasoning (2025.emnlp-main)

Challenge:	Existing models for dialogue policy training consider one-step dialogues, leading to inaccurate simulations.
Approach:	They propose a framework for dialogue policy learning that trains an agent to select dialogue actions via deep reinforcement learning.
Outcome:	The proposed framework achieves state-of-the-art performance on three dialogue datasets . it uses model-based reinforcement learning with automatically constructed causal chains .

Copied to clipboard

Gaurav Srivastava, Zhenyu Bi, Meng Lu, Xuan Wang

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

Challenge:	Large language models have improved significantly in reasoning through extensive training on massive datasets.
Approach:	They propose a ground truth-free training framework that uses multi-agent debate traces to evolve a single language model.
Outcome:	The proposed framework achieves 8.92% accuracy gain on the GSM-PLUS dataset.

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

Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds (2025.findings-acl)

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

YanfangZhou YanfangZhou, Yuntao Liu, Xiaodong Li, Yongqiang Zhao, Xintong Wang, Jinlong Tian, Zhenyu Li, Xinhai Xu

AI for Science in the Era of Large Language Models (2024.emnlp-tutorials)

Challenge:	Recent advances in large language models (LLMs) show promising potential through their world knowledge and language processing capabilities in open-world planning.
Approach:	They propose a framework that integrates the world knowledge of large language models, symbolic reasoning capabilities of cognitive architectures, and metacognition to improve experience utilization.
Outcome:	The proposed framework outperforms current state-of-the-art methods in Minecraft and reduces the average replanning counts by 34% and exceeds the human success rate by 18.96%.

Copied to clipboard

Zhenyu Bi, Minghao Xu, Jian Tang, Xuan Wang

SoulChat: Improving LLMs’ Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations (2023.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have demonstrated significant prowess in tasks involving natural language, such as translating languages, constructing chatbots, and answering questions.
Approach:	This tutorial explores the application of large language models to three crucial categories of scientific data: 1) textual data, 2) biomedical sequences, and 3) brain signals.
Outcome:	This tutorial will explore the application of large language models to three crucial categories of scientific data.

Copied to clipboard

Yirong Chen, Xiaofen Xing, Jingkai Lin, Huimin Zheng, Zhenyu Wang, Qi Liu, Xiangmin Xu

Bio-RFX: Refining Biomedical Extraction via Advanced Relation Classification and Structural Constraints (2024.emnlp-main)

Challenge:	Large language models (LLMs) are used in psychological counseling to provide universal advice.
Approach:	They constructed a multi-turn empathetic conversation dataset with 2 million samples . they found that the model's empathy ability is enhanced when finetuning .
Outcome:	Experiments show that large language models can be finetuned to provide empathy . but, when applied to mental health or emotional support conversation, there are three main issues .

Copied to clipboard

Minjia Wang, Fangzhou Liu, Xiuxing Li, Bowen Dong, Zhenyu Li, Tengyu Pan, Jianyong Wang

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

Challenge:	Existing methods for extracting structured data from unstructured texts neglect unique features of the biomedical literature, such as ambiguous entities and nested proper nouns.
Approach:	They propose a model that leverages sentence-level relation classification before entity extraction to tackle entity ambiguity.
Outcome:	The proposed model outperforms baselines in both NER and RE tasks and has competitive performance compared to the state-of-the-art fine-tuned baselines for RE.

Copied to clipboard

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

OpenICL: An Open-Source Framework for In-context Learning (2023.acl-demo)

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

Zhenyu Wu, Yaoxiang Wang, Jiacheng Ye, Zhiyong Wu, Jiangtao Feng, Jingjing Xu, Yu Qiao

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

Challenge:	In-context Learning (ICL) is a new paradigm for large language model evaluation.
Approach:	They propose an open-source toolkit for ICL and LLM evaluation.
Outcome:	The proposed framework is highly flexible and flexible and can be easily combined with other tools to suit users' needs.

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