Papers by Jingyuan Zhang

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search (2026.findings-acl)

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

Copied to clipboard

Yifei Zhang, Xu Yang, Xiao Yang, Bowen Xian, Qizheng Li, Shikai Fang, Jingyuan Li, Jian Wang, Minrui Xu, Yuge Zhang, Weiqing Liu, Jiang Bian

SDC-LoRA: Singular-Subspace Drift Controlled LoRA to Mitigate Knowledge Forgetting (2026.findings-acl)

Challenge:	LLM-based agents for machine learning engineering rely on tree search to rank candidates.
Approach:	They propose an LLM-based agent that operationalizes gradient-based optimization.
Outcome:	The proposed agent achieves a state-of-the-art 35.1% any-medal rate on MLE-Bench with a limited budget on a single GPU.

Copied to clipboard

Geyuan Zhang, Xiaofei Zhou, Shihao Liu, Jingyuan Tian, Jizheng Ma

Revisiting Data Reconstruction Attacks on Real-world Dataset for Federated Natural Language Understanding (2024.lrec-main)

Challenge:	Existing approaches to adapt LLMs to new tasks focus on limiting knowledge forgetting . et al., 2023b) suggest a solution to this problem by limiting update energy in the principal singular subspace of W0 .
Approach:	They propose a low-rank Adaptation (LoRA) that steers early updates away from principal directions and mitigates forgetting by constraining update energy in the principal singular subspace of W0.
Outcome:	The proposed model mitigates forgetting on MMLU, TruthfulQA, and HellaSwag while keeping minor-subspace updates unchanged.

Copied to clipboard

Zhuo Zhang, Jintao Huang, Xiangjing Hu, Jingyuan Zhang, Yating Zhang, Hui Wang, Yue Yu, Qifan Wang, Lizhen Qu, Zenglin Xu

SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models (2026.findings-acl)

Challenge:	Existing DRA methods fail to accurately recover the original text of real-world privacy data.
Approach:	They propose to use a real-world privacy dataset to examine the performance of federated learning (FL) methods.
Outcome:	The proposed method improves on a real-world privacy dataset and shows that the tokens within a recovery sentence are disordered and intertwined with tokens from other sentences in the same training batch.

Copied to clipboard

Xinyi Zeng, Xue Yang, Jingyuan Zhang, Huanqian Yan, Xiang Chen, Kaiwen Wei, Hankun Kang, Yu Tian

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors (2024.findings-emnlp)

Challenge:	Existing defense methods rely on fine-tuning or inefficient post-hoc interventions, limiting their ability to address novel attacks.
Approach:	They propose a decoding-level defense mechanism that employs a lightweight discriminator to iteratively steer the decoding process toward safety.
Outcome:	The proposed method improves safety performance by up to 33.40% without fine-tuning on multiple MLLMs.

Copied to clipboard

Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang

Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction (2026.acl-long)

Challenge:	Existing tools for detecting safety issues in LLMs are expensive and inefficient.
Approach:	They propose an LLM-based safety detector which annotates the safety of queries and provides explanations for its decisions.
Outcome:	The proposed detector outperforms baselines on four sets of query-response pairs and is effective as a safety evaluator for advanced LLMs.

Copied to clipboard

Tao Wu, Jingyuan Chen, Wang Lin, Jian Zhan, Mengze Li, Fangzhou Jin, Min Zhang, Kun Kuang, Fei Wu

Natural Language Interfaces

Challenge:	Current distractor generation methods produce shared distractors for all students, ignoring individual variations in reasoning, which limits their diagnostic effectiveness.
Approach:	They propose a method which tailors distractors to each student’s specific cognitive flaws, inferred from their past question-answering (QA) history.
Outcome:	The proposed framework outperforms existing methods in generating plausible distractors and adapts to group-level settings.

Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search (2025.acl-long)

Copied to clipboard

Linhao Yu, Xingguang Ji, Yahui Liu, Fanheng Kong, Chenxi Sun, Jingyuan Zhang, Hongzhi Zhang, V. W., Fuzheng Zhang, Deyi Xiong

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning (2026.findings-acl)

Challenge:	Existing benchmarks and evaluation protocols suffer from inadequate or homogeneous creation of key points, exorbitant cost of data creation, and limited evaluation scopes.
Approach:	They propose an automatic framework which leverages Monte Carlo Tree Search to construct numerous and diverse descriptive sentences that thoroughly represent video content in an iterative way.
Outcome:	The proposed framework improves MCTS-VCB and DREAM-1K on video captioning tasks by 25.0% and 16.3% respectively.

Copied to clipboard

Zheng Li, Qingxiu Dong, Jingyuan Ma, Di Zhang, Kai Jia, Zhifang Sui

Reasoning

Challenge:	Recent large reasoning models have shown exceptional performance on various tasks, but they consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency.
Approach:	They propose a self-adaptive reasoning strategy that automatically allocates budgets according to problem complexity and introduces GRPO for reinforcement learning to reduce output length.
Outcome:	The proposed model achieves an average response length compression of 61% on math reasoning tasks while maintaining accuracy.

Guide the Many-to-One Assignment: Open Information Extraction via IoU-aware Optimal Transport (2023.acl-long)

Copied to clipboard

Kaiwen Wei, Yiran Yang, Li Jin, Xian Sun, Zequn Zhang, Jingyuan Zhang, Xiao Li, Linhao Zhang, Jintao Liu, Guo Zhi

FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation (2026.acl-long)

Challenge:	Open Information Extraction (OIE) aims to extract structured information from text without the limitations of close ontology.
Approach:	They propose a method to assign ground truth labels to parallelly generated tuple proposals . they leverage intersection-over-union (IoU) as assignment quality measurement .
Outcome:	The proposed method outperforms the state-of-the-art models on three benchmarks.

Copied to clipboard

Yubo Shan, Kun Zhang, Qiming Xu, Liping Cao, Yingying Cao, Jian Zhang, Yu Wang, Jingyuan Li, Yuanzhuo Wang

CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG (2025.acl-long)

Challenge:	Existing benchmarks lack effective mechanisms to evaluate factual consistency in interleaved image-text generation.
Approach:	They propose a benchmark dedicated to evaluating factual consistency in interleaved image-text generation.
Outcome:	The proposed framework outperforms existing evaluation methods in evaluating factual consistency in interleaved image-text generation.

Copied to clipboard

Yang Tian, Fan Liu, Jingyuan Zhang, V. W., Yupeng Hu, Liqiang Nie

RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction (2023.findings-emnlp)

Challenge:	Recent advances in Multimodal Large Language Models have significantly improved reasoning and generation tasks by leveraging joint vision-language representations.
Approach:	They propose a framework that reconciles inconsistencies across knowledge sources . they use a four-stage pipeline to generate an internal response from parametric knowledge .
Outcome:	Experiments on KB-VQA show that CoRe-MMRAG achieves performance gains of 5.6% and 9.3% over baseline methods.

Copied to clipboard

Chengyuan Liu, Fubang Zhao, Yangyang Kang, Jingyuan Zhang, Xiang Zhou, Changlong Sun, Kun Kuang, Fei Wu

P²Net: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts (2025.findings-acl)

Challenge:	Named Entity Recognition (NER) and Relation Extraction (RE) models have limited success when extracting general schemas such as quadruples and quintuples.
Approach:	They propose a formal formulation that covers almost all extraction schemas and a Recursive Method with Explicit Schema Instructor for UIE.
Outcome:	The proposed method shows strong performance under full-shot and few-shot settings and achieves state-of-the-art results on the tasks of extracting complex schemas.

Copied to clipboard

Kaiwen Wei, Jie Yao, Jiang Zhong, Yangyang Kang, Jingyuan Zhang, Changlong Sun, Xin Zhang, Fengmao Lv, Li Jin

Distill and Replay for Continual Language Learning (2020.coling-main)

Challenge:	Existing methods for key information extraction are based on a limited set of entity categories and fixed layouts.
Approach:	They propose a large-scale, human-annotated dataset for key information extraction . it is based on a human-annotated layout and 1,162 entity categories . they propose 'parallel pointer-based network' that leverages implicit relationships .
Outcome:	Experiments on widely-used datasets show that the proposed model outperforms state-of-the-art methods while maintaining fast inference speeds.

Copied to clipboard

Jingyuan Sun, Shaonan Wang, Jiajun Zhang, Chengqing Zong

Integration of Knowledge Graph Embedding Into Topic Modeling with Hierarchical Dirichlet Process (N19-1)

Challenge:	Existing models fail to isolate acquired knowledge and forget previously learned tasks when learning in a stream where data distribution may shift.
Approach:	They propose a framework that distills knowledge and replays experience from previous tasks when fitting on a new task.
Outcome:	The proposed framework outperforms state-of-the-art models in continuously learning tasks of the same type but from different domains, as well as tasks of different types.

Copied to clipboard

Dingcheng Li, Siamak Zamani, Jingyuan Zhang, Ping Li

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)

Challenge:	Topic models are used to extract topical structures from document-word frequency representations of the text corpus without supervision.
Approach:	They propose a Bayesian nonparametric topic modeling with knowledge graph embedding to employ knowledge graphs to extract more coherent topics.
Outcome:	The proposed model performs better on three public datasets than state-of-the-art models on topic coherence and document classification accuracy.

Copied to clipboard

Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models (2026.findings-acl)

Challenge:	Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood.
Approach:	They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction .
Outcome:	The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones .

Copied to clipboard

Lifan Zheng, Xue Yang, Jiawei Chen, Chenyan WU, Jingyuan Zhang, Fanheng Kong, Xinyi Zeng, Xiang Chen, Yu Tian

Chain-of-Specificity: Enhancing Task-Specific Constraint Adherence in Large Language Models (2025.coling-main)

Challenge:	Current methods for editing personality traits in large language models can change personalities but reduce performance.
Approach:	They propose a novel paradigm for personality editing that locates and edits LLM neurons and enables competitive personality control at inference time.
Outcome:	Experiments on LLaMA-3-8B-Instruct and Qwen2.5-7B-instruct show that the proposed approach can improve performance and improve performance.

Copied to clipboard

Kaiwen Wei, Jiang Zhong, Hongzhi Zhang, Fuzheng Zhang, Di Zhang, Li Jin, Yue Yu, Jingyuan Zhang

TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos (2025.acl-long)

Challenge:	Existing approaches to enhancing large language models fail to emphasize specific constraints and unlock the underlying knowledge.
Approach:	They propose a method that emphasizes specific constraints and unlocks knowledge within LLMs by iteratively emphasising on specific constraints.
Outcome:	The proposed method outperforms existing methods in enhancing generated content, especially in terms of specificity.

Copied to clipboard

Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang, Shi Feng, Daling Wang, Linhao Yu, Xingguang Ji, Yu Tian, V. W., Fuzheng Zhang

Visual Data in NLP

Challenge:	Existing benchmarks for video understanding often focus on specific aspects, overlooking the holistic nature of video content.
Approach:	They propose a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos with two complementary tasks: captioning and QA.
Outcome:	The proposed model performs well on diverse video scenarios and dynamic videos, with interpretable and robust evaluation criteria.

FEDLEGAL: The First Real-World Federated Learning Benchmark for Legal NLP (2023.acl-long)

Copied to clipboard

Zhuo Zhang, Xiangjing Hu, Jingyuan Zhang, Yating Zhang, Hui Wang, Lizhen Qu, Zenglin Xu

Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction (2021.acl-long)

Challenge:	federated learning (FL) is a promising technique for preserving data privacy . however, there is no work on applying FL to legal NLP .
Approach:	They propose to use federated learning to train models in a collaborative way without sharing data . they propose to test the FL benchmark on real-world legal data from Chinese courts .
Outcome:	The proposed benchmark combines five legal NLP tasks and one privacy task on Chinese courts.

Copied to clipboard

Kaiwen Wei, Xian Sun, Zequn Zhang, Jingyuan Zhang, Guo Zhi, Li Jin

Reasoning

Challenge:	Existing methods to extract event arguments focus on learning pair-wise information between arguments and the given trigger.
Approach:	They propose a framework to extract event-related arguments from a given event frame-level scope.
Outcome:	The proposed method achieves state-of-the-art on the RAMS dataset.

Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction (2026.findings-acl)

Copied to clipboard

Shuoxin Wang, Chang Liu, Gowen Loo, Lifan Zheng, Kaiwen Wei, Huanqian Yan, Xinyi Zeng, Jingyuan Zhang, Yu Tian

Think Both Ways: Teacher-Student Bidirectional Reasoning Enhances MCQ Generation and Distractor Quality (2025.findings-acl)

Challenge:	Existing Large Language Model (LLM)-based mobile agents follow explicit user instructions without personalized needs.
Approach:	They propose a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance.
Outcome:	The proposed agent achieves state-of-the-art performance while maintaining competitive instruction execution performance.

Copied to clipboard

Yimiao Qiu, Yang Deng, Quanming Yao, Zhimeng Zhang, Zhiang Dong, Chang Yao, Jingyuan Chen

Reasoning

Challenge:	Existing methods for generating high-quality MCQs struggle with contextual relevance and plausible distractors.
Approach:	They propose a framework that integrates bidirectional reasoning perspectives to generate contextually relevant questions and plausible distractors while student reasoning evaluates question clarity and the misleading nature of distractors.
Outcome:	The proposed framework outperforms existing methods in generating text-grounded questions and high-quality distractors for narrative contexts.

Decoding the Multimodal Mind: Generalizable Brain-to-Text Translation via Multimodal Alignment and Adaptive Routing (2026.findings-acl)

Copied to clipboard

Chunyu Ye, Yunhao Zhang, Jingyuan Sun, Chong Li, Yang Zhao, Shaonan Wang

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents (2025.emnlp-demos)

Challenge:	Current approaches to decoding language from the human brain rely on unimodal representations, neglecting the brain’s inherently multimodal processing.
Approach:	They propose a framework that leverages Multimodal Large Language Models to align brain signals with a shared semantic space encompassing text, images, and audio.
Outcome:	The proposed framework achieves an 8.48% improvement on the most commonly used benchmark on fMRI datasets with textual, visual, and auditory stimuli.

Copied to clipboard

Ziyang Miao, Qiyu Sun, Jingyuan Wang, Yuchen Gong, Yaowei Zheng, Shiqi Li, Richong Zhang

CFlowPsyD: An Analysis-Enhanced Dataset for Asynchronous Psychological Counseling through Self-Optimizing Multi-Agent Framework (2026.findings-acl)

Challenge:	Existing data synthesis tools struggle to extract reliable fine-tuning data from heterogeneous documents.
Approach:	They propose a framework for synthesizing fine-tuning data from unstructured documents via an intuitive graphical user interface.
Outcome:	The proposed framework can extract reliable data from unstructured documents via an intuitive graphical user interface (GUI) it leverages persona-driven prompting approach to generate diverse question-answer pairs using public-available LLMs.

Copied to clipboard

Donghao Li, Yifan Deng, Jinta Weng, Xingsheng Zhang, Chenxu Niu, Jingyuan Tian, Heyan Huang, Yue Hu

Dialogue Systems & Conversational Agents

Challenge:	Asynchronous psychological counseling (APC) is a crucial mental health service modality that transcends temporal and spatial constraints.
Approach:	They propose a self-optimizing multi-agent framework for counseling dialogue generation, CFlowPsy, which utilizes real anonymized counseling cases as seed data to synthesize diverse problem-solving-oriented APC conversations through large language models.
Outcome:	The proposed framework synthesizes diverse problem-solving-oriented APC conversations through large language models.

MemRec: Collaborative Memory-Augmented Agentic Recommender System (2026.acl-long)

Copied to clipboard

Weixin Chen, Yuhan Zhao, Jingyuan Huang, Zihe Ye, Mingxuan Ju, Tong Zhao, Neil Shah, Li Chen, Yongfeng Zhang

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs (2024.lrec-main)

Challenge:	Existing recommender systems rely on semantic user and item memories to make predictions, but these memories are kept in isolation.
Approach:	They propose a framework that architecturally decouples memory management from reasoning to decouple memory management and reasoning from the user and item memories.
Outcome:	The proposed framework decouples memory management from reasoning and achieves state-of-the-art performance on four benchmarks.

Copied to clipboard

Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di Zhang, Kun Gai, Deyi Xiong

Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming (2024.findings-emnlp)

Challenge:	Large language models have demonstrated exceptional capability in natural language understanding and generation, but their generation speed is limited by the inherently sequential nature of their decoding process.
Approach:	They propose a method that accelerates decoding process without sacrificing quality . they propose lexical unit decoding, which can be integrated with other methods .
Outcome:	The proposed method significantly reduces decoding time while maintaining quality while maintaining output quality.

Copied to clipboard

Rui Li, Peiyi Wang, Jingyuan Ma, Di Zhang, Lei Sha, Zhifang Sui

Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level (2025.acl-long)

Challenge:	Large Language Models (LLMs) have gained increasing attention for their capacity to generate harmful content.
Approach:	They propose a scalable evolution framework to evolve red teaming prompts across breadth and depth dimensions, facilitating automatic generation of numerous high-quality and diverse red team prompts.
Outcome:	The proposed framework surpasses existing red teaming methods on attack success rate and diversity.

Copied to clipboard

Xinyi Zeng, Yuying Shang, Jiawei Chen, Jingyuan Zhang, Yu Tian

Intent Discovery with Frame-guided Semantic Regularization and Augmentation (2023.findings-acl)

Challenge:	Existing methods to detect harmful outputs from prefill-level lacks utilization of the model’s decoding outputs, leading to relatively lower effectiveness and robustness.
Approach:	They propose a robust decoding mechanism that corrects harmful queries directly rather than rejecting them outright.
Outcome:	The proposed model improves model security without compromising reasoning speed.

Copied to clipboard

Yajing Sun, Rui Zhang, Jingyuan Yang, Wei Peng

Asclepius: A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models (2025.acl-long)

Challenge:	Existing intent discovery methods focus on transferring prior knowledge of known intents to unknown ones.
Approach:	They propose to use frame knowledge as conceptual semantic guidance to bridge the gap between known intents representation learning and unknown intents clustering.
Outcome:	The proposed method outperforms solid baselines on two benchmark datasets.

Copied to clipboard

Jie Liu, Wenxuan Wang, Su Yihang, Jingyuan Huang, Yudi Zhang, Cheng-Yi Li, Wenting Chen, Xiaohan Xing, Kao-Jung Chang, Linlin Shen, Michael R. Lyu

H-Mem: Hybrid Multi-Dimensional Memory Management for Long-Context Conversational Agents (2026.eacl-long)

Challenge:	Medical Multi-Modal Large Language Models (Med-MLLMs) are a promising new form of artificial general intelligence due to their ability to tackle complex tasks.
Approach:	They propose a new benchmark that comprehensively assesses medical multi-modal large language models in terms of distinct medical specialties and different diagnostic capacities.
Outcome:	The proposed model covers 15 medical specialties and different diagnostic capacities, and excludes overlap with existing VQA dataset.

Copied to clipboard

Zihe Ye, Jingyuan Huang, Weixin Chen, Yongfeng Zhang

Natural Language Interfaces

Challenge:	Existing frameworks for long-context conversational agents struggle to organize information across dimensions like time and topic, leading to poor retrieval.
Approach:	They propose a Hybrid Multi-Dimensional Memory architecture that stores conversational facts in two parallel hierarchical data structures: a temporal tree that organizes information chronologically and a semantic tree that arranges it conceptually.
Outcome:	The proposed architecture improves performance on long-context QA datasets by 8.4% compared to current systems.

VenusFactory: An Integrated System for Protein Engineering with Data Retrieval and Language Model Fine-Tuning (2025.acl-demo)

Copied to clipboard

Yang Tan, Chen Liu, Jingyuan Gao, Wu Banghao, Mingchen Li, Ruilin Wang, Lingrong Zhang, Huiqun Yu, Guisheng Fan, Liang Hong, Bingxin Zhou