Papers by Junbo Zhao

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Recent approaches to annotate data focus on labeling, but lack holistic process control . a novel system that integrates task assignment, data annotation, and quality/cost management is needed .
Approach:	They propose a multi-agent system that integrates task assignment, data annotation, and quality/cost management.
Outcome:	The proposed system automates human management by using a collaborative multi-agent system.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

DORY: Deliberative Prompt Recovery for LLM (2024.findings-acl)

Copied to clipboard

Lirong Gao, Ru Peng, Yiming Zhang, Junbo Zhao

Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation (2025.acl-long)

Challenge:	Large language models (LLMs) are used for their groundbreaking performance across various tasks.
Approach:	They propose a method that leverages uncertainty to recover prompts accurately using a single LLM without external resources or models.
Outcome:	The proposed approach outperforms baselines across diverse LLMs and prompt benchmarks and establishes a new state-of-the-art record in prompt recovery tasks.

Copied to clipboard

Mingxuan Xia, Haobo Wang, Yixuan Li, Zewei Yu, Jindong Wang, Junbo Zhao, Runze Wu

Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow (2026.findings-acl)

Challenge:	Existing methods for data annotation use an aggressive approach prompting LLMs to determine a single gold label for each unlabeled sample.
Approach:	They propose a teacher-student framework that distills candidate annotations with a Small Language Model (SLM) they propose to use LLMs to generate and distill candidate annotation with slms to ensure unique labels are provided for downstream tasks.
Outcome:	The proposed method outperforms existing methods due to uncertainty in LLMs and is noisetolerant.

Copied to clipboard

Yangyang Zhong, Yanmei Gu, Zhengqing Zang, Xiaomeng Li, Yuqi Ding, Xibei Jia, Yuting Shen, Zhenzhong Lan, Liwang Zhu, Weiping Liu, Junlin Zhou, Haisheng Liu, Zhong Xin Yu, Pengxin Luo, Donglian Qi, Yunfeng Yan, Junbo Zhao

Duplicate-Aware Controlled Code Generation: Enhancing Copyright Protection with Targeted Reordering Beam Search in LLMs (2026.findings-acl)

Challenge:	Autoregressive (AR) language models dominate modern natural language processing due to strong likelihood-based training objectives and reliable left-to-right decoding.
Approach:	They characterize MDLM behavior along two dimensions: parallelism strength and generation order . authors propose a Generate-then-Edit paradigm that mitigates dependency loss .
Outcome:	The proposed model improves on tasks that require "backward information" the Generate-then-Edit paradigm improves parallel decoding efficiency while reducing dependency loss.

Copied to clipboard

Junbo Fu, Guoshuai Zhao, Linkang Yang, Yunqi Mi, Xueming Qian

Programming Languages in NLP

Challenge:	Experimental results demonstrate that TRBS effectively reduces verbatim repetition while maintaining functional adequacy.
Approach:	They propose a plug-and-play decoding method that dynamically reorders beam candidates to reduce direct copying.
Outcome:	The proposed method reduces verbatim repetition while maintaining functional adequacy on a multi-language code generation benchmark.

Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)

Copied to clipboard

Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo

Multimodality

Challenge:	Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity.
Approach:	They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability.
Outcome:	The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability.

RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering (2025.emnlp-main)

Copied to clipboard

Yiming Zhang, Siyue Zhang, Junbo Zhao, Chen Zhao

On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey (2024.findings-acl)

Challenge:	Long-tail question answering presents significant challenges for large language models due to limited ability to acquire and accurately recall less common knowledge.
Approach:	They propose a data augmentation framework that selects high-quality easy-to-learn training data to enhance dense retrieval models.
Outcome:	The proposed framework improves on two long-tail retrieval benchmarks, PopQA and EntityQuestion, and shows that it outperforms existing retrievers on extremely long-tailed questions.

Copied to clipboard

Lin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao, Xiao Ding, Gang Chen, Haobo Wang

Challenge:	Large Language Models (LLMs) provide a data-centric solution to alleviate limitations of real-world data with synthetic data generation.
Approach:	They propose a generic workflow for LLM-driven synthetic data generation.
Outcome:	The proposed workflows highlight gaps in existing research and outline avenues for future studies.

RECOST: External Knowledge Guided Data-efficient Instruction Tuning (2024.findings-acl)

Copied to clipboard

Qi Zhang, Yiming Zhang, Haobo Wang, Junbo Zhao

D.Va: Validate Your Demonstration First Before You Use It (2025.acl-long)

Challenge:	Considering the high computing power overhead, data-efficient instruction tuning is proposed to reduce the training data size.
Approach:	They propose a framework to improve instruction tuning by integrating external knowledge into a single pipeline.
Outcome:	The proposed method achieves better results with only 1% of the full dataset.

Copied to clipboard

Qi Zhang, Zhiqing Xiao, Ruixuan Xiao, Lirong Gao, Junbo Zhao

Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models (2026.findings-acl)

Challenge:	In-context learning (ICL) heavily relies on selecting effective demonstrations to achieve outputs that better align with the expected results.
Approach:	They propose a method which integrates a demonstration validation perspective into this field and integrates it into the learning paradigm.
Outcome:	The proposed method surpasses all retrieval-based in-context learning techniques across both natural language understanding (NLU) and natural language generation (NLG) tasks.

Copied to clipboard

Xiaomeng Hu, Yixuan Tang, Haoze Li, Hao Chen, Qi Zhang, Zhanming Shen, Yiming Zhang, Haobo Wang, Junbo Zhao

RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)

Challenge:	Prior work focused on data preprocessing, focusing on filtering and cleaning data . a study aimed to improve fine-grained scheduling of data order in epochs .
Approach:	They propose a fine-grained scheduling method of data order in epochs to fill this gap . they define data difficulty based on relevance between data and model .
Outcome:	The proposed method improves on pre-training and small-scale fine-tuning experiments 2.4% over baselines.

Copied to clipboard

Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, Haobo Wang

Multimodality

Challenge:	Existing benchmarks for large language models focus on simple, flat table structures.
Approach:	They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.
Outcome:	The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.

Ensembling Prompting Strategies for Zero-Shot Hierarchical Text Classification with Large Language Models (2025.emnlp-main)

Copied to clipboard

Mingxuan Xia, Zhijie Jiang, Haobo Wang, Junbo Zhao, Tianlei Hu, Gang Chen

ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models (2025.findings-acl)

Challenge:	Hierarchical text classification is a challenging task in natural language processing.
Approach:	They propose a method which integrates the results of diverse prompting strategies to promote LLMs’ reliability.
Outcome:	The proposed method boosts the performance of single prompting strategies and achieves SOTA results on three benchmark datasets.

Copied to clipboard

Hao Chen, Haoze Li, Zhiqing Xiao, Lirong Gao, Qi Zhang, Xiaomeng Hu, Ningtao Wang, Xing Fu, Junbo Zhao

Data Contamination Calibration for Black-box LLMs (2024.findings-acl)

Challenge:	Prior research has focused on optimizing general-purpose large language models to downstream tasks . however, these approaches inherently introduce data dependency, which hinders generalization and reusability.
Approach:	They propose an algorithm that localizes the most task-sensitive attention heads and prunes by restricting attention training updates to these heads, thereby reducing alignment costs.
Outcome:	The proposed algorithm achieves 2% performance improvement over baselines on three tasks while localizing the most task-sensitive attention heads.

Copied to clipboard

Wentao Ye, Jiaqi Hu, Liyao Li, Haobo Wang, Gang Chen, Junbo Zhao

Challenge:	Despite the rapid advancements of Large Language Models, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination.
Approach:	They propose a method to detect contaminated training data and diminish the contamination effect by using a to-be-released dataset.
Outcome:	The proposed method outperforms existing methods by at least 4.5% on more 4 dataset formats, with more than 10 base LLMs.

Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis (2022.findings-acl)

Copied to clipboard

Yiming Zhang, Min Zhang, Sai Wu, Junbo Zhao

Sentiment Analysis

Challenge:	Existing methods to train ABSA model are limited by lack of annotated data . a dual-granularity pseudo labeling approach is proposed to solve this problem .
Approach:	They propose a framework for aspect-based sentiment analysis that uses annotated data to train ABSA models.
Outcome:	The proposed framework surpasses previous methods on benchmarks.

Revisiting the Knowledge Injection Frameworks (2023.emnlp-main)

Copied to clipboard

Peng Fu, Yiming Zhang, Haobo Wang, Weikang Qiu, Junbo Zhao

Learning to Paraphrase for Alignment with LLM Preference (2024.findings-emnlp)

Challenge:	Injecting unaligned knowledge tuple into large language models achieves comparable (and sometimes better) results than aligned knowledge.
Approach:	They propose a technique to inject random knowledge into large language models to improve performance.
Outcome:	The proposed technique overcomes the sanity problem and pushes the performance limit.

Copied to clipboard

Junbo Fu, Guoshuai Zhao, Yimin Deng, Yunqi Mi, Xueming Qian

Text Generation

Challenge:	Large Language Models (LLMs) exhibit the issue of paraphrase divergence, which means that when a question is phrased in a slightly different but semantically similar way, LLM may output a wrong response . retraining faces challenges in meeting the computational costs and privacy security demands of LLMs.
Approach:	They propose a black-box method that enhances model performance by paraphrasing questions in expressions preferred by the model.
Outcome:	The proposed method improves performance by paraphrasing questions in expressions preferred by the model.

GUICourse: From General Vision Language Model to Versatile GUI Agent (2025.acl-long)

Copied to clipboard

Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan Yao, Yankai Lin, Zhiyuan Liu, Maosong Sun

Visual Data in NLP

Challenge:	Graphical User Interfaces (GUIs) are a pivotal medium for human-computer interaction.
Approach:	They propose a series of datasets for training visual-based GUI agents using general VLMs.
Outcome:	The proposed GUICourse datasets show that even a small-sized GUI agent performs better on GUI tasks.

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models (2025.findings-naacl)

Copied to clipboard

Jiachen Ma, Yijiang Li, Zhiqing Xiao, Anda Cao, Jie Zhang, Chao Ye, Junbo Zhao

Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination (2026.acl-long)

Challenge:	Text-to-image (T2I) models can be used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images.
Approach:	They propose a more practical and universal attack that does not require the presence of a target model.
Outcome:	The proposed attack bypasses both text and image safety checkers while preserving high semantic alignment with the target prompt.

Copied to clipboard

Lirong Gao, Zeqing Wang, Yuyan Cai, Jiayi Deng, Yanmei Gu, Yiming Zhang, Jia Zhou, Yanfei Zhang, Junbo Zhao

Reasoning

Challenge:	Existing benchmarks assess basic knowledge breadth or lexical understanding, failing to capture higher-order skills that are central to historical research.
Approach:	They propose a benchmark anchored in the Chinese Imperial Examination system that assesses historical knowledge and lexical understanding.
Outcome:	The new benchmark aims to assess the ability of LLMs to process historical materials and documents.

AIGT: AI Generative Table Based on Prompt (2025.coling-main)

Copied to clipboard

Mingming Zhang, Zhiqing Xiao, Guoshan Lu, Sai Wu, Weiqiang Wang, Xing Fu, Can Yi, Junbo Zhao

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models (2023.emnlp-main)

Challenge:	Tabular data is an essential resource for many fields, but current methods do not fully utilize the rich information available in tables.
Approach:	They propose a method that utilizes metadata information to generate tabular data . they propose long-token partitioning algorithms that enable AIGT to model tables of any scale .
Outcome:	The proposed approach achieves state-of-the-art on 14 out of 20 public datasets and two real industry datasets within the Alipay risk control system.

Copied to clipboard

Shuai Zhao, Jinming Wen, Anh Luu, Junbo Zhao, Jie Fu

FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models (2023.emnlp-main)

Challenge:	ProAttack is a novel and efficient method for performing clean-label backdoor attacks based on the prompt, which uses the prompt itself as a trigger.
Approach:	They propose a method for performing clean-label backdoor attacks based on the prompt, which uses the prompt itself as a trigger.
Outcome:	The proposed method achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings.

Copied to clipboard

Ruixuan Xiao, Yiwen Dong, Junbo Zhao, Runze Wu, Minmin Lin, Gang Chen, Haobo Wang

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents (2024.findings-emnlp)

Challenge:	Modern machine learning models require a huge collection of precisely labeled data, which can be labor-intensive and time-consuming.
Approach:	They propose a collaborative learning framework that interactively distills and filters the task-specific knowledge from LLMs.
Outcome:	The proposed framework improves zero-shot performance on eight benchmark datasets without human supervision.

Copied to clipboard

Ruixuan Xiao, Wentao Ma, Ke Wang, Yuchuan Wu, Junbo Zhao, Haobo Wang, Fei Huang, Yongbin Li

Challenge:	LLM-based agents are susceptible to undesired planning hallucinations when lacking specific knowledge for expertise-intensive tasks.
Approach:	They propose a benchmark to evaluate the efficacy of workflow-guided agent planning by formalizing different formats of workflow knowledge.
Outcome:	The proposed benchmark aims to improve the planning reliability of LLM-based agents by incorporating external workflow-related knowledge.

HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs (2026.findings-acl)

Copied to clipboard

Ru Peng, Tianyu Zhao, Xijun Gu, Zhiting Fan, Haokai Xu, Jinyang Zhang, Yawen Zeng, Yihong Zhuang, Kexin Yang, Junyang Lin, Dayiheng Liu, Junbo Zhao

Challenge:	High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly.
Approach:	They define the first HSS domain system covering 14 mainstream fields and introduce HSS-Synth.
Outcome:	the proposed pipeline outperforms 14 leading baselines on 16 benchmarks.

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)

Copied to clipboard

Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao

Reasoning

Challenge:	Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL).
Approach:	They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.
Outcome:	The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.

Large Margin Representation Learning for Robust Cross-lingual Named Entity Recognition (2025.acl-long)

Copied to clipboard

Guangcheng Zhu, Ruixuan Xiao, Haobo Wang, Zhen Zhu, Gengyu Lyu, Junbo Zhao

Robustness in NLP

Challenge:	Existing approaches to name entity recognition neglect distribution skewness and pseudo-label bias . despite promising results, current approaches neglect these problems .
Approach:	They propose a framework that optimizes an adaptively reweighted contrastive loss to handle class skewness and pseudo-label bias.
Outcome:	The proposed framework outperforms existing methods on multiple benchmarks.

Towards Reverse Engineering of Language Models: A Survey (2025.findings-emnlp)

Copied to clipboard

Xinpeng Ti, Wentao Ye, Zhifang Zhang, Junbo Zhao, Chang Yao, Lei Feng, Haobo Wang

LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains (2025.findings-emnlp)

Challenge:	Due to the vast amounts of data and computational resources required for model development, protecting the model’s parameters and training data has become an urgent and crucial concern.
Approach:	They define "reverse engineering" techniques as attacks on large language models and provide an in-depth analysis of them.
Outcome:	The proposed attacks are described as “reverse engineering” techniques on LMs and provide an introduction to existing protective strategies.

Copied to clipboard

Liyao Li, Jiaming Tian, Hao Chen, Wentao Ye, Chao Ye, Haobo Wang, Ningtao Wang, Xing Fu, Gang Chen, Junbo Zhao

Multimodality

Challenge:	Evaluating 52 LLMs reveals that only the strongest models maintain robust performance under increasing context lengths and format diversity.
Approach:	They propose a benchmark for evaluating long-context reasoning over semi-structured tables across diverse formats, tasks, and domains.
Outcome:	The proposed model outperforms compression-based approaches on tasks requiring semantic integration.

Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection (2024.emnlp-main)

Copied to clipboard

Xiaomeng Hu, Yiming Zhang, Ru Peng, Haozhe Zhang, Chenwei Wu, Gang Chen, Junbo Zhao