Papers by Miao Zhou

ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)

Challenge:	Existing defenses rely on impractical assumptions about trigger settings to mitigate backdoor attacks . a recent study found that small amounts of training data can systematically induce harmful behaviors in large language models.
Approach:	They propose a backdoor defense framework that requires no prior knowledge of trigger settings . they use a two-stage process to aggregate backdoor representations and fine-tune recovery .
Outcome:	The proposed defense reduces the average Attack Success Rate to 4.41% across multiple benchmarks . the proposed framework generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.

Copied to clipboard

Chaoyue He, Xin Zhou, Yi Wu, Xinjia Yu, Yan Zhang, Lei Zhang, Di Wang, Shengfei Lyu, Hong Xu, Wang Xiaoqiao, Wei Liu, Chunyan Miao

FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs’ Responsiveness to Human Feedback (2025.emnlp-main)

Challenge:	ESGenius is a comprehensive benchmark for evaluating Large Language Models on ESG and sustainability knowledge.
Approach:	They introduce ESGenius, a benchmark for evaluating and enhancing ESG proficiency . they use a rigorous two-stage evaluation protocol and a repository of foundational frameworks .
Outcome:	ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in ESG and sustainability-focused question answering.

Copied to clipboard

Youquan Li, Miao Zheng, Fan Yang, Guosheng Dong, Bin Cui, Weipeng Chen, Zenan Zhou, Wentao Zhang

Aligning VLM Assistants with Personalized Situated Cognition (2025.acl-long)

Challenge:	Existing research focuses on benchmarking LLMs in single-turn dialogues, neglecting the nuanced nature of human feedback within real-world usage scenarios.
Approach:	They propose a fine-grained, multi-task benchmark designed to evaluate LLMs’ responsiveness to human feedback under real-world usage scenarios in Chinese.
Outcome:	The proposed benchmarks show that human feedback can significantly impact LLMs’ responsiveness in real-world usage scenarios.

Copied to clipboard

Yongqi Li, Shen Zhou, Xiaohu Li, Xin Miao, Jintao Wen, Mayi Xu, Jianhao Chen, Birong Pan, Hankun Kang, Yuanyuan Zhu, Ming Zhong, Tieyun Qian

End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding (2022.acl-long)

Challenge:	Existing studies on vision-language models aligned with general human objectives have not been successful because people with diversified backgrounds have different cognition even in the same situation.
Approach:	They propose to characterize individuals based on the sociological concept of Role-Set and then evaluate their actions to see whether personalized alignment is achieved.
Outcome:	The proposed framework constructs a cognition-aware and action-based reward model for personalized alignment.

Copied to clipboard

Mengze Li, Tianbao Wang, Haoyu Zhang, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Wenming Tan, Jin Wang, Peng Wang, Shiliang Pu, Fei Wu

Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training (2022.coling-1)

Challenge:	Existing methods for grounding video frames with dense annotations require enormous amount of human effort.
Approach:	They propose to ground natural language in video frames with only one frame labeled . they propose an end-to-end model that eliminates interference of irrelevant frames .
Outcome:	The proposed model can ground natural language in all video frames with only one frame labeled . the proposed model eliminates interference of irrelevant frames based on branch search and cropping techniques .

Copied to clipboard

Zhongjian Miao, Xiang Li, Liyan Kang, Wen Zhang, Chulun Zhou, Yidong Chen, Bin Wang, Min Zhang, Jinsong Su

Robustness in NLP

Challenge:	Existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
Approach:	They propose an iterative scheduled data-switch training framework to mitigate this problem by injecting noise into authentic examples and indiscriminately exploiting two types of examples.
Outcome:	The proposed model outperforms several competitive benchmarks on four translation benchmarks.

Generating Fluent Adversarial Examples for Natural Languages (P19-1)

Copied to clipboard

Huangzhao Zhang, Hao Zhou, Ning Miao, Lei Li

Robustness in NLP

Challenge:	Current methods for building adversarial attackers for NLP are inefficient as the gradient is discarded.
Approach:	They propose an adversarial attacker which performs Metropolis-Hastings sampling with the guidance of gradients to solve these problems.
Outcome:	The proposed algorithm outperforms the baseline model on attacking capability on IMDB and SNLI.

Rank-Awareness and Angular Constraints: A New Perspective on Learning Sentence Embeddings from NLI Data (2025.emnlp-main)

Copied to clipboard

Zicheng Zhou, Min Huang, Qinghai Miao

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

Challenge:	High-quality sentence embeddings are critical for advancing a wide range of Natural Language Processing tasks.
Approach:	They propose a framework that leverages the full NLI dataset augmented with pre-computed continuous similarity scores (S) they employ a Rank Margin objective that enforces rank consistency against S using an explicit margin and a Gated Angular objective that conditionally refines embedding geometry based on NLI label (L) and S score agreement.
Outcome:	The proposed framework outperforms baseline models on STS and the MTEB benchmarks.

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.

LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey (2026.findings-acl)

Copied to clipboard

Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu, Jizhou Guo, Yankai Chen, Chunyu Miao, Hoang H Nguyen, Yue Zhou, Weizhi Zhang, Liancheng Fang, Hanrong Zhang, Fangxin Wang, Pengfei Zhang, Langzhou He, Yangning Li, Dongyuan Li, Renhe Jiang, Philip S. Yu

ConNER: Consistency Training for Cross-lingual Named Entity Recognition (2022.emnlp-main)

Challenge:	Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents.
Approach:	They propose to integrate human-provided information, feedback, or control into the agent system to enhance system performance, reliability, and safety.
Outcome:	The proposed systems improve system performance, reliability, and safety by integrating human-provided information, feedback, or control into the agent system.

Copied to clipboard

Ran Zhou, Xin Li, Lidong Bing, Erik Cambria, Luo Si, Chunyan Miao

Multilinguality

Challenge:	Existing consistency training methods for named entity recognition (NER) are likely to violate the consistency hypothesis or focus on coarse-grain consistency.
Approach:	They propose a consistency training framework for cross-lingual named entity recognition that leverages unlabeled target-language data and dropout-based consistency training on labeled source-language datasets.
Outcome:	The proposed framework improves on translation-based consistency training on unlabeled target-language data and dropout-based consistent training on labeled source-language datasets.

An Ensemble-of-Experts Framework for Rehearsal-free Continual Relation Extraction (2024.findings-acl)

Copied to clipboard

Shen Zhou, Yongqi Li, Xin Miao, Tieyun Qian

Information Extraction & Text Mining

Challenge:	Existing methods for continual relation extraction (CRE) are rehearsal-based and need to store samples and thus may encounter privacy and security issues.
Approach:	They propose an Ensemble-of-Experts framework for rehearsal-free continual relation extraction that discriminates between experts and augments analogous relations across tasks.
Outcome:	The proposed method outperforms existing rehearsal-free methods and is even better than existing methods.

Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction (2024.findings-acl)

Copied to clipboard

Xin Miao, Yongqi Li, Shen Zhou, Tieyun Qian

Information Extraction & Text Mining

Challenge:	Large language models (LLMs) have achieved satisfactory performance in counterfactual generation, however, there are misalignments between LLMs and humans which hinder LLM from handling complex tasks like relation extraction.
Approach:	They propose to mimic the episodic memory retrieval mechanism of human hippocampus to align LLMs’ generation process with that of humans.
Outcome:	The proposed framework improves over existing methods in terms of quality of counterfactuals.

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Copied to clipboard

Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang

Responsible & Trustworthy NLP

Challenge:	Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach:	AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome:	Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .

Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach (2022.emnlp-main)

Copied to clipboard

Miao Chen, Xinjiang Lu, Tong Xu, Yanyan Li, Zhou Jingbo, Dejing Dou, Hui Xiong

Text Generation

Challenge:	Currently, the generalization issues hinder the applicability of neural table-to-text models due to the limited source tables.
Approach:	They propose a table-structureaware text generation model with pretrained language model and propose TASD to bridge the gap between the structured table and text input.
Outcome:	The proposed model bridges the gap between the structured table and text input and generates accurate and fluent descriptive texts on two public datasets.

Prevent the Language Model from being Overconfident in Neural Machine Translation (2021.acl-long)

Copied to clipboard

Mengqi Miao, Fandong Meng, Yijin Liu, Xiao-Hua Zhou, Jie Zhou

SocialEval: Evaluating Social Intelligence of Large Language Models (2025.acl-long)

Challenge:	Neural Machine Translation models are based on partial translation and a language model that predicts the next token based only on partial.
Approach:	They propose a Margin-based Token-level Objective and a Sentence-level Goal to maximize the Margin . they propose to model the next token based on partial translation .
Outcome:	The proposed approach improves translation adequacy and fluency on English-to-German, Chinese-to English and French translation tasks.

Copied to clipboard

Jinfeng Zhou, Yuxuan Chen, Yihan Shi, Xuanming Zhang, Leqi Lei, Yi Feng, Zexuan Xiong, Miao Yan, Xunzhi Wang, Yaru Cao, Jianing Yin, Shuai Wang, Quanyu Dai, Zhenhua Dong, Hongning Wang, Minlie Huang

ART: rule bAsed futuRe-inference deducTion (2023.emnlp-main)

Challenge:	Existing work on LLMs does not address their social intelligence (SI) and their discrepancy with humans.
Approach:	They propose a script-based bilingual SI benchmark that integrates outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation by manually crafting narrative scripts.
Outcome:	The proposed model is based on a script-based bilingual evaluation paradigm that integrates outcome- and process-oriented evaluation by manually crafting narrative scripts.

Copied to clipboard

Mengze Li, Tianqi Zhao, Bai Jionghao, Baoyi He, Jiaxu Miao, Wei Ji, Zheqi Lv, Zhou Zhao, Shengyu Zhang, Wenqiao Zhang, Fei Wu

Reasoning

Challenge:	Existing studies focus on language-based premises and deduce valid conclusions from visual observations.
Approach:	They propose a rule-based deductive reasoning task that uses video to deduce the correct future event . they use commonsense knowledge to annotate video and a strong baseline to conduct reasoning .
Outcome:	Empirical studies validate the rationality of ARTNet in deductive reasoning upon visual observations . ART is a method that rigorously follows a set of explicit constraints to deduce valid conclusions from empirical facts .

MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER (2022.acl-long)

Copied to clipboard

Ran Zhou, Xin Li, Ruidan He, Lidong Bing, Erik Cambria, Luo Si, Chunyan Miao

X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding (2025.findings-emnlp)

Challenge:	Named entity recognition (NER) tasks have limited amount of labeled data . data augmentation methods suffer from token-label misalignment, which leads to unsatsifactory performance.
Approach:	They propose a data augmentation framework that explicitly injects NER labels into sentence context and generates high-quality augmented data with novel entities.
Outcome:	The proposed framework outperforms baseline methods on low-resource tasks.

Copied to clipboard

Wenqi Zhou, Kai Cao, Hao Zheng, Yunze Liu, Xinyi Zheng, Miao Liu, Per Ola Kristensson, Walterio W. Mayol-Cuevas, Fan Zhang, Weizhe Lin, Junxiao Shen

Do you have the right scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods (2020.acl-main)

Challenge:	Existing benchmark datasets focus on short to moderately long videos, leaving a substantial gap in evaluating extensive, ultra-long egocentric video recordings.
Approach:	X-LeBench is a benchmark dataset designed to evaluate long egocentric video recordings . it uses a life-logging pipeline to produce realistic, coherent daily plans .
Outcome:	X-LeBench is a new benchmark dataset designed to evaluate long-form egocentric video understanding . the approach produces realistic, coherent daily plans aligned with real-world video data .

Copied to clipboard

Ning Miao, Yuxuan Song, Hao Zhou, Lei Li

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

Challenge:	Pre-trained language models can be fine-tuned on task-specific datasets, but fine-timing can lead to over- and/or under-estimation problems.
Approach:	They propose a method to transfer probability mass from over-estimated regions to under-estimates by truncating and transferring probability mass between over- and under-estimating regions.
Outcome:	The proposed method outperforms the fine-tuning approach on a variety of datasets.

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)

Prompting Large Language Models for Counterfactual Generation: An Empirical Study (2024.lrec-main)

Copied to clipboard

Yongqi Li, Mayi Xu, Xin Miao, Shen Zhou, Tieyun Qian

Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models (2025.emnlp-main)

Challenge:	Large language models (LLMs) have made remarkable progress in a wide range of natural language understanding and generation tasks, but their ability to generate counterfactuals has not been examined systematically.
Approach:	They propose a framework to evaluate LLMs' ability to generate counterfactuals based on key factors including intrinsic properties and prompt design.
Outcome:	The proposed framework examines the strengths and weaknesses of large language models (LLMs) and identifies factors that influence their ability to generate counterfactuals.

Copied to clipboard

Renjie Pi, Kehao Miao, Li Peihang, Runtao Liu, Jiahui Gao, Jipeng Zhang, Xiaofang Zhou

YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Challenge:	Multimodal large language models exhibit a pronounced form of visual sycophantic behavior when they process image inputs.
Approach:	They propose a technique that allows multimodal large language models to engage in reflective reasoning and determine whether a user’s instruction is misleading or corrective.
Outcome:	The proposed model resists misleading instructions but is stubborn even if it is wrong.

Copied to clipboard

Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen

Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learning (2023.acl-long)

Challenge:	prevailing pre-training approaches for large language models involve several complexities.
Approach:	They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data .
Outcome:	The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data .

Copied to clipboard

Ran Zhou, Xin Li, Lidong Bing, Erik Cambria, Chunyan Miao

Information Extraction & Text Mining

Challenge:	Existing methods to bridge the linguistic gap between self-training and monolingual named entity recognition (NER) however, due to sub-optimal performance on target languages, the pseudo labels are noisy and limit the overall performance.
Approach:	They propose to combine representation learning and pseudo label refinement in one coherent framework to improve self-training for cross-lingual named entity recognition (NER)
Outcome:	The proposed method improves cross-lingual named entity recognition (NER) on multiple transfer pairs.

MECH: A Cost-Effective Multi-Task Cascade Framework for Classroom Opinion Evolution Recognition (2026.acl-long)

Copied to clipboard

Yancui Li, Xiaoyu Zhou, Guoyi Miao, Fang Kong

ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects (2025.findings-emnlp)

Challenge:	Existing studies focus on dialogue act annotation, overlooking the deeper dimension of opinion evolution.
Approach:	They propose a framework for Classroom Opinion Evolution Recognition that translates "Action-Opinion" dualism into a risk-aware routing mechanism.
Outcome:	The proposed framework achieves state-of-the-art accuracy of 78.55% while reducing API costs by 44.4%.

Copied to clipboard

Jipeng Zhang, Haolin Yang, Kehao Miao, Ruiyuan Zhang, Renjie Pi, Jiahui Gao, Xiaofang Zhou

Programming Languages in NLP

Challenge:	Existing text-to-SQL models are limited to SQLite due to dataset limitations . data generated through static prompting is noisy and unreliable, authors say .
Approach:	They propose a text-to-SQL framework with execution-driven, agentic bootstrapping . ExeSQl bridges the dialect gap in text- to-Sql, achieving average improvements .
Outcome:	ExeSQL bridges the dialect gap in text-to-SQl, with average improvements of 15.2%, 10.38%, and 4.49% over GPT-4o on PostgreSQLE, MySQL, and Oracle.

Basic Reading Distillation (2025.acl-long)

Copied to clipboard

Zhi Zhou, Sirui Miao, Xiangyu Duan, Hao Yang, Min Zhang

Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences (2026.findings-acl)

Challenge:	Large language models require high computational resources which limits their deployment in real-world applications.
Approach:	They propose to distill large language models into smaller language models by either knowledge distillation or task distillation.
Outcome:	The proposed model outperforms or performs comparable to over 20x bigger LLMs on language inference benchmarks and BIG-bench tasks.

Copied to clipboard

Zhen Wang, Xi Zhou, Yating Yang, Bo Ma, Lei Wang, Rui Dong, Azmat Anwar, Siru Miao

Multi-modal Action Chain Abductive Reasoning (2023.acl-long)

Challenge:	Existing cross-modal image-text retrieval models often retrieve samples with inconsistent details.
Approach:	They propose two fine-grained image-text retrieval benchmarks that incorporate extensive contrastive samples with one controlled contrastive difference from its anchor.
Outcome:	Extensive experiments show that contrastive samples can significantly degrade retrieval performance.

Copied to clipboard

Mengze Li, Tianbao Wang, Jiahe Xu, Kairong Han, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Shiliang Pu, Fei Wu

SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters (2026.acl-long)

Challenge:	Existing models for Abductive Reasoning are limited in their ability to infer the most plausible explanation of incomplete known phenomena.
Approach:	They propose a vision-language task that aims to imagine the most plausible event by spatio-temporal grounding in past video and infer the hypothesis of subsequent action chain layer by layer.
Outcome:	The proposed model outperforms existing video-language models in terms of effectiveness on the proposed dataset.

Copied to clipboard

Wenhao Gao, Tianlong Wang, Wei Jia, Linhao Zhang, Aiwei Liu, Miao Fan, Zhou Xiao

Responsible & Trustworthy NLP

Challenge:	Prompt-based in-context learning and parameter fine-tuning are dominant paradigms for incorporating external information into large language models, but they incur high inference costs or require expensive retraining.
Approach:	They propose to convert prompts into temporary adapter weights to bridge this gap by converting prompts to temporary adapters.
Outcome:	The proposed model outperforms baselines on long-context language modeling and downstream NLU and summarization benchmarks while significantly reducing memory footprint and latency.

Rethinking Negative Pairs in Code Search (2023.emnlp-main)

Copied to clipboard

Haochen Li, Xin Zhou, Anh Luu, Chunyan Miao

Dual-Path Dynamic Fusion with Learnable Query for Multimodal Sentiment Analysis (2025.emnlp-main)

Challenge:	Comparative learning is a key component in fine-tuning code search models . however, negative samples of InfoNCE may deteriorate its representation learning .
Approach:	They propose a loss function that inserts weight terms into InfoNCE to improve contrastive learning.
Outcome:	The proposed loss function is a special case of Soft-InfoNCE, the authors show . it is more accurate than other loss functions, and it is faster than other models.

Copied to clipboard

Miao Zhou, Lina Yang, Thomas Wu, Dongnan Yang, Xinru Zhang