Papers by Miao Zhang

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

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

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

CodeArena: Evaluating and Aligning CodeLLMs on Human Preference (2025.emnlp-main)

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

Jian Yang, Jiaxi Yang, Wei Zhang, Jin Ke, Yibo Miao, Lei Zhang, Liqun Yang, Zeyu Cui, Yichang Zhang, Zhoujun Li, Binyuan Hui, Junyang Lin

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

Challenge:	Code large language models (codeLLMs) focus on synthesizing the correct code snippet, ignoring the alignment with human preferences.
Approach:	They propose a benchmark code-based on 40 categories and 44 programming languages to emulate real-world coding tasks.
Outcome:	The proposed benchmarks show that open-source code LLMs perform better than open-sourced ones.

Copied to clipboard

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

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

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.

Copied to clipboard

Huangzhao Zhang, Hao Zhou, Ning Miao, Lei Li

Structure Guided Retrieval-Augmented Generation for Factual Queries (2026.acl-long)

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.

Copied to clipboard

Miao Xie, Xiao Zhang, Yi Li, Chunli Lv

Information Retrieval

Challenge:	Existing methods for RAG produce factually incorrect outputs, resulting in incorrect answers.
Approach:	They propose a novel problem that explicitly incorporates structural information into RAG for factual questions to satisfy all query conditions.
Outcome:	The proposed method significantly outperforms baselines on ERQA while maintaining reasonable computational overhead.

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification (2026.findings-acl)

Copied to clipboard

Wangjie Gan, Miao Pan, Linbo Xi, Wenqi Zhang, Jintao Chen, Jianwei Yin, Xuhong Zhang

AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models (2024.findings-emnlp)

Challenge:	Existing studies have demonstrated that supervised fine-tuning and reinforcement learning are effective in integrating knowledge injection with robust generalization.
Approach:	They propose a unified post-training framework that addresses intrinsic limitations of supervised fine-tuning and reinforcement learning.
Outcome:	The proposed framework surpasses SFT-based methods and yields policies that integrate more smoothly with subsequent RL training.

Copied to clipboard

Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng

AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration (2025.findings-emnlp)

Challenge:	Existing MoE methods require a constant top-k routing for all tokens, which is restrictive because of the number of experts required for feature abstraction.
Approach:	They propose a token-adaptive routing method that allows different tokens to select a different number of experts.
Outcome:	a new method can reduce average expert load while achieving superior performance.

Copied to clipboard

Chunhao Tian, Yutong Wang, Xuebo Liu, Zhexuan Wang, Liang Ding, Miao Zhang, Min Zhang

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

Challenge:	Existing MAS initialization methods do not fully account for the collaborative needs of the generated agents in subsequent stages.
Approach:	They propose to use a Natural Language to Format mechanism to optimize the structure of agent teams and incorporate a natural language to format mechanism to ensure consistency and standardization.
Outcome:	The proposed method outperforms state-of-the-art initialization methods and pre-defined strategies across various frameworks and tasks while reducing token consumption.

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

Towards Better Document-level Relation Extraction via Iterative Inference (2022.emnlp-main)

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.

Copied to clipboard

Liang Zhang, Jinsong Su, Yidong Chen, Zhongjian Miao, Min Zijun, Qingguo Hu, Xiaodong Shi

Information Extraction & Text Mining

Challenge:	Existing methods only consider feature information of entity pairs, but our model exploits both feature information and previous predictions of entity pair.
Approach:	They propose a document-level relation extraction model with iterative inference to extract relations between entities from raw texts.
Outcome:	The proposed model outperforms existing methods on three commonly-used datasets.

Werewolf Among Us: Multimodal Resources for Modeling Persuasion Behaviors in Social Deduction Games (2023.findings-acl)

Copied to clipboard

Bolin Lai, Hongxin Zhang, Miao Liu, Aryan Pariani, Fiona Ryan, Wenqi Jia, Shirley Anugrah Hayati, James Rehg, Diyi Yang

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety (2025.findings-acl)

Challenge:	Existing studies on persuasive behavior modeling focus on textual dialogues . a multimodal dataset is available for persuasion modeling .
Approach:	They propose a multimodal dataset for modeling persuasive behaviors using visual signals.
Outcome:	The proposed dataset includes 199 dialogue transcriptions and videos captured in a multi-player social deduction game setting and 26,647 utterance level annotations of persuasion strategy and game level annotation of deduction game outcomes.

Copied to clipboard

Yuyou Zhang, Miao Li, William Han, Yihang Yao, Zhepeng Cen, Ding Zhao

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

Challenge:	Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment.
Approach:	They propose a framework that trains models to engage in explicit safe reasoning before response . they propose RATIONAL, which allows models to reject harmful prompts while providing meaningful and context-aware responses.
Outcome:	The proposed framework fine-tunes models to reason about query intent, ethics, and potential harm.

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

AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration (2025.acl-long)

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

Zhexuan Wang, Yutong Wang, Xuebo Liu, Liang Ding, Miao Zhang, Jie Liu, Min Zhang

DimA: A Parameter-efficient Fine-tuning Method with Knowledge Transfer Based on Transformer (2024.lrec-main)

Challenge:	Existing methods for MAS suffer from high token consumption and inefficiency due to frequent generation and communication among multiple agents.
Approach:	They propose a multi-agent system based on large language models that identifies redundant agents and communication across different communication rounds by optimizing the adjacency matrices of the communication graphs and eliminates them to enhance both token efficiency and task performance.
Outcome:	The proposed method reduces prompt token consumption and completion token consumption by 18.4% and improves task performance by 1.14.

Copied to clipboard

Wenxuan Zhang, Min Huang, Zhuoyang Song, Qinghai Miao

SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework (2024.emnlp-main)

Challenge:	Pre-trained language models (PLMs) have demonstrated impressive performance across various downstream tasks, but fine-tuning is computationally expensive and storage-intensive.
Approach:	They propose a parameter-efficient method called DimA which enhances the transformer architecture by increasing the dimensionality.
Outcome:	The proposed method achieves state-of-the-art results in GLUE and XSUM tasks while utilizing less than 1% of the original model’s parameters.

Copied to clipboard

Fu Zhang, Qi Miao, Jingwei Cheng, Hongsen Yu, Yi Yan, Xin Li, Yongxue Wu

Information Extraction & Text Mining

Challenge:	Existing methods for document-level relation extraction ignore bidirectional mention interaction when generating relational features for entity pairs.
Approach:	They propose a document-level relation extraction model that incorporates bidirectional mention fusion and a simple yet effective evidence extraction module for relation prediction.
Outcome:	The proposed model achieves SOTA performance and the proposed method is effective and general when integrated into existing models.

LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models (2024.acl-long)

Copied to clipboard

Jiaqi Zhao, Miao Zhang, Chao Zeng, Ming Wang, Xuebo Liu, Liqiang Nie

Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Sampling (2025.emnlp-main)

Challenge:	Existing methods for post-training quantization (PTQ) are limited by the complexity of the quantization parameter and performance degradations when tested on unseen datasets.
Approach:	They propose a learnable smooth-based PTQ framework that allows for rapid adaptation during testing.
Outcome:	The proposed framework improves performance on unseen datasets and reduces memory constraints.

Copied to clipboard

Zhenning Shi, Yijia Zhu, Yi Xie, Junhan Shi, Guorui Xie, Haotian Zhang, Yong Jiang, Congcong Miao, Qing Li

AgentAsk: Multi-Agent Systems Need to Ask (2026.acl-long)

Challenge:	Large language models suffer from overconfidence and computational inefficiency due to fixed computation budgets and miscalibrated confidence estimates.
Approach:	They propose a framework for computationally efficient, trustworthy reasoning under uncertainty using Diversity-Aware Self-Signal Dilution and Convergent Adaptive Weighted Sampling techniques.
Outcome:	The proposed framework reduces inference cost by 70% while maintaining accuracy levels while reducing inference costs.

Copied to clipboard

Bohan Lin, Kuo Yang, Zelin Tan, Yingchuan Lai, Chen Zhang, Guibin Zhang, Xinlei Yu, Miao Yu, Xu Wang, Yudong Zhang, Yang Wang

G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems (2025.acl-long)

Challenge:	Multi-agent systems fail to consistently outperform strong single-a agent baselines due to error propagation at inter-aggent message handoffs.
Approach:	They propose an edge-level error taxonomy that identifies four main errors in multi-agent interactions as data gaps, signal corruption, referential drift and capacity gaps as primary sources of failure.
Outcome:	The proposed module outperforms existing systems on five benchmarks and is architecture-agnostic.

Copied to clipboard

Shilong Wang, Guibin Zhang, Miao Yu, Guancheng Wan, Fanci Meng, Chongye Guo, Kun Wang, Yang Wang

Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method (2024.findings-acl)

Challenge:	Large Language Model (LLM)-based Multi-agent Systems (MAS) have demonstrated remarkable capabilities in various complex tasks, but their vulnerability to adversarial attacks, misinformation propagation, and unintended behaviors have raised significant concerns.
Approach:	They propose a topology-guided security lens and treatment for robust LLM-MAS that leverages graph neural networks to detect anomalies on the multi-agent utterance graph and employ topological intervention for attack remediation.
Outcome:	Experiments show that the proposed security lens recovers 40% of the performance under various attack strategies and integrates with mainstream MAS with security guarantees.

Copied to clipboard

Tian Xia, Zhiwei He, Tong Ren, Yibo Miao, Zhuosheng Zhang, Yang Yang, Rui Wang

Challenge:	Using a novel approach, we can evaluate an agent’s bargaining abilities as an asymmetric incomplete information game.
Approach:	They propose an approach that integrates a deterministic Offer Generator and an LLM Narrator to create natural language sentences for generated offers.
Outcome:	The proposed approach improves the buyer’s deal rates from 26.67% to 88.88% and brings a ten times multiplication of profits on all baselines, even a model that has not been aligned.

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

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 .

Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training (2025.findings-acl)

Copied to clipboard

Yihang Yao, Zhepeng Cen, Miao Li, William Han, Yuyou Zhang, Emerson Liu, Zuxin Liu, Chuang Gan, Ding Zhao

CARD: Cross-modal Agent Framework for Generative and Editable Residential Design (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks.
Approach:	They propose a data-centric approach that enhances LLMs’ awareness of symmetry in query variations and propose syMmetry-ENhanceD (MEND) data augmentation.
Outcome:	Extensive experiments on logical and arithmetic reasoning tasks show that the proposed approach improves model robustness at the knowledge extraction stage through query augmentation.

Copied to clipboard

Pengyu Zeng, Jun Yin, Miao Zhang, Yuqin Dai, Jizhizi Li, ZhanXiang Jin, Shuai Lu

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

Challenge:	Architectural design automation has made significant progress, but the complexity of open-world environments makes residential design a challenging task.
Approach:	They propose a framework that leverages a system of specialized cross-modal agents to adapt to open-world residential design.
Outcome:	The proposed framework enables users to generate and edit residential design without requiring specialized expertise.

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

History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System (2022.findings-emnlp)

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

Tong Zhang, Yong Liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui

Dialogue Systems & Conversational Agents

Challenge:	Existing open-domain dialogue systems conduct one-session conversations, but multi-session MSCs are under-investigated.
Approach:	They propose a History-Aware Hierarchical Transformer for multi-session open-domain dialogue . they propose to encode history conversations into a history memory and leverage historical information to generate well-informed responses.
Outcome:	The proposed model outperforms baseline models on a large-scale MSC dataset.

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

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)

Weight-Aware Activation Sparsity with Constrained Bayesian Optimization Scheduling for Large Language Models (2025.emnlp-main)

Copied to clipboard

Ming Wang, Miao Zhang, Xuebo Liu, Liqiang Nie

Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation (2024.findings-acl)

Challenge:	Existing activation sparsification methods rely on activation magnitude and weights for sparsity . authors propose a weight-aware activation-a-ware framework for large language models .
Approach:	They propose a weight-aware activation sparsity framework that uses weight-based scoring to measure activation importance in sparsification and a custom GPU sparse kernel to support it.
Outcome:	The proposed framework outperforms existing methods at 60% model-level sparsity and significantly outperfies them at higher sparsities.

Copied to clipboard

Zhexuan Wang, Shudong Liu, Xuebo Liu, Miao Zhang, Derek Wong, Min Zhang

FloorPlan-LLaMa: Aligning Architects’ Feedback and Domain Knowledge in Architectural Floor Plan Generation (2025.acl-long)

Challenge:	Existing methods to transfer knowledge from kNN datastore into new models are expensive and arbitrarily transfer knowledge.
Approach:	They propose a domain-aware method which filters out domain-relevant neighborhood knowledge for learning in the distillation process.
Outcome:	The proposed method achieves state-of-the-art on four domain translation tasks.

Copied to clipboard

Jun Yin, Pengyu Zeng, Haoyuan Sun, Yuqin Dai, Han Zheng, Miao Zhang, Yachao Zhang, Shuai Lu

Challenge:	Existing evaluation methods for floor plan generation rely on statistical metrics like FID, GED, and PSNR, which fail to evaluate using domain knowledge.
Approach:	They propose to use a first floor plan dataset to train a floor plan generation model based on a multi-dimensional preference score and a textual analysis to integrate architects’ professional expertise and preferences.
Outcome:	The proposed model outperforms baseline models in text-conditional and class-condition tasks and is more rational and aligns better with human preferences.

Composition-based Heterogeneous Graph Multi-channel Attention Network for Multi-aspect Multi-sentiment Classification (2022.coling-1)

Copied to clipboard

Hao Niu, Yun Xiong, Jian Gao, Zhongchen Miao, Xiaosu Wang, Hongrun Ren, Yao Zhang, Yangyong Zhu

Sentiment Analysis

Challenge:	Existing methods for Aspect-based sentiment analysis (ABSA) focus on aspect terms with the same sentiment polarity . current methods focus on sentences with only one aspect term or multiple aspect terms .
Approach:	They propose a novel method to model inter-aspect relationships and aspect-context relationships simultaneously using a heterogeneous graph.
Outcome:	The proposed method can predict sentiments towards the given aspect term in a sentence . it can provide more detailed predictions compared with sentence-level sentiment analysis.

NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering (2025.acl-long)

Copied to clipboard

Ruisheng Cao, Hanchong Zhang, Tiancheng Huang, Zhangyi Kang, Yuxin Zhang, Liangtai Sun, Hanqi Li, Yuxun Miao, Shuai Fan, Lu Chen, Kai Yu

Natural Language Interfaces

Challenge:	Existing approaches to retrieval augmented generation neglect PDF structure and layout . individual PDFs often exceed prompt limits and user queries may span multiple documents.
Approach:	They propose a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process.
Outcome:	The proposed framework organizes semi-structured PDF content into relational database and vectorstore . it defeats both RAG and structured baselines on three PDF-based QA datasets .

NetSafe: Exploring the Topological Safety of Multi-agent System (2025.findings-acl)

Copied to clipboard

Miao Yu, Shilong Wang, Guibin Zhang, Junyuan Mao, Chenlong Yin, Qijiong Liu, Kun Wang, Qingsong Wen, Yang Wang

Challenge:	Large language models (LLMs) have fueled significant progress in intelligent Multi-agent Systems (MAS), with expanding academic and industrial applications.
Approach:	They propose a framework that unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.
Outcome:	The proposed framework unifies diverse MAS workflows via iterative RelCom interactions to enable generalized analysis.

PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models (2025.acl-long)

Copied to clipboard

Jiaqi Zhao, Miao Zhang, Ming Wang, Yuzhang Shang, Kaihao Zhang, Weili Guan, Yaowei Wang, Min Zhang

SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection (2026.findings-acl)

Challenge:	Existing methods for sub 2-bit quantization introduce an extra 1-bit or more per weight.
Approach:	They propose a sub 2-bit post-training quantization method that enables weight quantization to 1.61-bit for the first time.
Outcome:	The proposed method reduces the upper bound of quantization error to 1.61-bit for the first time.

Copied to clipboard

Huopu Zhang, Yanguang Liu, Miao Zhang, Zirui He, Mengnan Du

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

Challenge:	Conference call transcripts contain significant redundancy and industry-specific terminology that creates obstacles for language models.
Approach:	They propose a Sparse Autoencoder for Financial Representation Enhancement framework to extract key information from earnings conference call transcripts and eliminate redundancy.
Outcome:	The proposed method outperforms baselines in analyzing earnings conference call transcripts.

Copied to clipboard

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

Exploring Representation-level Augmentation for Code Search (2022.emnlp-main)

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

Haochen Li, Chunyan Miao, Cyril Leung, Yanxian Huang, Yuan Huang, Hongyu Zhang, Yanlin Wang

Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation (2023.emnlp-main)

Challenge:	Recent data augmentations for code search are at the raw-data level, which requires additional code analysis and training cost.
Approach:	They propose a general format of representation-level augmentation that unifies existing methods.
Outcome:	The proposed methods can boost the performance of code search models on a large-scale dataset.

Copied to clipboard

Zhongjian Miao, Wen Zhang, Jinsong Su, Xiang Li, Jian Luan, Yidong Chen, Bin Wang, Min Zhang

On the Step Length Confounding in LLM Reasoning Data Selection (2026.findings-acl)

Challenge:	Existing knowledge distillation methods only obtain one lightweight student each time . this could be resource-intensive and resulting in multiple students not being optimally utilized .
Approach:	They propose a knowledge distillation framework which generates multiple satisfactory students at once.
Outcome:	The proposed framework generates multiple satisfactory students at once.

Copied to clipboard

Bing Wang, Rui Miao, Chen Shen, Shaotian Yan, Kaiyuan Liu, Ximing Li, Xiaosong Yuan, Sinan Fan, Jun Zhang, Jieping Ye

Reasoning

Challenge:	Existing pipelines generate long reasoning data from more capable Large Language Models (LLMs) and apply manually heuristic or naturalness-based selection methods to filter high-quality samples.
Approach:	They propose to use supervised fine-tuning to generate long reasoning data from more capable Large Language Models and apply manually heuristic or naturalness-based selection methods to filter high-quality samples.
Outcome:	Experiments on four LLMs and five evaluation benchmarks show that the proposed approach is effective in mitigating step length confounding problem.

SAM3-I: Segment Anything with Instructions (2026.acl-long)

Copied to clipboard

Jingjing Li, Yue Feng, Yuchen Guo, Jincai Huang, Wei Ji, Qi Bi, Yongri Piao, Miao Zhang, Xiaoqi Zhao, Qiang Chen, Shihao Zou, Huchuan Lu, Li Cheng

Low-Resource NLP

Challenge:	Existing methods for concept-level grounding and instruction-level reasoning use coarse representations and iterative mask filtering.
Approach:	They propose an instruction-following extension of the Segment Anything Model 3 family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework.
Outcome:	Experiments show that SAM3-I achieves appealing performance across referring and reasoning-based segmentation while maintaining its strong concept recall ability.

Towards Persona-Based Empathetic Conversational Models (2020.emnlp-main)

Copied to clipboard

Peixiang Zhong, Chen Zhang, Hao Wang, Yong Liu, Chunyan Miao

Dialogue Systems & Conversational Agents

Challenge:	Empathetic conversational models have been shown to improve user satisfaction and task outcomes in numerous domains.
Approach:	They propose a task towards persona-based empathetic conversations and propose e-learning model CoBERT that can be used to train persona on emmpathetic conversations.
Outcome:	The proposed model improves empathetic responding more when trained on e-mpathetic conversations than non-empathy ones.

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)

Copied to clipboard

Siyuan Gan, Jiaheng Liu, Boyan Wang, Tianpei Yang, Runqing Miao, Yuyao Zhang, Fanyu Meng, Junlan Feng, Linjian Meng, Jing Huo, Yang Gao

Reasoning

Challenge:	Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Approach:	They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Outcome:	The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy.

TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation (2025.emnlp-main)

Copied to clipboard

Daiye Miao, Yufang Liu, Jie Wang, Changzhi Sun, Yunke Zhang, Demei Yan, Shaokang Dong, Qi Zhang, Yuanbin Wu

Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies (2025.naacl-long)

Challenge:	Existing studies have shown that LoRA introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning.
Approach:	They propose a method that leverages importance information from the pretrained model’s weights to mitigate LoRA redundancy.
Outcome:	The proposed method significantly reduces the number of trainable parameters required for task adaptation while providing a task-aligned perspective for LoRA redundancy reduction.

Copied to clipboard

Zirui Song, Guangxian Ouyang, Meng Fang, Hongbin Na, Zijing Shi, Zhenhao Chen, Fu Yujie, Zeyu Zhang, Shiyu Jiang, Miao Fang, Ling Chen, Xiuying Chen

Challenge:	Existing household robots are inability to recognize potential problems or dangers in home environments.
Approach:	They propose a task of creating anomaly scenarios using generative models instead of manually labeled data to build simulated environments.
Outcome:	The proposed framework outperforms existing models in terms of task description and scene diversity.

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)

Copied to clipboard

Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Dialogue Systems & Conversational Agents

Challenge:	Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns.
Approach:	They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory.
Outcome:	Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy.

Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval (2024.findings-acl)

Copied to clipboard

Yan Gao, Zhiwei Cao, Zhongjian Miao, Baosong Yang, Shiyu Liu, Min Zhang, Jinsong Su

Information Retrieval

Challenge:	Existing models for non-parametric domain adaptation lack kNN retrieval at each timestep, leading to substantial time overhead.
Approach:	They propose a kNN-MT-based model that uses a domain-specific translation knowledge store to interpolate the prediction distribution of the model.
Outcome:	The proposed model significantly extends kNN-MT with dynamic retrieval on widely-used datasets.

Qwen2.5-xCoder: Multi-Agent Collaboration for Multilingual Code Instruction Tuning (2025.acl-long)

Copied to clipboard

Jian Yang, Wei Zhang, Yibo Miao, Shanghaoran Quan, Zhenhe Wu, Qiyao Peng, Liqun Yang, Tianyu Liu, Zeyu Cui, Binyuan Hui, Junyang Lin

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

Challenge:	Existing methods to train code LLMs view each programming language in isolation . experimental results show that Qwen2.5-xCoder can bridge the gap between different programming languages .
Approach:	They propose a framework that allows agents to collaborate to enhance multilingual instruction tuning for code LLMs.
Outcome:	Experimental results show that Qwen2.5-xCoder can transfer knowledge efficiently and effectively between languages.

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.

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

Copied to clipboard

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

Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention (2026.acl-long)

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

Ruizi Han, Miao Zhang, Ziyue Qiao, Liqiang Nie

Revisiting Representation Degeneration Problem in Language Modeling (2020.findings-emnlp)

Challenge:	Efficient long-context inference remains a major challenge for large language models (LLMs), as the cost of attention computation during auto-regressive decoding grows linearly with the context length.
Approach:	They propose to model token importance as a dynamic process that evolves over decoding steps and propagates through model layers.
Outcome:	The proposed method outperforms baseline sparse attention methods and achieves speedups of up to 5.36 for attention latency and 2.33 for end-to-end decoding.

Copied to clipboard

Zhong Zhang, Chongming Gao, Cong Xu, Rui Miao, Qinli Yang, Junming Shao

Basic Reading Distillation (2025.acl-long)

Challenge:	Language modeling is a fundamental task in natural language processing, applications include machine translation, image captioning and speech recognition.
Approach:	They propose a cosine regularization method to solve the representation degeneration problem by analyzing the limitations of the proposed method and then propose an alternative regularization technique to tackle the problem.
Outcome:	The proposed method is effective in language modeling and image captioning.

Copied to clipboard

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

Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking (2024.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

Ming Dong, Yujing Chen, Miao Zhang, Hao Sun, Tingting He

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

Challenge:	Chinese Spell Checking (CSC) is a widely used technology for speech to text and optical character recognition.
Approach:	They propose to use Chinese rich semantic information to introduce large language models as the foundation model.
Outcome:	The proposed framework performs better on few-shot CSC task than existing methods.

Copied to clipboard

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

Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model (2024.findings-acl)

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

Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models (2026.acl-long)

Challenge:	Large language models can be used to produce text that is coherent, well-written, and persuasive . some individuals have misused LLMs for nefarious purposes, such as creating fake news articles or engaging in cheating .
Approach:	They propose to incorporate a Bayesian surrogate model to improve query efficiency . they propose to select typical samples based on Bayes' uncertainty and interpolate scores .
Outcome:	The proposed method significantly outperforms existing approaches under a low query budget.

Copied to clipboard

Yilun Liu, Chunguang Zhao, Mengyao Piao, Lingqi Miao, Shimin Tao, Minggui HE, Chenxin Liu, Zhang Li, null Mahongxia, Jiaxin Guo, Chen Liu, Liqun Deng, Jiansheng Wei, Xiaojun Meng, Fanyi Du, Daimeng Wei, Yanghua Xiao

Identity-Robust Language Model Generation via Content Integrity Preservation (2026.acl-long)

Challenge:	Existing multilingual evaluation benchmarks neglect cultural nuances and lack language coverage in subjective tasks.
Approach:	They propose a framework that categorizes evaluation tasks into three cultural layers and nine cognitive sub-layers.
Outcome:	The proposed framework surpasses prior coverage by up to 111% on 20+ LLMs.

Copied to clipboard

Miao Zhang, Kelly Chen, Mehrab Tanjim, Rumi Chunara

Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models (2024.acl-long)

Challenge:	Existing studies show that Large Language Model outputs vary across sociodemographic attributes . this causes disparities in factual accuracy, utility, and safety, even for objective questions .
Approach:	They propose a lightweight framework for identity-robust generation that neutralizes non-critical identity information while preserving semantically essential attributes.
Outcome:	The proposed framework reduces identity-dependent generation bias by 66.3% over vanilla prompting and outperforms existing prompt-based defenses.

Copied to clipboard

Zhengxin Zhang, Dan Zhao, Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Qing Li, Yong Jiang, Zhihao Jia

CLLE: A Benchmark for Continual Language Learning Evaluation in Multilingual Machine Translation (2022.findings-emnlp)

Challenge:	Existing methods to finetun large language models (LLMs) only update a small number of trainable parameters, or attempt to reduce the memory footprint during the training phase of the finetune process.
Approach:	They propose quantized side tuing (QST) which quantizes an LLM’s model weights into 4-bit to reduce the memory footprint of the original weights.
Outcome:	The proposed method reduces the memory footprint of the model weights, optimizer states, and intermediate activations while reducing the memory requirements.

Copied to clipboard

Han Zhang, Sheng Zhang, Yang Xiang, Bin Liang, Jinsong Su, Zhongjian Miao, Hui Wang, Ruifeng Xu

Multilinguality

Challenge:	Existing benchmarks for Continual Language Learning (CLL) are limited due to the complexity of the task and the lack of unified benchmarks.
Approach:	They propose a Continual Language Learning Evaluation benchmark CLLE in multilingual translation.
Outcome:	The proposed method is effective when compared with other strong benchmarks.

Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization (2026.acl-long)

Copied to clipboard

Zixuan Huang, Zhihong Zhu, Xiaolong Liu, Yanchao Hao, Manman Zhang, Zheng Wei, Bowen Xing, Xian Wu, Ye Li, Fen Miao, Yefeng Zheng

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

Challenge:	Existing preference-based methods for medical large vision-Language Models face limitations in medical settings . existing methods are limited by overfitting to superficial cues and pseudo convergence of the preference signal.
Approach:	They propose a framework that enables evidence-aware and adaptive preference learning for Med-LVLMs.
Outcome:	The proposed framework improves evidence-aware and adaptive preference learning for Med-LVLMs.

Copied to clipboard

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

Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety (2026.acl-long)

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.

Copied to clipboard

Wei-Chieh Huang, Henry Peng Zou, Yaozu Wu, Dongyuan Li, Yankai Chen, Weizhi Zhang, Yangning Li, Angelo Zangari, Jizhou Guo, Chunyu Miao, Liancheng Fang, Langzhou He, Yinghui Li, Renhe Jiang, Philip S. Yu

DRLK: Dynamic Hierarchical Reasoning with Language Model and Knowledge Graph for Question Answering (2022.emnlp-main)

Challenge:	Existing deep research frameworks lack adequate evaluation procedures and stage-specific protections.
Approach:	They propose a framework with open-domain evaluation and a stage-wise safety benchmark to address this oversight.
Outcome:	The proposed framework improves defense success rates by 16.53% while reducing over-refusal rates to approximately 6%.

Copied to clipboard

Miao Zhang, Rufeng Dai, Ming Dong, Tingting He

The ELCo Dataset: Bridging Emoji and Lexical Composition (2024.lrec-main)

Challenge:	Existing work only uses the same QA context representation to interact with multiple layers of KG, which results in a restricted interaction.
Approach:	They propose a model that utilizes dynamic hierarchical interactions between QA context and KG for reasoning.
Outcome:	The proposed model performs state-of-the-art on two benchmark datasets and competitively on the others.

Copied to clipboard

Zi Yun Yang, Ziqing Zhang, Yisong Miao

Visual Data in NLP

Challenge:	Emoji-Lexical Composition dataset provides parallel annotations of emoji sequences corresponding to English phrases.
Approach:	They propose a dataset that offers parallel annotations of emoji sequences corresponding to English phrases.
Outcome:	The Emoji-Lexical Composition (ELCo) dataset offers parallel annotations of emoji sequences corresponding to English phrases.

TF-Mamba: Text-enhanced Fusion Mamba with Missing Modalities for Robust Multimodal Sentiment Analysis (2025.findings-emnlp)

Copied to clipboard

Xiang Li, Xianfu Cheng, Dezhuang Miao, Xiaoming Zhang, Zhoujun Li

CodecLM: Aligning Language Models with Tailored Synthetic Data (2024.findings-naacl)

Challenge:	Existing Transformer-based methods with missing modalities are difficult to use and have quadratic complexity.
Approach:	They propose a text-enhanced Fusion Mamba framework for robust MSA with missing modalities . a Text-aware Modality Enhancement module aligns and enriches non-text modality while reconstructing missing text semantics.
Outcome:	The proposed method is efficient under missing modalities and can be used in long-range modeling and multimodal fusion scenarios.

Copied to clipboard

Zifeng Wang, Chun-Liang Li, Vincent Perot, Long Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister

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

Challenge:	Recent work on generating diverse instructions and applying LLM to increase instruction complexity neglects downstream use cases.
Approach:	They propose a framework for generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs.
Outcome:	Experiments on four open-domain instruction using the proposed framework validate the effectiveness of CodecLM over the current state-of-the-art.

Copied to clipboard

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

T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step (2024.acl-long)

Challenge:	Existing methods for multimodal sentiment analysis struggle with global and fine-grained contributions and over-reliance on text.
Approach:	They propose a multimodal sentiment analysis architecture that processes inputs through two complementary paths: global and local.
Outcome:	The proposed architecture achieves state-of-the-art in fine-grained sentiment prediction on the CMU-MOSI and CMU MOSEI benchmarks.

Copied to clipboard

Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu, Jiangning Liu, Miao Zheng, Jingming Zhuo, Songyang Zhang, Dahua Lin, Kai Chen, Feng Zhao

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention (2026.acl-long)

Challenge:	Existing studies evaluate the tool utilization ability of large language models based on the final output or only consider the single-step tool calling.
Approach:	They propose a new approach to evaluate the tool utilization capability of large language models (LLMs) they decompose the tool usage into multiple sub-processes, including instruction following, planning, reasoning, retrieval, understanding, and review.
Outcome:	The proposed model exhibits consistency with the outcome-oriented evaluation and provides a more fine-grained analysis of the capabilities of LLMs.

Copied to clipboard

Shuochen Chang, Tong Bai, Xiaofeng Zhang, Qianli Ma, Qingyang Liu, Zhaohe Liao, Yibo Miao, Li Niu