Papers by Yan Zheng

DORE: Document Ordered Relation Extraction based on Generative Framework (2022.findings-emnlp)

Challenge:	Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities.
Approach:	They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters.
Outcome:	The proposed model retains the modal understanding capabilities of each original model.

Copied to clipboard

Qipeng Guo, Yuqing Yang, Hang Yan, Xipeng Qiu, Zheng Zhang

Cross-Lingual Phrase Retrieval (2022.acl-long)

Challenge:	Existing generative methods do not fit document-level relation extraction tasks where there are multiple entities and relational facts.
Approach:	They propose to generate a symbolic and ordered sequence from relation matrix which is easier to learn and introduce several negative sampling strategies to improve the performance with balanced signals.
Outcome:	The proposed method can improve the performance of the generative DocRE models on four datasets.

Copied to clipboard

Heqi Zheng, Xiao Zhang, Zewen Chi, Heyan Huang, Yan Tan, Tian Lan, Wei Wei, Xian-Ling Mao

Cross-Lingual Transfer

Challenge:	Existing approaches to cross-lingual phrase retrieval learn word or sentence representations in word or sentences.
Approach:	They propose a cross-lingual phrase retrieval model that extracts phrase representations from unlabeled example sentences.
Outcome:	The proposed model outperforms state-of-the-art methods on a large-scale cross-lingual phrase retrieval dataset, showing it can perform in an unseen language pair during training.

LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Copied to clipboard

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Experience-driven Multi-turn Reinforcement Learning for GUI Agents (2026.acl-long)

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

Copied to clipboard

Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang

Challenge:	GUI agents have demonstrated remarkable progress in automating complex user interface interactions . training such agents for long-horizon tasks remains challenging due to limited rewards and prohibitive costs.
Approach:	They propose a method that leverages expert trajectories as environment experiences for on-policy multi-turn training.
Outcome:	The proposed method achieves significant gains over the base model with 1K public trajectories as RL experiences . it achieves competitive performance against strong baselines such as UI-TARS-7B and GPT-4o .

Instruction-following Evaluation through Verbalizer Manipulation (2024.findings-naacl)

Copied to clipboard

Shiyang Li, Jun Yan, Hai Wang, Zheng Tang, Xiang Ren, Vijay Srinivasan, Hongxia Jin

Sentiment Analysis

Challenge:	Existing benchmarks focus on common instructions that align well with what the model learned during training, but proficiency in responding to these instructions does not necessarily imply strong ability in instruction following.
Approach:	They propose a new instruction-following evaluation protocol called verbalizer manipulation that instructs the model to verbalize the task label with words aligning with model priors to different extents.
Outcome:	The proposed protocol can be integrated with any classification benchmark to examine the model’s reliance on priors and its ability to override them to accurately follow the instructions.

Budget-Constrained Tool Learning with Planning (2024.findings-acl)

Copied to clipboard

Yuanhang Zheng, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Challenge:	Existing methods for budget-constrained tool learning have been overlooked . et al., 2023b) compared tool learning with other methods to improve performance .
Approach:	They propose a method for budget-constrained tool learning by creating a preferable plan under the budget constraint before utilizing the tools.
Outcome:	The proposed method reduces the cost of tool learning and reaches competitive Pass Rate.

Copied to clipboard

Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai

A Unified Generative Framework for Various NER Subtasks (2021.acl-long)

Challenge:	Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach:	They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome:	The proposed model achieves comparable performance to standard dense models with more parameters.

Copied to clipboard

Hang Yan, Tao Gui, Junqi Dai, Qipeng Guo, Zheng Zhang, Xipeng Qiu

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)

Challenge:	Named Entity Recognition (NER) is the task of identifying spans that represent entities in sentences.
Approach:	They propose to formulate NER subtasks as entity span sequence generation task . framework can be used to solve all three kinds of NER tasks without tagging schema .
Outcome:	The proposed framework achieves state-of-the-art (SoTA) or near SoTA performance on eight English NER datasets.

Copied to clipboard

Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Challenge:	Existing presentation agents rely on predefined workflows and fixed templates to generate presentations.
Approach:	They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation.
Outcome:	The proposed framework can be used to generate presentations with environmental observations.

Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)

Copied to clipboard

Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu

Bridging Distance and Spectral Positional Encodings via Anchor-Based Diffusion Geometry Approximation (2026.acl-long)

Challenge:	Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole .
Approach:	They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task.
Outcome:	The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices.

Copied to clipboard

Yan Zimo, Zheng Xie, Runfan Duan, Chang Liu, Wumei Du

Structured Data in NLP

Challenge:	Molecular graph learning benefits from positional signals that capture local neighborhoods and global topology.
Approach:	They propose to use anchor-based distance encodings to approximate diffusion geometry.
Outcome:	The proposed model outperforms models without positional encodings on DrugBank with a shared GNP-based DDI backbone.

Flaming-hot Initiation with Regular Execution Sampling for Large Language Models (2025.findings-naacl)

Copied to clipboard

Weizhe Chen, Zhicheng Zhang, Guanlin Liu, Renjie Zheng, Wenlei Shi, Chen Dun, Zheng Wu, Xing Jin, Lin Yan

RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities across various domains since the release of ChatGPT . a key challenge in developing these general capabilities is efficiently sourcing diverse, high-quality data.
Approach:	They introduce Flaming-hot Initiation with Regular Execution (FIRE) sampling to efficiently find good responses by promoting diversity.
Outcome:	The proposed method enhances inference-time generation quality and benefits training in the alignment stage.

Copied to clipboard

Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang

Text Generation

Challenge:	Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains, but their ability to replicate complex, multi-panel visualizations remains largely unassessed.
Approach:	They propose a large-scale benchmark to evaluate chart generation from large- scale raw data and assess iterative code refinement in a multi-turn conversational setting.
Outcome:	The new benchmark evaluates 14 leading VLMs on real-world data and shows they struggle with complex plot structures and authentic data.

MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Chia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh, Menghai Pan, Chin-Chia Michael Yeh, Guanchu Wang, Mingzhi Hu, Zhichao Xu, Yan Zheng, Mahashweta Das, Na Zou

Information Retrieval

Challenge:	Existing RAG systems struggle with the quality of retrieval documents, causing performance degradation and reducing performance.
Approach:	They propose a training-free RAG framework that leverages multiple LLM agents to collaboratively filter and score retrieved documents.
Outcome:	The proposed framework outperforms existing RAG frameworks in QA benchmarks and shows superior answer consistency and answer accuracy over baseline methods.

Enhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings (2025.emnlp-industry)

Copied to clipboard

Xiran Fan, Zhimeng Jiang, Chin-Chia Michael Yeh, Yuzhong Chen, Yingtong Dou, Menghai Pan, Yan Zheng

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)

Challenge:	Existing foundation models for tabular transactional data rely on index-based representations for categorical merchant fields.
Approach:	They propose a framework that uses LLM-generated embeddings as semantic initializations for lightweight transaction models.
Outcome:	The proposed framework improves performance on large transaction datasets.

Copied to clipboard

Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum

Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window.
Approach:	They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window.
Outcome:	The proposed model scales to multi-million-token effective TTC without exceeding context limits.

Copied to clipboard

Wentao Zhang, Yan Zhuang, ZhuHang Zheng, Mingfei Zhang, Jiawen Deng, Fuji Ren

Robustness in NLP

Challenge:	Existing jamming attacks on RAG systems typically induce explicit refusals or denial-of-service behaviors.
Approach:	They propose a black-box attack framework that exploits safety-aligned behaviors of large language models to trigger soft failures.
Outcome:	The proposed framework exploits safety-aligned behaviors of large language models to induce soft failures.

DNA: Denoised Neighborhood Aggregation for Fine-grained Category Discovery (2023.emnlp-main)

Copied to clipboard

Wenbin An, Feng Tian, Wenkai Shi, Yan Chen, Qinghua Zheng, QianYing Wang, Ping Chen

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)

Challenge:	Existing methods to learn compact cluster representations from coarsely labeled data are noisy and degrade the quality of learning.
Approach:	They propose a framework that encodes semantic structures of data into the embedding space . they retrieve k-nearest neighbors of a query as positive keys to capture similarities .
Outcome:	The proposed framework can retrieve more accurate neighbors and outperform state-of-the-art models by a large margin.

Copied to clipboard

Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng

Challenge:	Existing studies on large language model-based agents focus on evaluation benchmarks without training support.
Approach:	They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents.
Outcome:	The proposed model performs poorly in a large-scale and challenging shopping environment in China.

Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks (D19-60)

Copied to clipboard

Xiepeng Li, Zhexi Zhang, Wei Zhu, Zheng Li, Yuan Ni, Peng Gao, Junchi Yan, Guotong Xie

A Parallelized Framework for Simulating Large-Scale LLM Agents with Realistic Environments and Interactions (2025.acl-industry)

Challenge:	Existing approaches to represent knowledge in the low-dimensional space are to leverage large-scale unsupervised text corpus to train fixed or contextual representations.
Approach:	They propose to leverage large-scale unsupervised text corpus to train fixed or contextual language representations and to express knowledge into a knowledge graph (KG) they incorporate distributional representations of a KG onto the representations from pre-trained language models, via simply concatenation or multi-head attention.
Outcome:	The proposed models outperform the other models on the COIN: COmmonsense INference in Natural Language Processing (COIN) Workshop datasets.

Copied to clipboard

Jun Zhang, Yuwei Yan, Junbo Yan, Zhiheng Zheng, Jinghua Piao, Depeng Jin, Yong Li

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection (2024.naacl-long)

Challenge:	Existing work on large language models lacks a realistic environment and parallelized framework to support complex interactions between agents and environments.
Approach:	They propose a framework that integrates realistic societal environments and parallelized interactions to support simulations of large-scale agents.
Outcome:	The proposed framework can support simulations of 30,000 agents faster than the wall-clock time with 24 NVIDIA A800 GPUs and the performance increases linearly with the increase of LLM computational resources.

Copied to clipboard

Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin

DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering (2025.acl-long)

Challenge:	Instruction-tuned Large Language Models (LLMs) can modulate responses based on human instructions, but they can be maliciously steered to impact society in subtle but persistent ways.
Approach:	They propose a backdoor attack setting that allows an attacker to inject a virtual prompt into an LLM to steer it without any explicit injection at its input.
Outcome:	The proposed method is able to poison the model's instruction tuning data and show that it is highly effective in steering the model.

Copied to clipboard

Rong Cheng, Jinyi Liu, Yan Zheng, Fei Ni, Jiazhen Du, Hangyu Mao, Fuzheng Zhang, Bo Wang, Jianye Hao

Natural Language Interfaces

Challenge:	Existing approaches to multi-hop question answering struggle to identify and organize dynamic knowledge . et al., 2023; Liu e.t. al. 2023) suggest a dual-process framework for multi-step reasoning .
Approach:	They propose a synergistic dual-process framework that integrates reasoning and retrieval.
Outcome:	The proposed framework improves answer accuracy and coherence even in smaller-scale models.

Well Begun Is Half Done: An Implicitly Augmented Generative Framework with Distribution Modification for Hierarchical Text Classification (2024.lrec-main)

Copied to clipboard

Huawen Feng, Jingsong Yan, Junlong Liu, Junhao Zheng, Qianli Ma

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)

Challenge:	Hierarchical Text Classification (HTC) is a challenging task which aims to extract the labels in a tree structure corresponding to a given text.
Approach:	They propose an explicit-agmented-generativ-e framework with distribution modification for hierarchical text classification.
Outcome:	The proposed framework improves on the initial distributions of tail classes and avoids misinterpreting predictions on unbalanced data.

Copied to clipboard

Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu, Wenqi Zhang, Yuchen Yan, Qiuying Peng, Jun Wang, Weiming Lu

Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout Grounding (2025.findings-emnlp)

Challenge:	Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification.
Approach:	They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth.
Outcome:	The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation.

Copied to clipboard

Hangdi Xing, Feiyu Gao, Qi Zheng, Zhaoqing Zhu, Zirui Shao, Ming Yan

Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning (2026.findings-acl)

Challenge:	Existing methods fragment document parsing into pipeline of separated subtasks, resulting in incomplete semantics and error propagation.
Approach:	They propose an end-to-end document parsing framework that leverages vision-language priors of MLLMs.
Outcome:	The proposed method surpasses existing methods significantly in document parsing . it leverages the vision-language priors of MLLMs to decouple parse and layout grounding based on visual information.

Copied to clipboard

Zichuan Fu, Xian Wu, Guojing Li, Yejing Wang, Yijun Chen, Zhao Zihao, Luo Yixuan, Hanyu Yan, Yefeng Zheng, Xiangyu Zhao

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Challenge:	Recent advances in large language models (LLMs) have catalyzed the rise of reasoningintensive inference paradigms, where models perform explicit step-by-step reasoning before generating final answers.
Approach:	They propose a large-small LLM collaboration framework that synergizes large and small language models to achieve high-quality reasoning with significantly reduced computational cost.
Outcome:	The proposed framework outperforms the mentor LLM while preserving the benefits of the thinking paradigm of LLMs.

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

Marrying Up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding (P18-1)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Bingfeng Luo, Yansong Feng, Zheng Wang, Songfang Huang, Rui Yan, Dongyan Zhao

Challenge:	Experimental results show that the combination of regular expressions and NNs improves learning effectiveness when a small number of training examples are available.
Approach:	They propose to combine a neural network (NN) with regular expressions (RE) to improve supervised learning for NLP by exploiting the rich expressiveness of REs at different levels within a NN.
Outcome:	The proposed approach significantly improves learning effectiveness when a small number of training examples are available.

DeltaNet: Conditional Medical Report Generation for COVID-19 Diagnosis (2022.coling-1)

Copied to clipboard

Xian Wu, Shuxin Yang, Zhaopeng Qiu, Shen Ge, Yangtian Yan, Xingwang Wu, Yefeng Zheng, S. Kevin Zhou, Li Xiao

Object-oriented Neural Programming (OONP) for Document Understanding (P18-1)

Challenge:	X-ray and CT are the gold standard for COVID-19 diagnosis and treatment . however, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists.
Approach:	They propose to use X-ray and CT to generate medical reports automatically . they evaluate DeltaNet on a COVID-19 dataset, where it outperforms state-of-the-art approaches .
Outcome:	The proposed system outperforms state-of-the-art methods on a COVID-19 dataset.

Copied to clipboard

Zhengdong Lu, Xianggen Liu, Haotian Cui, Yukun Yan, Daqi Zheng

LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models (2025.acl-long)

Challenge:	Object-oriented Neural Programming (OONP) is a framework for semantically parsing documents in domains.
Approach:	They propose a framework for semantically parsing documents in specific domains using OONP . OOPN parsers use a rich family of operations to represent the semantics of the document .
Outcome:	The proposed framework can learn to handle fairly complicated ontology with training data of modest sizes.

Copied to clipboard

Yan Wang, Ling Ding, Tien N Nguyen, Shaohua Wang, Yanan Zheng

Text Generation

Challenge:	Large Language Models often require significant computational resources, often constraining input word or code token lengths.
Approach:	They propose to use the encoder-decoder attention scores to represent the importance of a code token across multiple contexts to reduce training and prediction time.
Outcome:	The proposed approach outperforms the SOTAs DietCode and SlimCode in code search and summarization tasks.

Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization (2024.lrec-main)

Copied to clipboard

Linzhi Wu, Xingyu Zhang, Yakun Zhang, Changyan Zheng, Tiejun Liu, Liang Xie, Ye Yan, Erwei Yin

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models (2026.findings-acl)

Challenge:	Lip reading is a process of interpreting silent speech from visual lip movements . but lip reading in cross-speaker scenarios poses a challenging problem due to inter-speech variability .
Approach:	They propose to exploit lip landmark-guided visual clues instead of mouth-cropped images as input features.
Outcome:	Experimental results show that the proposed approach reduces speaker-specific appearance characteristics in cross-speaker scenarios.

Copied to clipboard

Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang

Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)

Challenge:	Existing static image-text benchmarks are insufficient for evaluating multimodal large language models’ dynamic perception and interactive reasoning abilities.
Approach:	They propose a game-based evaluation framework to assess multimodal large language models’ visual reasoning in dynamic, continuous-space environments.
Outcome:	The proposed framework systematically assesses MLLMs’ visual reasoning in dynamic, continuous-space environments.

Copied to clipboard

Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values.
Approach:	They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values .
Outcome:	The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets.

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (2025.findings-acl)

Copied to clipboard

Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen

Asymmetric Conflict and Synergy in Post-training for LLM-based Multilingual Machine Translation (2025.findings-acl)

Challenge:	Image captioning has been a challenge for vision-language researchers for decades . current VLMs focus on tasks like visual question answering (YA) but image captioning is not as advanced as expected.
Approach:	They evaluate VLMs' performance on image captioning using human annotations . they find that some metrics show high caption-level agreement with humans .
Outcome:	The proposed model outperforms open-source models on image captioning . it achieves 93.4% correlation with human rankings at $4 per test .

Copied to clipboard

Tong Zheng, Yan Wen, Huiwen Bao, Junfeng Guo, Heng Huang

Multilinguality

Challenge:	Existing work in LLM-based MMT typically mitigates the Curse of Multilinguality . asymmetric phenomenon in linguistic conflicts and synergy varies in different translation directions .
Approach:	They propose a direction-aware training approach to address asymmetry in linguistic conflicts and synergy . they propose X-ALMA-13B-Pretrain with multilingual pre-training to achieve comparable performance .
Outcome:	The proposed method achieves comparable performance to X-ALMA-13B-Pretrain (only SFT) with fewer pretraining tokens and 17B parameters.

A Unified Generative Framework for Aspect-based Sentiment Analysis (2021.acl-long)

Copied to clipboard

Hang Yan, Junqi Dai, Tuo Ji, Xipeng Qiu, Zheng Zhang

Sentiment Analysis

Challenge:	Existing complicated ABSA models focus on subtasks, which leads to complicated solutions . et al., j. c. d. r., and j dr. s. v. present a unified approach to solve seven subtask tasks in one framework.
Approach:	They redefine every subtask target as a sequence mixed by pointer indexes and sentiment class indexe . they exploit the pre-training sequence-to-sequence model BART to solve all ABSA subtasks in an end-to end framework.
Outcome:	The proposed framework achieves substantial performance gain and provides a real unified solution for the whole ABSA subtasks.

Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field (2023.acl-long)

Copied to clipboard

Zixia Jia, Zhaohui Yan, Wenjuan Han, Zilong Zheng, Kewei Tu

What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? (2024.naacl-long)

Challenge:	Existing approaches to joint Information Extraction (IE) neglect cross-instance or cross-task dependencies.
Approach:	They propose a joint IE framework that formulates joint 'conditional random field' to model cross-instance interactions . they incorporate a high-order neural decoder that is unfolded from a mean-field variational inference method .
Outcome:	The proposed approach improves on three IE tasks compared with baseline and prior work.

Copied to clipboard

Yan Zeng, Hanbo Zhang, Jiani Zheng, Jiangnan Xia, Guoqiang Wei, Yang Wei, Yuchen Zhang, Tao Kong, Ruihua Song

The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection (2020.emnlp-main)

Challenge:	Recent advances in GPT-4V have demonstrated remarkable multi-modal capabilities in processing image inputs and following open-ended instructions.
Approach:	They propose a plug-and-play technique to enhance multi-modal LLMs . they propose 'lynx' to train multi-modal LLM models .
Outcome:	The proposed training strategy improves understanding accuracy and instruction-following proficiency of multi-modal models.

Copied to clipboard

Zibo Lin, Deng Cai, Yan Wang, Xiaojiang Liu, Haitao Zheng, Shuming Shi

Information Retrieval

Challenge:	Existing approaches to learning-to-rank response selection are suboptimal due to ignorance of diversity of response quality.
Approach:	They propose to use off-the-shelf response retrieval models as automatic grayscale data generators to train response selection models.
Outcome:	The proposed approach can be automated without human effort on grayscale data.

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models (2024.findings-emnlp)

Copied to clipboard

Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu

Learning Goal-oriented Dialogue Policy with opposite Agent Awareness (2020.aacl-main)

Challenge:	Recent advances in multimodal large language models have seen remarkable progress for medical decision-making, however, they are designated for specific classification or generative tasks and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing.
Approach:	They propose a framework that tackles discriminative and generative multimodal medical tasks using multimodal alignment, instruction tuning and routing.
Outcome:	The proposed model can achieve superior performance to or on par with state-of-the-art baselines while only requiring 30%-50% of activated model parameters.

Copied to clipboard

Zheng Zhang, Lizi Liao, Xiaoyan Zhu, Tat-Seng Chua, Zitao Liu, Yan Huang, Minlie Huang

Dialogue Systems & Conversational Agents

Challenge:	Existing approaches for goal-oriented dialogue policy learning focus on the target agent policy and treat the opposite agent policy as part of the environment.
Approach:	They propose a framework for policy learning in goal-oriented dialogues that uses the opposite agent's policy estimation to improve the target agent by regarding it as part of the target policy.
Outcome:	The proposed framework shows superior performance over state-of-the-art models on cooperative and competitive dialogue tasks.

Investigating Glyph-Phonetic Information for Chinese Spell Checking: What Works and What’s Next? (2023.findings-acl)

Copied to clipboard

Xiaotian Zhang, Yanjun Zheng, Hang Yan, Xipeng Qiu

Syntactic Text Processing

Challenge:	Pre-trained Chinese language models have shown impressive performance on a wide range of NLP tasks, but the generalization ability of these models has not been well understood.
Approach:	They propose to use glyph-phonetic information to improve Chinese spell checking models . they propose a new, more challenging, and practical setting for testing the generalizability of CSC models.
Outcome:	The proposed model incorporates glyph-phonetic information and is more challenging and practical.

Let Retrievers Think Before Action: Thought-Augmented Embedding for Dense Retrieval (2026.findings-acl)

Copied to clipboard

Ruiran Yan, Wen Xiong, Ze Liu, Chaozhuo Li, Hao Liao, Defu Lian, Zheng Liu

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization (2024.findings-emnlp)

Challenge:	Large language models have demonstrated that explicit step-by-step thinking can substantially improve performance on complex tasks.
Approach:	They propose a model that generates preliminary thoughts for input queries before document retrieval.
Outcome:	The proposed model generates preliminary thoughts for input queries before document retrieval.

Copied to clipboard

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu, Zheng Liu, Tun Lu, Xing Xie, Ning Gu

Jailbreaking LLMs with Arabic Transliteration and Arabizi (2024.emnlp-main)

Challenge:	Existing methods to steer LLMs towards human preference suffer from noisy positive-negative training pairs.
Approach:	They propose a distributional preference optimization method which maximizes discrepancy between dispreferred responses and generated non-negative ones.
Outcome:	The proposed method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence.

Copied to clipboard

Mansour Ghanim, Saleh Almohaimeed, Mengxin Zheng, Yan Solihin, Qian Lou

Dialogue Meaning Representation for Task-Oriented Dialogue Systems (2022.findings-emnlp)

Challenge:	Large Language Models (LLMs) are vulnerable to ‘jailbreak’ attacks, focusing on the Arabic language and its various forms.
Approach:	They propose to use Arabic transliteration and chatspeak to generate unsafe content on platforms like OpenAI GPT-4 and Anthropic Claude 3 Sonnet.
Outcome:	The proposed model could generate unsafe content on platforms like OpenAI GPT-4 and Anthropic Claude 3 Sonnet, highlighting the need for more comprehensive safety training across all language forms.

Copied to clipboard

Xiangkun Hu, Junqi Dai, Hang Yan, Yi Zhang, Qipeng Guo, Xipeng Qiu, Zheng Zhang

Natural Language Interfaces

Challenge:	Existing work on dialogue meaning representations is limited in scalability for complex expressions.
Approach:	They propose a pliable and easily extendable representation for task-oriented dialogue . they propose an inheritance hierarchy mechanism focusing on domain extensibility .
Outcome:	The proposed representation can be easily extended to a task-oriented dialogue dataset.

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization (2025.findings-emnlp)

Copied to clipboard

Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jingpu Yang, Hong-Qing Liang, Yan Hu, Benyou Wang

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

Challenge:	characterization imaging data is fundamental to acquiring materials information.
Approach:	a team of researchers develop a benchmark for materials characterization imaging data . the goal is to bridge this gap by addressing 1,500 questions that require expert-level expertise.
Outcome:	a new benchmark for materials characterization imaging data is presented . the benchmark reveals that MLLMs perform poorly when addressing higher-level questions .

Copied to clipboard

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

Demystify the Role of Memory in Machine Learning Engineering Agents (2026.findings-acl)

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

Copied to clipboard

Xinyu Zhao, Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Jiarui Sun, Yan Zheng, Mahashweta Das, Tianlong Chen

Challenge:	Unlike short, reactive exchanges, MLE agents solve tasks through cycles of experimentation and improvement where past errors can inform future success.
Approach:	They propose a dynamic coding memory that captures and reuses debugging experiences and integrates it into two representative agent paradigms.
Outcome:	The proposed agent model captures and reuses debugging experiences and integrates it into two agent paradigms.

Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold (2022.naacl-main)

Copied to clipboard

Yanan Wu, Keqing He, Yuanmeng Yan, QiXiang Gao, Zhiyuan Zeng, Fujia Zheng, Lulu Zhao, Huixing Jiang, Wei Wu, Weiran Xu

A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models (2025.findings-acl)

Challenge:	Existing methods for OOD detection are based on labeled in-domain data . detecting out-of-domain (OOD) or unknown intents is challenging .
Approach:	They propose a novel reassigned contrastive learning method to discriminate IND intents for over-confident OOD and an adaptive class-dependent local threshold mechanism to separate similar IND and OOD intents.
Outcome:	The proposed method is effective for both aspects of overconfidence issues.

Copied to clipboard

Shuliang Liu, Hongyi Liu, Aiwei Liu, Duan Bingchen, Zheng Qi, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, Xuming Hu

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)

Challenge:	Existing methods for detection of misinformation generated by large language models fail to mitigate societal risks . authors propose a paradigm shift from passive detection to anticipatory mitigation strategies . existing defenses remain reactionary in an era demanding proactive defense, authors say .
Approach:	They propose a three-pillar approach to prevent misinformation by fortifying integrity of training data and inference reliability by embedding self-corrective mechanisms during reasoning.
Outcome:	The proposed framework improves existing methods in misinformation prevention by 63% . it demonstrates that existing methods exhibit false negative rates against misinformation .

Copied to clipboard

Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges (2025.findings-acl)

Challenge:	Existing research on reinforcement learning for LLMs under data scarcity has not been unified.
Approach:	They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric.
Outcome:	The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area.

Copied to clipboard

Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qingsong Wen, Xuming Hu

Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows (2026.findings-acl)

Challenge:	This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models . integrating large language model with mathematical reasoning tasks is becoming significant as AI advances .
Approach:	They review over 200 studies published since 2021 and examine the state-of-the-art developments in Math-LLMs . they identify five major challenges hindering the realization of AGI in this domain .
Outcome:	The authors examine the state-of-the-art developments in Math-LLMs with a focus on multimodal settings.

Copied to clipboard

Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Adina Yakefu, Shuxin Zheng

Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis (2022.emnlp-main)

Challenge:	FinWorkBench evaluates real-world enterprise-grade finance and accounting workflows . a human evaluation of GPT 5.1 Pro passes only 38.4% of workflows, a study finds .
Approach:	They propose a workflow construction process that combines LLM-assisted mining and expert annotation to build 172 composite workflows.
Outcome:	The proposed process combines expert annotation with LLM-assisted mining of workflows from authentic enterprise environments.

Copied to clipboard

Zhihao Du, ShiLiang Zhang, Siqi Zheng, Zhi-Jie Yan

Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations (2025.findings-emnlp)

Challenge:	Existing approaches to speaker diarization treat speaker dependency and overlaps as multi-label classification problems.
Approach:	They propose to reformulate overlapped speaker diarization task as a single-label prediction problem via power set encoding (PSE) to overcome the disadvantages, they propose a speaker overlap-aware neural diarisation model which incorporates a context-independent scorer and a contextual-dependent score.
Outcome:	The proposed model outperforms the state-of-the-art methods on speaker voice activity detection and improves relative diarization error reduction by 6.30%.

Copied to clipboard

Mansour Al Ghanim, Jiaqi Xue, Rochana Prih Hastuti, Mengxin Zheng, Yan Solihin, Qian Lou

Cross-Lingual Transfer

Challenge:	a study focuses on evaluating watermarking methods for the English language . the literature for evaluating cross-lingual watermarks is scarce .
Approach:	They evaluate representative watermarking methods in four different languages . they examine the quality of text under different watermark procedures .
Outcome:	The proposed method is compared with other evaluation methods in four different languages.

Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)

Copied to clipboard

Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality.
Approach:	They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward.
Outcome:	The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability.

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning (2025.findings-acl)

Copied to clipboard

Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, Xuming Hu

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Challenge:	Existing methods for MU forget quality and model utility are not fully explored for safety in MLLMs.
Approach:	They propose a safety unlearning benchmark for MLLMs to measure over-forgetting . they propose MU methods to forget quality and model utility .
Outcome:	The proposed method reduces over-forgetting by 79.5% while maintaining forget quality and model utility.

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding (2025.emnlp-main)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

Zirui Shao, Feiyu Gao, Zhaoqing Zhu, Chuwei Luo, Hangdi Xing, Zhi Yu, Qi Zheng, Ming Yan, Jiajun Bu

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models (2025.findings-acl)

Challenge:	Multimodal large language models (MLLMs) have shown impressive capabilities in document understanding due to different types of annotation noise in training.
Approach:	They propose a method to reduce C&P knowledge conflicts across all tested MLLMs . they propose to use annotation noise to train models to understand document content .
Outcome:	The proposed method reduces C&P knowledge conflicts across all tested MLLMs and enhances their performance in both cognitive and perceptual tasks.

Copied to clipboard

Jiahao Huo, Yibo Yan, Xu Zheng, Yuanhuiyi Lyu, Xin Zou, Zhihua Wei, Xuming Hu

NLoPT: N-gram Enhanced Low-Rank Task Adaptive Pre-training for Efficient Language Model Adaption (2024.lrec-main)

Challenge:	Recent advances in machine learning (MU) have enabled the selective removal of private or sensitive information encoded within deep neural networks.
Approach:	They propose to "reformulate" the task of multimodal MU in the era of MLLMs by preserving only the visual patterns associated with a given entity while preserving the corresponding textual knowledge.
Outcome:	The proposed method surpasses baselines that finetuned MLLMs with VQA data directly through Gradient Ascent (GA) or Negative Preference Optimization (NPO), across all evaluation dimensions.

Copied to clipboard

Hao Gu, Jiangyan Yi, Zheng Lian, Jianhua Tao, Xinrui Yan

Position: LLMs Can be Good Tutors in English Education (2025.emnlp-main)

Challenge:	Pre-trained Language Models (PLMs) have superior performance on downstream tasks . however, conventional TAPT adjusts all parameters of the PLMs, which distorts the learned generic knowledge embedded in the original PLM's weights.
Approach:	They propose a two-step n-gram enhanced low-rank task adaptive pre-training method to customize a PLM to the downstream task.
Outcome:	The proposed method improves performance on six datasets from four domains.

Copied to clipboard

Jingheng Ye, Shen Wang, Deqing Zou, Yibo Yan, Kun Wang, Hai-Tao Zheng, Ruitong Liu, Zenglin Xu, Irwin King, Philip S. Yu, Qingsong Wen

Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models (2025.findings-acl)

Challenge:	Recent efforts to integrate large language models into English education lack adaptability to language learning.
Approach:	They argue that large language models can be effective tutors in English education . they encourage interdisciplinary research to explore these roles, fostering innovation and risks .
Outcome:	The proposed models can play three critical roles: 1) as data enhancers, 2) as task predictors, 3) as agents, enabling personalized and inclusive education.

Copied to clipboard

Kening Zheng, Junkai Chen, Yibo Yan, Xin Zou, Huiyu Zhou, Xuming Hu

A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarization (2021.findings-emnlp)

Challenge:	Existing research focuses on object-level or attribute-level hallucinations, neglecting the more complex relation hallucinosities.
Approach:	They propose a comprehensive benchmark targeting relation hallucinations comprising over 20,000 real-world samples and a confidence-based mitigation strategy which reduces the halluciation rate by an average of 9.75% across three datasets.
Outcome:	The proposed approach reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot.

Copied to clipboard

Yuejie Lei, Fujia Zheng, Yuanmeng Yan, Keqing He, Weiran Xu

Dialogue Systems & Conversational Agents

Challenge:	Abstractive summarization models have achieved impressive results on document summarizing tasks, but their performance on dialogue modeling is poor due to the crude and straight methods for dialogue encoding.
Approach:	They propose a model that leverages Finer-grain universal Dialogue semantic Structures to model dialogue and generate better summaries.
Outcome:	The proposed model outperforms various dialogue summarization approaches and achieves state-of-the-art (SOTA) ROUGE results on a SAMsum dataset.

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems (2020.acl-demos)

Copied to clipboard

Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang

Natural Language Interfaces

Challenge:	ConvLab-2 inherits Convlab's framework but integrates more powerful dialogue models and supports more datasets.
Approach:	They present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models and perform an end-to-end evaluation.
Outcome:	The new tool inherits ConvLab's framework and extends it by integrating many recently proposed state-of-the-art dialogue models.

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)

Copied to clipboard

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

Visual Data in NLP

Challenge:	Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment.
Approach:	They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives.
Outcome:	The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering.

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Copied to clipboard

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Programming Languages in NLP

Challenge:	Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach:	They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome:	The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.

mABC: Multi-Agent Blockchain-inspired Collaboration for Root Cause Analysis in Micro-Services Architecture (2024.findings-emnlp)

Copied to clipboard

Wei Zhang, Hongcheng Guo, Jian Yang, Zhoujin Tian, Yi Zhang, Yan Chaoran, Zhoujun Li, Tongliang Li, Xu Shi, Liangfan Zheng, Bo Zhang

Understanding Gender Bias in Knowledge Base Embeddings (2022.acl-long)

Challenge:	Root cause analysis (RCA) in Micro-services architectures with escalating complexity is challenging due to fault propagation and circular dependencies among nodes.
Approach:	They propose a framework where multiple agents follow Agent Workflow and collaborate in blockchain-inspired voting to ensure the reliability of root cause analysis.
Outcome:	The proposed framework reduces the number of steps and standardizes task processing through Agent Workflow.

Copied to clipboard

Yupei Du, Qi Zheng, Yuanbin Wu, Man Lan, Yan Yang, Meirong Ma

Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering (P19-1)

Challenge:	Knowledge base (KB) embeddings have been shown to contain gender biases . authors develop two new bias measures to quantify them and trace their origins in KB .
Approach:	They propose two ways to quantify gender biases in knowledge base (KB) embeddings . they use the influence function to inspect the contribution of each triple in KB to the overall group bias .
Outcome:	The proposed measures are compared with real-world census data to examine gender biases.

Copied to clipboard

Peng Wu, Shujian Huang, Rongxiang Weng, Zaixiang Zheng, Jianbing Zhang, Xiaohui Yan, Jiajun Chen

War of Thoughts: Competition Stimulates Stronger Reasoning in Large Language Models (2025.findings-acl)

Challenge:	Existing approaches to detect relation detection only get high accuracy for questions whose relations have been seen in training data.
Approach:	They propose a method to learn representation mapping for both seen and unseen relations based on previously learned relation embedding.
Outcome:	The proposed method improves the performance of unseen relations while keeping the performance comparable to the state-of-the-art.

Copied to clipboard

Yibin Chen, Jinyi Liu, Yan Zheng, Yifu Yuan, Jianye Hao

Hallucination Detection for Generative Large Language Models by Bayesian Sequential Estimation (2023.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs) have reshaped the landscape of reasoning tasks.
Approach:	They propose a method that enhances LLM reasoning without finetuning by using test-time scaling.
Outcome:	The proposed method outperforms baseline models in both budget and model size.

Copied to clipboard

Xiaohua Wang, Yuliang Yan, Longtao Huang, Xiaoqing Zheng, Xuanjing Huang

Relaxing the Constraints: A Dual-Importance Projection Mechanism for Lifelong Model Editing (2026.findings-acl)

Challenge:	Existing methods for detecting hallucinations require large numbers of observations to be retrieved, increasing response times.
Approach:	They propose a framework that leverages Bayesian sequential analysis to optimize the trade-off between costs and benefits during the hallucination detection process.
Outcome:	The proposed framework surpasses existing methods in efficiency and precision of hallucination detection.

Copied to clipboard

Zhenghai Chen, Senbin Xu, Jiaxi Tan, Xinhua Wu, Yan Zhang, Xiawu Zheng, Shengchuan Zhang, Ke Li, Sicheng Zhao, Liujuan Cao, Rongrong Ji

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)

Challenge:	Existing knowledge editing methods rely on strict orthogonal projection to preserve previously edited knowledge, but this constraint limits gradient expressiveness, resulting in degradation of model generalization and overall performance as the number of edits increases.
Approach:	They propose a method that leverages Singular Value Decomposition to identify critical gradient subspaces and introduces a dual mechanism comprising "accumulated importance" and "projection importance"
Outcome:	Extensive experiments on five mainstream LLMs show that the proposed method achieves an average comprehensive performance improvement of 10.36% and effectively maintains the model’s general capabilities on downstream tasks.

Copied to clipboard

Yi Sun, Han Wang, Jiaqiang Li, Jiacheng Liu, Xiangyu Li, Hao Wen, Yizhen Yuan, Huiwen Zheng, Yan Liang, Yuanchun Li, Yunxin Liu

Low-Resource NLP

Challenge:	Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints.
Approach:	They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking .
Outcome:	The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints.

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Copied to clipboard

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen

Challenge:	a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach:	They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome:	The proposed benchmarks show that the current models perform worse than the human ceiling.

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models (2025.naacl-long)

Copied to clipboard

Ying Nie, Binwei Yan, Tianyu Guo, Hao Liu, Haoyu Wang, Wei He, Binfan Zheng, Weihao Wang, Qiang Li, Weijian Sun, Yunhe Wang, Dacheng Tao

LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored.
Approach:	They propose a benchmark to assess the financial knowledge of large language models (LLMs) in China.
Outcome:	The proposed benchmark is the most comprehensive evaluation benchmark to date for LLMs in finance.

Copied to clipboard

Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li

CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation (2025.emnlp-main)

Challenge:	Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training.
Approach:	They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks.

Copied to clipboard

Ziyue Liu, Ruijie Zhang, Zhengyang Wang, Mingsong Yan, Zi Yang, Paul D. Hovland, Bogdan Nicolae, Franck Cappello, Sui Tang, Zheng Zhang

Measure Children’s Mindreading Ability with Machine Reading (2023.findings-emnlp)

Challenge:	Large foundation models have become huge, but they consume computational resources in pretraining.
Approach:	They propose to replace full-size layers with compute-efficient auto-encoders that enforce low-rank activations throughout training.
Outcome:	The proposed method reduces the computing cost by 2pmbtimes and improves training throughput by 1.86pmtime.

Copied to clipboard

Yuliang Yan, Xiaohua Wang, Xiang Zhou, Xiaoqing Zheng, Xuanjing Huang

Visual Data in NLP

Challenge:	Existing scoring models do not take the features of the stories and video clips into account when scoring, which will reduce the accuracy of the models.
Approach:	They propose to leverage the features extracted from stories and videos related to the questions being asked during the children’s mindreading evaluation.
Outcome:	The proposed framework agrees well with human experts on scores produced by the models.

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use (2026.acl-industry)

Copied to clipboard

Yuanjie Lyu, Chengyu Wang, Haonan Zheng, Yuanhao Yue, Junbing Yan, Ming Wang, Jun Huang

AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis (2022.coling-1)

Challenge:	Modern industrial applications increasingly demand language models capable of multi-step reasoning and tool use in real-world settings.
Approach:	They propose a model family that trains via multi-round reinforcement learning on synthetic data and open-source data.
Outcome:	The proposed model train on synthetic and open-source data achieves strong performance on multiple agentic benchmarks and in an industrial agent system.

Copied to clipboard

Ziming Li, Yan Zhou, Weibo Zhang, Yaxin Liu, Chuanpeng Yang, Zheng Lian, Songlin Hu

Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs (2025.findings-emnlp)

Challenge:	Existing methods treat three modal features equally, without distinguishing the importance of different modalities. Existing models split the video into frames, leading to missing the global acoustic information.
Approach:	They propose a global Acoustic feature enhanced Modal-Order-Aware network to address these problems.
Outcome:	The proposed model outperforms state-of-the-art models on two public datasets.

Copied to clipboard

Yu Yan, Sheng Sun, Zhe Wang, Yijun Lin, Zenghao Duan, Zhifei Zheng, Min Liu, Zhiyi Yin, Jianping Zhang

M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation (2025.acl-long)

Challenge:	Large Language Models have been developed to deal with real-world crimes, but it remains unclear whether they internalize authentic knowledge or are forced to simulate toxic language patterns.
Approach:	They construct knowledge-intensive Q&A to investigate misuse threats of Large Language Models in terms of dangerous knowledge possession, harmful task planning utility, and harmfulness judgment robustness.
Outcome:	The findings raise concerns that jailbreak success is often attributable to a hallucination loop between jailbroken LLM and judger LLM .

Copied to clipboard

Zhaopeng Feng, Jiayuan Su, Jiamei Zheng, Jiahan Ren, Yan Zhang, Jian Wu, Hongwei Wang, Zuozhu Liu

Machine Translation

Challenge:	Recent advances in large language models (LLMs) have shown their potential to deliver human-like judgments.
Approach:	They propose a systematic LLM-based multi-agent framework for advanced LLM as-a-judge MT evaluation that integrates dimension-specific results into a final evaluation judgment.
Outcome:	The proposed framework outperforms existing LLM-as-a-judge methods and competes with state-of-the-art automatic metrics even when powered by a suboptimal model like GPT-4o mini.

Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens (2024.findings-emnlp)

Copied to clipboard

Weiyao Luo, Suncong Zheng, Heming Xia, Weikang Wang, Yan Lei, Tianyu Liu, Shuang Chen, Zhifang Sui

Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision (2026.acl-long)

Challenge:	Existing studies have explored compression and accumulation methods to compress contexts, but these methods lose useful context information during the compression process, leading to performance degradation.
Approach:	They propose a method that allows LLMs to take a deep breath and insert a special token at the end of each chunk.
Outcome:	Experiments on language modeling and out-of-domain tasks validate the superiority of the proposed method.

Copied to clipboard

Ge Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang, Yuhao Shang, Huiwen Zheng, Hongli Ma, Yan Liang, Yuanchun Li, Yunxin Liu