Papers by Tao Yang

FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval (2026.findings-acl)

Challenge:	Existing sentiment analysis models do not have sufficient sentiment corpus to detect sentiment in low-resource languages.
Approach:	They propose a cross-lingual sentiment analysis approach to transfer sentiment knowledge across languages . they use emojis to bridge the source and target languages to find the sentiment .
Outcome:	The proposed approach bridges the source and target languages using emojis . it can learn delicate sentiment knowledge, avoiding cross-lingual gaps .

Copied to clipboard

Caishuang Huang, Yang Qiao, Rongyu Zhang, Junjie Ye, Pu Lu, null Wuwenxi, Meng Zhou, Xiku Du, Qi Zhang, Tao Gui, Xuanjing Huang

ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition (2024.acl-long)

Challenge:	Existing data synthesis methods rely on static tools to generate queries . this approach fails to capture the implicit, event-driven nature of real-world needs .
Approach:	They propose a forward synthesis framework to generate high-quality financial dialogues . they construct a repository of 43,066 tools and synthesize over 148k dialogue instances .
Outcome:	Experiments show that models trained on FinToolSyn achieve a 21.06% improvement . the framework is designed to generate high-quality financial dialogues .

Copied to clipboard

Lu Ye, Ze Tao, Yong Huang, Yang Li

Pre-training Cross-Modal Retrieval by Expansive Lexicon-Patch Alignment (2024.lrec-main)

Challenge:	Experiments show that ChunkAttention can speed up the self-attention kernel by 3.2-4.8 compared to the start-of-the-art implementation.
Approach:	They propose a prefix-aware self-attention module that can detect matching prompt prefixes across multiple requests and share their key/value tensors in memory at runtime.
Outcome:	The proposed module can speed up the self-attention kernel by 3.2-4.8 compared to the start-of-the-art implementation, with the length of the system prompt ranging from 1024 to 4096.

Copied to clipboard

Yang Yiyuan, Guodong Long, Michael Blumenstein, Xiubo Geng, Chongyang Tao, Tao Shen, Daxin Jiang

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Recent large-scale vision-language pre-training relies on image-text global alignment by contrastive learning and is further boosted by fine-grained alignment in a weakly contrastive manner for cross-modal retrieval.
Approach:	They propose expansive lexicon-patch alignment (ELA) to align image patches with a vocabulary rather than only the words explicitly in the text for annotation-free alignment and information augmentation.
Outcome:	The proposed method outperforms state-of-the-art methods on cross-modal retrieval and can learn representative fine-grained information.

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

From Charts to Code: A Hierarchical Benchmark for Multimodal Models (2026.acl-long)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang

Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding (2025.findings-naacl)

Challenge:	Chart2Code is a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models.
Approach:	They introduce Chart2Code, a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models.
Outcome:	The proposed benchmark is the first to scale task complexity while capturing diverse scenarios.

Copied to clipboard

Shulei Wang, Shuai Yang, Wang Lin, Zirun Guo, Sihang Cai, Hai Huang, Ye Wang, Jingyuan Chen, Tao Jin

Task-oriented Domain-specific Meta-Embedding for Text Classification (2020.emnlp-main)

Challenge:	Existing chart-related training methods lack capabilities in information extraction, mathematical reasoning, and understanding of multiple chart types.
Approach:	They propose a two-stage training strategy and method for jointly training a vision encoder tailored for multi-type charts to address the deficiencies in chart types and limited scope of chart tasks in existing datasets.
Outcome:	The proposed dataset includes 21 diverse chart types and tasks, including data retrieval and mathematical reasoning.

Copied to clipboard

Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li

PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation (2025.emnlp-main)

Challenge:	Existing methods neglect domain-specific knowledge and use the same word embedding for each word in all domain-specified datasets.
Approach:	They propose a method to incorporate domain-specific and task-oriented information into meta-embeddings by combining pre-trained word embeddings.
Outcome:	The proposed method performs well on four text classification datasets and shows that it is compatible with existing methods.

Copied to clipboard

Tao Fan, Guoqiang Ma, Yuanfeng Song, Lixin Fan, Qiang Yang

Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) are becoming more popular and are gaining widespread use in artificial intelligence.
Approach:	They propose a unified framework that addresses both privacy preservation and model compression in federated settings.
Outcome:	The proposed framework maintains competitive performance comparable to full-sized LLMs while ensuring robust privacy protection through its federated architecture.

Copied to clipboard

Haonan He, Yuchen Ren, Yining Tang, Ziyang Xu, Junxian Li, Minghao Yang, Di Zhang, Yuan Dong, Tao Chen, Shufei Zhang, Yuqiang Li, Nanqing Dong, Wanli Ouyang, Dongzhan Zhou, Peng Ye

TexSmart: A System for Enhanced Natural Language Understanding (2021.acl-demo)

Challenge:	Biology-Instructions is the first large-scale instruction-tuning dataset for multi-omics biological sequences.
Approach:	They propose a large-scale instruction-tuning dataset for multi-omics biological sequences . they propose 'chatMultiOmics' to overcome limitations of current LLMs on multi-ome tasks .
Outcome:	The proposed dataset bridges LLMs and complex biological sequence-related tasks while maintaining conversational fluency.

Copied to clipboard

Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, ZhanHui Kang, Shuming Shi

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

Challenge:	TexSmart supports fine-grained named entity recognition (NER) Large-scale fine-granular entity types are expected to provide richer semantic information for downstream NLP applications.
Approach:	They introduce TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Outcome:	The proposed system supports fine-grained named entity recognition (NER) and enhanced semantic analysis functions.

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

PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction (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

Shulin Liu, Tao Yang, Tianchi Yue, Feng Zhang, Di Wang

Understanding GUI Agent Localization Biases through Logit Sharpness (2025.findings-emnlp)

Challenge:	Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts.
Approach:	They propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) which jointly learns how to understand language and correct spelling errors.
Outcome:	The proposed model outperforms state-of-the-art methods on widely used benchmarks and achieves superior performance against existing models.

Copied to clipboard

Xingjian Tao, Yiwei Wang, Yujun Cai, Zhicheng Yang, Jing Tang

Challenge:	Multimodal large language models often exhibit hallucinations that compromise reliability . despite promising performance, these models often display systematic localization errors .
Approach:	They propose a framework that categorizes model predictions into four distinct types . they propose metric that evaluates alignment between semantic continuity and logits distribution .
Outcome:	The proposed framework categorizes model predictions into four different types . it reveals nuanced failure modes beyond traditional accuracy metrics .

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Copied to clipboard

Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement (2025.naacl-long)

Challenge:	Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach:	They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome:	The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)

Copied to clipboard

Jinhao Jiang, Jiayi Chen, Junyi Li, Ruiyang Ren, Shijie Wang, Xin Zhao, Yang Song, Tao Zhang

Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Challenge:	Existing large language models (LLMs) show exceptional problem-solving capabilities but struggle with complex reasoning tasks.
Approach:	They propose a novel RAG approach that integrates retrieved information to guide tree-based reasoning process based on LLMs.
Outcome:	The proposed approach outperforms existing methods in large language models . iteratively plans intermediate sub-queries and answers based on the LLM itself .

Copied to clipboard

Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding (2025.findings-acl)

Challenge:	Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach:	They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome:	The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.

Copied to clipboard

Mingxu Tao, Jie Hu, Mingchuan Yang, Yunhuai Liu, Dongyan Zhao, Yansong Feng

Psycholinguistic Tripartite Graph Network for Personality Detection (2021.acl-long)

Challenge:	Existing methods to enhance performance of Large language models are limited due to the cost of training data and privacy concerns.
Approach:	They propose a method that enhances a finetuned model with its inferior version and adopts contrastive decoding to reduce predicted errors.
Outcome:	The proposed method outperforms existing methods in data-scarcity scenarios across three domains and shows that it is more robust and robust.

Copied to clipboard

Tao Yang, Feifan Yang, Haolan Ouyang, Xiaojun Quan

Improving Chinese Grammatical Error Detection via Data augmentation by Conditional Error Generation (2022.findings-acl)

Challenge:	Existing work on personality detection from online posts adopts multifarious deep neural networks to represent the posts and builds predictive models in a data-driven manner without the exploitation of psycholinguistic knowledge.
Approach:	They propose a psycholinguistic knowledge-based tripartite graph network, TrigNet, which consists of a tripartitic graph network and a BERT-based graph initializer.
Outcome:	The proposed graph network outperforms the existing state-of-the-art model by 3.47 and 2.10 points in average F1 on two datasets.

Copied to clipboard

Tianchi Yue, Shulin Liu, Huihui Cai, Tao Yang, Shengkang Song, TingHao Yu

Low-Resource NLP

Challenge:	Chinese Grammatical Error Detection is a non-automatic method to detect grammatical errors in texts.
Approach:	They propose a Conditional Non-Autoregressive Error Generation model for Chinese grammatical errors that uses a masking and prediction method to generate a context-dependent error.
Outcome:	The proposed method achieves better performance than all compared data augmentation methods on the CGED-2018 and CGAD-2020 benchmarks.

Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains (2025.findings-emnlp)

Copied to clipboard

Yang Wu, Raha Moraffah, Rujing Yao, Jinhong Yu, Zhimin Tao, Xiaozhong Liu

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have demonstrated an impressive level of general knowledge, but often struggle in highly specialized domains due to the lack of expert knowledge.
Approach:	They propose a framework to actively engage domain experts within a fixed budget to enhance domain-specific LLMs.
Outcome:	The proposed framework improves LLMs in highly specialized domains while adhering to budget constraints.

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)

Copied to clipboard

Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

AudioVSR: Enhancing Video Speech Recognition with Audio Data (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks.
Approach:	They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes.
Outcome:	The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset.

Copied to clipboard

Xiaoda Yang, Xize Cheng, Jiaqi Duan, Hongshun Qiu, Minjie Hong, Minghui Fang, Shengpeng Ji, Jialong Zuo, Zhiqing Hong, Zhimeng Zhang, Tao Jin

FedCoT: Federated Chain-of-Thought Distillation for Large Language Models (2025.findings-emnlp)

Challenge:	Recent work has shown poor performance with non-Indo-European languages . previous work primarily utilizes video information to build VSR models .
Approach:	They propose a generative model for data inflation that integrates synthetic data with authentic visual data to enhance the VSR model.
Outcome:	The proposed model improves on the audio-visual alignment problem in audio-video tasks.

Copied to clipboard

Tao Fan, Weijing Chen, Yan Kang, Guoqiang Ma, Hanlin Gu, Yuanfeng Song, Lixin Fan, Qiang Yang

Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have emerged as a transformative force in artificial intelligence, demonstrating exceptional proficiency across various tasks.
Approach:	They propose a federated framework for the Chain-of-Thought distillation of knowledge from LLMs to SLMs, while adhering to privacy requirements.
Outcome:	The proposed framework ensures secure knowledge transfer from an LLM on a high-powered server to an SLM on resource-constrained client while adhering to privacy requirements.

Copied to clipboard

Zhuofan Wen, Zheng Lian, Shun Chen, Hailiang Yao, Longjiang Yang, Bin Liu, Jianhua Tao

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)

Challenge:	Existing methods to assess human emotion are limited by the subjective nature of emotion perception, limiting the robustness of existing models.
Approach:	They propose a plug-and-play module that enhances MLLMs’ ability to tackle compound and context-rich emotion tasks.
Outcome:	The proposed framework improves MLLMs' ability to tackle compound and context-rich emotion tasks and the Compound Emotion QA dataset shows it performs well across both benchmarks and evaluation frameworks.

Copied to clipboard

Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui

Programming Languages in NLP

Challenge:	coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored .
Approach:	They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding.
Outcome:	The proposed benchmark aims to accelerate the development of more scaffold-aware agents.

AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Copied to clipboard

Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang

SmartSpanNER: Making SpanNER Robust in Low Resource Scenarios (2023.findings-emnlp)

Challenge:	Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach:	They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome:	The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.

Copied to clipboard

Min Zhang, Xiaosong Qiao, Yanqing Zhao, Shimin Tao, Hao Yang

Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Challenge:	Named Entity Recognition (NER) is one of the most fundamental tasks in natural language processing.
Approach:	They propose a method which introduces a Named Entity Head (NEH) prediction task to SpanNER and performs multi-task learning together with task of span classification.
Outcome:	The proposed method improves the robustness of SpanNER in low resource scenarios on the CoNLL03, Few-NERD, GENIA and ACE05 benchmark datasets.

Copied to clipboard

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)

Challenge:	MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach:	They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome:	The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).

Copied to clipboard

Junxiao Yang, Haoran Liu, Jinzhe Tu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Jiaqi Weng, Jialing Tao, Hui Xue, Hongning Wang, Han Qiu, Minlie Huang

Challenge:	Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages.
Approach:	They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks.
Outcome:	The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B).

Private Language Models via Truncated Laplacian Mechanism (2024.emnlp-main)

Copied to clipboard

Tianhao Huang, Tao Yang, Ivan Habernal, Lijie Hu, Di Wang

SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning (2026.acl-long)

Challenge:	Existing methods for word embedding are prone to privacy leakage, resulting in weaker relaxations of DP that are inferior to the canonical DP in terms of privacy strength.
Approach:	They propose a method for private word embedding that uses a non-trivial extension of the truncated Laplacian mechanism and propose to test its effectiveness.
Outcome:	The proposed method has lower variance compared to the previous methods.

Copied to clipboard

Jinyang Wu, Shuo Yang, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao

Challenge:	Existing methods for training large language models waste computation budget on trivial steps while failing to guarantee sample quality.
Approach:	They propose a framework that selectively branches at critical decision states for resource-efficient exploration.
Outcome:	The proposed framework activates adaptive branching exploration at critical decision states to probe promising trajectories, thereby achieving precise resource allocation that prioritizes sampling quality over blind coverage.

PLACES: Prompting Language Models for Social Conversation Synthesis (2023.findings-eacl)

Copied to clipboard

Maximillian Chen, Alexandros Papangelis, Chenyang Tao, Seokhwan Kim, Andy Rosenbaum, Yang Liu, Zhou Yu, Dilek Hakkani-Tur

MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation (2023.acl-long)

Challenge:	Currently, collecting high quality conversational data is expensive and infeasible for many applications . a promising direction is to generate synthetic dialogues by prompting large language models .
Approach:	They propose to use expert-written conversations as in-context examples to generate synthetic dialogues by prompting large language models.
Outcome:	The proposed approach is generalizable to multi-party conversations, compared to human-collected conversations.

Copied to clipboard

Jiazhan Feng, Qingfeng Sun, Can Xu, Pu Zhao, Yaming Yang, Chongyang Tao, Dongyan Zhao, Qingwei Lin

Natural Language Interfaces

Challenge:	MMDialog is a dataset of 1.08 million real-world dialogues with 1.53 million unique images across 4,184 topics.
Approach:	They propose to use a curated set of 1.08 million dialogues with 1.53 million unique images to generalize the open domain.
Outcome:	The proposed system can predict responses to multi-modal content with state-of-the-art techniques and measure their performance.

CRASpell: A Contextual Typo Robust Approach to Improve Chinese Spelling Correction (2022.findings-acl)

Copied to clipboard

Shulin Liu, Shengkang Song, Tianchi Yue, Tao Yang, Huihui Cai, TingHao Yu, Shengli Sun

The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights (2025.acl-long)

Challenge:	Recent research on Chinese spelling correction methods has poor performance on multi-typo texts.
Approach:	They propose to use Bert-based Chinese spelling correction models to overcome these limitations by constructing a noisy context for each training sample and a copy mechanism to encourage the model to choose the input character when the miscorrected and input character are both valid.
Outcome:	The proposed model outperforms state-of-the-art models on widely used benchmarks and achieves a remarkable gain.

Copied to clipboard

Yufang Liu, Yao Du, Tao Ji, Jianing Wang, Yang Liu, Yuanbin Wu, Aimin Zhou, Mengdi Zhang, Xunliang Cai

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention (2026.acl-long)

Challenge:	Existing models that leverage visual information do not improve math reasoning performance . authors suggest that visual information is important for multimodal reasoning .
Approach:	They propose a dataset to require image reliance for problem-solving and challenge models with similar, yet distinct, images that change the correct answer.
Outcome:	The proposed model performance is unaffected by changes to or removal of images in the dataset.

Copied to clipboard

Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, Xin Tao, Ying-Cong Chen

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have focused on test-time scaling to improve reasoning quality but at the cost of efficiency.
Approach:	They propose a training-free framework that enhances reasoning accuracy and stability with minimal overhead.
Outcome:	The proposed framework yields consistent gains across general, coding, and STEM tasks while remaining highly efficient.

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task (D18-1)

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Tao Yu, Michihiro Yasunaga, Kai Yang, Rui Zhang, Dongxu Wang, Zifan Li, Dragomir Radev

Clustering-Aware Negative Sampling for Unsupervised Sentence Representation (2023.findings-acl)

Challenge:	Existing studies in text-to-SQL do not require generating complex SQL queries with multiple clauses or sub-queries.
Approach:	They propose a syntax tree network to address the complex text-to-SQL generation task.
Outcome:	The proposed model outperforms the current state-of-the-art model by 9.5% on a large text-to-SQL corpus.

Copied to clipboard

Jinghao Deng, Fanqi Wan, Tao Yang, Xiaojun Quan, Rui Wang

Representation Learning with Ordered Relation Paths for Knowledge Graph Completion (D19-1)

Challenge:	Using clustering-aware learning, in-batch negatives are often ignored in sentence representation learning.
Approach:	They propose a method that integrates cluster information into contrastive learning for unsupervised sentence representation learning.
Outcome:	The proposed method compares favorably with baselines on semantic textual similarity tasks.

Copied to clipboard

Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yang Song, Tao Zhang

Threshold-driven Pruning with Segmented Maximum Term Weights for Approximate Cluster-based Sparse Retrieval (2024.emnlp-main)

Challenge:	Existing knowledge graphs are incomplete and lack the order of relations in paths.
Approach:	They propose a method which takes relation paths into account but ignores order of relations in paths which is important for reasoning.
Outcome:	The proposed method performs better than state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Yifan Qiao, Parker Carlson, Shanxiu He, Yingrui Yang, Tao Yang

Text Clustering

Challenge:	Using rank score thresholding, sparse retrieval skips the index at cluster and document levels.
Approach:	They propose a pruning control scheme with a probabilistic guarantee on rank-safeness competitiveness.
Outcome:	The proposed pruning control scheme improves accuracy and safeness while delivering low latency on single-threaded CPU.

Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems (2023.emnlp-main)

Copied to clipboard

Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang, Xiaojun Quan, Qifan Wang

Natural Language Interfaces

Challenge:	Current approaches to task-oriented dialogue systems integrate knowledge retrieval and response generation, which poses scalability challenges when dealing with extensive knowledge bases.
Approach:	They propose a retriever-generator architecture that harnesses a retrieval and a generator to generate system responses by using feedback from the generator as pseudo-labels.
Outcome:	The proposed architecture shows superior performance on three benchmark datasets.

Type Enhanced BERT for Correcting NER Errors (2023.findings-acl)

Copied to clipboard

Kuai Li, Chen Chen, Tao Yang, Tianming Du, Peijie Yu, Dong Du, Feng Zhang

Learning to Answer Psychological Questionnaire for Personality Detection (2021.findings-emnlp)

Challenge:	Named entity recognition (NER) is the task of identifying spans that belong to particular categories, such as person, location, organization, etc.
Approach:	They propose a method that integrates named entity’s type information into BERT by an adapter layer and integrates it into a gazetteer.
Outcome:	The proposed method outperforms baselines in multiple corpus.

Copied to clipboard

Feifan Yang, Tao Yang, Xiaojun Quan, Qinliang Su

Representation Learning

Challenge:	Existing text-based personality detection research relies on data-driven approaches to implicitly capture personality cues in online posts lacking the guidance of psychological knowledge.
Approach:	They propose a model to capture key information in texts and a questionnaire to help the user to make a personality assessment.
Outcome:	The proposed model captures key information in texts and a questionnaire and can be used to improve personality prediction.

UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)

Copied to clipboard

Jing Xiong, Jianghan Shen, Fanghua Ye, Chaofan Tao, Zhongwei Wan, Jianqiao Lu, Xun Wu, Chuanyang Zheng, Zhijiang Guo, Min Yang, Lingpeng Kong, Ngai Wong

From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation (2026.findings-acl)

Challenge:	Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands.
Approach:	They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content.
Outcome:	The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup.

Copied to clipboard

Peng Chuang, Wei Zhang, Renshuai Tao, Xinhao Zhang, Jian Yang

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)

Challenge:	Text-based web agents offer computational efficiency for autonomous web navigation, yet they lack discrimination capabilities to reject plausible but incorrect elements in densely populated pages.
Approach:	They propose a model that uses a text-based web agent to learn to discriminate against incorrect elements in densely populated HTML and a training curriculum to synthesize diverse cross-domain tasks with strict verification.
Outcome:	Empirical evaluation shows that the model performs better than open-source models with 58.7% step success rate.

Copied to clipboard

Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Challenge:	Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.
Approach:	They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls.
Outcome:	The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents.

Copied to clipboard

Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation (2025.findings-emnlp)

Challenge:	Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach:	They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome:	The proposed framework improves instruction following performance without compromising general performance.

Copied to clipboard

Chenghao Yang, Yinbo Luo, Zhoufutu Wen, Qi Chu, Tao Gong, Longxiang Liu, Kaiyuan Zhang, Jianpeng Jiao, Ge Zhang, Wenhao Huang, Nenghai Yu

Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have been widely adopted in real-world dialogue applications, but their robustness is criticized all along.
Approach:	They propose to use play-by-play text commentary to build a multi-turn athletic real-world scenario dialogue benchmark to evaluate three critical aspects of multi-turned conversations: ultra multi- turn, interactive multi-twist, and cross-turn tasks.
Outcome:	The proposed benchmarks outperform open-source LLMs on three critical aspects of multi-turn conversations: ultra multi-turned, interactive multi- turn, and cross-turn tasks.

Copied to clipboard

Yuan Ge, Yilun Liu, Chi Hu, Weibin Meng, Shimin Tao, Xiaofeng Zhao, Mahong Xia, Zhang Li, Boxing Chen, Hao Yang, Bei Li, Tong Xiao, JingBo Zhu

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition (2025.coling-main)

Challenge:	Existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset.
Approach:	They propose an industrial-friendly, expert-aligned and diversity-preserved instruction data selection method: Clustering and Ranking (CaR).
Outcome:	The proposed method outperforms Alpaca's existing methods by 32.1% in GPT-4 evaluations.

Copied to clipboard

Yuming Yang, Wantong Zhao, Caishuang Huang, Junjie Ye, Xiao Wang, Huiyuan Zheng, Yang Nan, Yuran Wang, Xueying Xu, Kaixin Huang, Yunke Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships (2021.findings-emnlp)

Challenge:	Current Large Language Models struggle with complex entity taxonomies in open domains and lack NER capabilities.
Approach:	They propose a dataset to guide LLMs' generalization in Open NER under a universal entity taxonomy.
Outcome:	The proposed model outperforms GPT-4 in 3 out-of-domain benchmarks across 15 datasets and 6 languages.

Copied to clipboard

Lei He, Suncong Zheng, Tao Yang, Feng Zhang

Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric (2025.acl-long)

Challenge:	Existing knowledge-enhanced pretrained language models focus on entity information and ignore fine-grained relationships between entities.
Approach:	They propose to incorporate KG into the language learning process to obtain a KG-enhanced pretrained Language Model.
Outcome:	The proposed model improves on several knowledge-driven tasks, such as entity typing and relation classification, compared with the state-of-the-art knowledge-enhanced PLMs.

Copied to clipboard

Yuming Yang, Yang Nan, Junjie Ye, Shihan Dou, Xiao Wang, Shuo Li, Huijie Lv, Tao Gui, Qi Zhang, Xuanjing Huang

Guess Me if You Can: Acronym Disambiguation for Enterprises (P18-1)

Challenge:	Existing studies have explored various diversity-aware data selection methods to construct high-quality datasets and enhance model performance.
Approach:	They propose to use data diversity to measure instruction tuning of large language models.
Outcome:	The proposed diversity metric outperforms existing methods on simulated and real-world data and shows that it captures diversity variations and achieves a 0.97 correlation with instruction tuning.

Copied to clipboard

Yang Li, Bo Zhao, Ariel Fuxman, Fangbo Tao

Knowledge Representation

Challenge:	Acronyms are abbreviations formed from the initial components of words or phrases . acronyms can be difficult to understand for people who are not familiar with the subject matter .
Approach:	They propose a framework to automatically resolve the true meanings of acronyms in a given context . they use the enterprise corpus as input and a high-quality acronym disambiguation system as output .
Outcome:	The proposed framework can be deployed to any enterprise to support acronym disambiguation.

Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference (2022.findings-acl)

Copied to clipboard

Yuxia Wang, Minghan Wang, Yimeng Chen, Shimin Tao, Jiaxin Guo, Chang Su, Min Zhang, Hao Yang

Improved Pseudo Data for Machine Translation Quality Estimation with Constrained Beam Search (2023.emnlp-main)

Challenge:	Previously, it's common to disregard it as noise or as a sign of poor-quality data, as their annotations are heavily based on personal experience and opinions.
Approach:	They propose to capture the human disagreement distribution from the perspective of model calibration.
Outcome:	The proposed model can achieve competitive performance when well-calibrated, on divergence scores between predictive probability and the true human opinion distribution, and the accuracy.

Copied to clipboard

Xiang Geng, Yu Zhang, Zhejian Lai, Shuaijie She, Wei Zou, Shimin Tao, Hao Yang, Jiajun Chen, Shujian Huang

PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection (2023.findings-emnlp)

Challenge:	evaluating the quality of machine translation outputs becomes increasingly essential with the rapid development of machine language (MT).
Approach:	They propose to generate pseudo data using the MT model with constrained beam search (CBSQE) they propose to preserve the reference parts with high MT probabilities as correct translations .
Outcome:	The proposed model outperforms strong baselines in both supervised and unsupervised settings.

Copied to clipboard

Tao Yang, Tianyuan Shi, Fanqi Wan, Xiaojun Quan, Qifan Wang, Bingzhe Wu, Jiaxiang Wu

XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser (2025.coling-main)

Challenge:	Recent advances in large language models (LLMs) have demonstrated remarkable zero-shot performance across various NLP tasks.
Approach:	They propose a method which mimics the way individuals complete psychological questionnaires in a multi-turn dialogue manner and prompts an LLM to rate individual items at each turn.
Outcome:	The proposed method improves the performance and robustness of the standard GPT-3.5 personality detection task on two benchmark datasets.

Copied to clipboard

Xianfu Cheng, Hang Zhang, Jian Yang, Xiang Li, Weixiao Zhou, Fei Liu, Kui Wu, Xiangyuan Guan, Tao Sun, Xianjie Wu, Tongliang Li, Zhoujun Li

Multilinguality

Challenge:	Document AI parsing semi-structured image form is a key information extraction task.
Approach:	They propose a multimodal and multilingual semi-structured FORM PARSER which integrates SER and relation extraction into a unified framework.
Outcome:	The proposed framework achieves up to 1.79% improvement on RE tasks in multilingual and zero-shot settings.

InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model (2024.findings-acl)

Copied to clipboard

Haogeng Liu, Quanzeng You, Yiqi Wang, Xiaotian Han, Bohan Zhai, Yongfei Liu, Wentao Chen, Yiren Jian, Yunzhe Tao, Jianbo Yuan, Ran He, Hongxia Yang

OEE-CFC: A Dataset for Open Event Extraction from Chinese Financial Commentary (2024.findings-emnlp)

Challenge:	InfiMM is a multimodal large language model that adapts to complex vision-language tasks.
Approach:	They present a Multimodal Large Language Model that adapts to intricate vision-language tasks using large-scale training data and comprehensive training strategies.
Outcome:	Empirical evaluations across a variety of benchmarks underscore InfiMM’s remarkable capability in multimodal understanding.

Copied to clipboard

Qizhi Wan, Changxuan Wan, Rong Hu, Dexi Liu, Xu Wenwu, Kang Xu, Zou Meihua, Liu Tao, Jie Yang, Zhenwei Xiong

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Existing corpora with unconventional entities serving as event arguments lack rich multi-events and shared arguments.
Approach:	They develop an open event template that includes 21 event argument roles and an open corpus supporting open event extraction.
Outcome:	The proposed corpus includes 17,469 events, 44,221 arguments, 3,644 complex arguments, and 5,898 shared arguments.

Copied to clipboard

Peiru Yang, Haoran Zheng, Tong Ju, Shiting Wang, Wanchun Ni, Jiajun Liu, Shangguang Wang, Yongfeng Huang, Tao Qi

An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation (2023.acl-long)

Challenge:	Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability .
Approach:	They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval .
Outcome:	The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets.

Copied to clipboard

Xuancheng Huang, Zijun Liu, Peng Li, Tao Li, Maosong Sun, Yang Liu

Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction (2024.findings-acl)

Challenge:	Multi-aspect controllable text generation has attracted increasing attention . but the mutual interference of multiple prefixes limits its extensibility to training-time unseen combinations.
Approach:	They propose to use trainable gates to normalize the intervention of prefixes to restrain the interference.
Outcome:	The proposed approach outperforms baselines on constraint accuracy, text quality, and extensibility.

Copied to clipboard

Dingyao Yu, Yang An, Wei Ye, Xiongfeng Xiao, Shaoguang Mao, Tao Ge, Shikun Zhang

MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Challenge:	Chinese Spelling Correction (CSC) lacks large-scale high-quality corpora due to labor-intensive labeling of spelling errors in real-life writing or typing scenarios.
Approach:	They propose to use OCR/ASR-based generation to refine Chinese Spelling Correction models on random replacement-based corpora and filter them based on prediction confidence.
Outcome:	The proposed model outperforms existing models on three widely-used benchmarks while significantly alleviating over-correction.

Copied to clipboard

Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li

HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation (2021.acl-long)

Challenge:	Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach:	They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome:	The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.

Copied to clipboard

Tao Qi, Fangzhao Wu, Chuhan Wu, Peiru Yang, Yang Yu, Xing Xie, Yongfeng Huang

Representation Learning

Challenge:	Existing news recommendation methods learn a single user embedding for each user from their previous behaviors to represent their overall interest. Existing methods only learn 'one' embeddable representation vectors to model user interest.
Approach:	They propose a news recommendation method with hierarchical user interest modeling that captures user interest in news rather than a single user embedding.
Outcome:	The proposed method can better capture multi-grained user interest in news.

Harder Task Needs More Experts: Dynamic Routing in MoE Models (2024.acl-long)

Copied to clipboard

Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng

Robust and Scalable Model Editing for Large Language Models (2024.lrec-main)

Challenge:	Unlike existing MoE approaches that rely on fixed TopK Routing, our dynamic expert selection framework dynamically allocates experts based on the confidence level in expert selection for each input.
Approach:	They propose a dynamic expert selection framework that dynamically allocates experts based on the confidence level in expert selection for each input.
Outcome:	The proposed method achieves an average improvement of 0.7% with less than 90% activated parameters and outperforms dense models in QA and machine translation tasks.

Copied to clipboard

Yingfa Chen, Zhengyan Zhang, Xu Han, Chaojun Xiao, Zhiyuan Liu, Chen Chen, Kuai Li, Tao Yang, Maosong Sun

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (D18-1)

Challenge:	Existing methods that ignore contextual knowledge fail to reliably fall back to parametric knowledge when presented with irrelevant context.
Approach:	They propose to use contextual knowledge to update and correct LLMs' knowledge by in-context editing instead of retraining.
Outcome:	The proposed method outperforms current state-of-the-art methods by a large margin on a dataset that contains irrelevant questions.

Copied to clipboard

Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, Dragomir Radev

Programming Languages in NLP

Challenge:	Existing datasets for semantic parsing are too small in terms of number of programs for training modern data-intensive models.
Approach:	They propose a large-scale complex and cross-domain semantic parsing task for a database . they use a dataset with 10,181 questions and 5,693 unique complex SQL queries .
Outcome:	The proposed task is different from previous tasks because it uses the same database and program . the best model achieves only 9.7% exact matching accuracy on a database split setting.

Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration (2023.emnlp-main)

Copied to clipboard

Fanqi Wan, Xinting Huang, Tao Yang, Xiaojun Quan, Wei Bi, Shuming Shi

M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models (2025.findings-emnlp)

Challenge:	Existing data for instruction-tuning are inadequate for a wide range of tasks, limiting the scope for nuanced comprehension and interactions within these domains.
Approach:	They propose to use Large Language Models to explore a multitude of variations or possibilities to improve instruction-tuning data by active exploration.
Outcome:	The proposed approach improves domain-specific instruction coverage and shows significant improvements over baselines.

Copied to clipboard

Jiaxin Guo, Daimeng Wei, Yuanchang Luo, Hengchao Shang, Zongyao Li, Jinlong Yang, Zhanglin Wu, Zhiqiang Rao, Shimin Tao, Hao Yang

PACHAT: Persona-Aware Speech Assistant for Multi-party Dialogue (2025.emnlp-main)

Challenge:	a new ensemble decoding approach enhances the performance of Large Language Models.
Approach:	They propose a multi-prompt ensemble decoding approach to enhance LLM performance . they submit n variations of prompts with X to LLMs in batch mode to decode and derive probability distributions .
Outcome:	The proposed method improves pass@k rates, LENS metrics and BLEU scores on diverse NLP tasks.

Copied to clipboard

Dongjie Fu, Xize Cheng, Linjun Li, Xiaoda Yang, Lujia Yang, Tao Jin

TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning (2026.findings-acl)

Challenge:	Extensive research on spoken dialogue systems has advanced the development of intelligent voice assistants, but integration of role information within speech remains an underexplored area.
Approach:	They propose a language-based spoken dialogue system that integrates role information within speech to generate contextually appropriate responses.
Outcome:	The proposed architecture achieves speaker-specific responses, character understanding, and the generation of targeted replies in multi-party dialogue scenarios, surpassing existing spoken dialogue systems.

Copied to clipboard

Jinyang Wu, Chonghua Liao, Mingkuan Feng, Shuai Zhang, Zhengqi Wen, Haoran Luo, Ling Yang, Huazhe Xu, Jianhua Tao

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment (2026.acl-long)

Challenge:	Existing RL methods rely on unstructured self-sampling to fit scalar rewards, resulting in inefficient rollouts.
Approach:	They propose a structured template-guided RL framework that augments policy optimization with explicit template guidance.
Outcome:	Experiments show that TemplateRL outperforms GRPO and GRPI by 99% on AIME and 41% on AMC with superior stability on weak models and remarkable cross-domain generalization.

Copied to clipboard

Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin Sun

Robustness in NLP

Challenge:	Existing approaches to safety alignment of large language models rely on costly manual annotations or human review.
Approach:	They propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative collaboration among three roles with near-zero manual annotation.
Outcome:	The proposed framework achieves 20%–50% improvement in adversarial effectiveness while preserving high output diversity while achieving 10%–30% gains in safety performance without degrading general reasoning capability.

Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation (2022.naacl-main)

Copied to clipboard

Guangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang, Junwei Bao, Zhen Li, Xiaodong He, Shuguang Cui, Zhiting Hu

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)

Challenge:	Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss.
Approach:	They propose an Edit-Invariant Sequence Loss method which computes the matching loss of a target sequence with all n-grams in the generated sequence.
Outcome:	The proposed method outperforms the common CE loss and strong baselines on a wide range of tasks.

Copied to clipboard

Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun

Modeling Consistency Preference via Lexical Chains for Document-level Neural Machine Translation (2022.emnlp-main)

Challenge:	Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks.
Approach:	They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies.
Outcome:	The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%.

Copied to clipboard

Xinglin Lyu, Junhui Li, Shimin Tao, Hao Yang, Ying Qin, Min Zhang

Part Represents Whole: Improving the Evaluation of Machine Translation System Using Entropy Enhanced Metrics (2022.findings-aacl)

Challenge:	Experimental results show that consistency preference for lexical chains reduces lexical translation inconsistency . Lexical translation consistency is a common discourse phenomenon .
Approach:	They propose a consistency-aware model which captures consistency context . they then define consistency-tailored latent variables which guide translation of corresponding sentences .
Outcome:	The proposed model significantly improves translation performance in ChineseEnglish and FrenchEnglish translation tasks.

Copied to clipboard

Yilun Liu, Shimin Tao, Chang Su, Min Zhang, Yanqing Zhao, Hao Yang

V-GameGym: Visual Game Generation for Code Large Language Models (2026.findings-acl)

Challenge:	Existing machine translation metrics have poor correlations with human assessments . entropy-based evaluations are often limited to a limited number of samples .
Approach:	They propose a fast and unsupervised approach to enhance machine translation metrics using entropy by introducing sentence-level difficulty.
Outcome:	The proposed method outperforms existing metrics on five sub-tracks in the WMT19 Metrics shared tasks.

Copied to clipboard

Wei Zhang, Jian Yang, Renshuai Tao, Linzheng Chai, Shuyue Guo, Jiajun Wu, Xiaoming Chen, Ganqu Cui, Ning Ding, Xander Xu, HU Wei, Bowen Zhou

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

Challenge:	Existing code-related benchmarks focus on single modality rather than visual game development.
Approach:	They propose a multimodal benchmark for evaluating code large language models in visual game generation that integrates a clustering-based curation methodology and a pipeline for visual code synthesis.
Outcome:	The proposed framework assesses code generation and visual game generation using a sandbox environment.

Copied to clipboard

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

Attacking Vision-Language Computer Agents via Pop-ups (2025.acl-long)

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

Yanzhe Zhang, Tao Yu, Diyi Yang

Robustness in NLP

Challenge:	Existing tools for analyzing and testing VLMs are lacking in understanding what types of attacks are possible and what types are effective.
Approach:	They propose to integrate pop-ups into existing agent testing environments to attack VLM agents by ignoring them.
Outcome:	The proposed attack success rate is 86% and decreases by 47% when integrating pop-ups into existing agent testing environments.

Scattered Hypothesis Generation for Open-Ended Event Forecasting (2026.findings-acl)

Copied to clipboard

He Chang, Zhulin Tao, Lifang Yang, Xianglin Huang, Yunshan Ma

Challenge:	Existing methods for event forecasting focus on the most probable outcomes, neglecting the intrinsic uncertainty of real-world events.
Approach:	They propose a reinforcement learning framework that optimizes inclusiveness and diversity of the hypothesis by integrating validity-gated score into the overall objective.
Outcome:	The proposed framework outperforms baselines on two real-world benchmark datasets.

Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)

Copied to clipboard

Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Yang Liu, Hang Li

Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision (2022.findings-naacl)

Challenge:	Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values.
Approach:	They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent.
Outcome:	The proposed method improves on a two-agent game with an adversarial agent and a defensive agent.

Copied to clipboard

Yang Li, Guodong Long, Tao Shen, Jing Jiang

Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models (2026.acl-long)

Challenge:	Distant supervision uses triple facts to label corpus for relation extraction, leading to wrong labeling and long-tail problems.
Approach:	They propose a model to enrich distantly-supervised sentences with entity types by injecting context-free and -related backgrounds into sentences to alleviate sentence-level wrong labeling.
Outcome:	The proposed model achieves state-of-the-art on benchmarks and in overall and long-tail performance.

Copied to clipboard

Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zhengqi Wen, Chonghua Liao, Ling Yang, Haoran Luo, Zheng Lian, Jianhua Tao

Revisiting Model Interpolation for Efficient Reasoning (2026.acl-long)

Challenge:	In-context learning (ICL) struggles with complex reasoning due to superficial, example-level implicit imitation.
Approach:	They propose an automated method that shifts from surface-level examples to more guidance-oriented thought patterns.
Outcome:	The proposed method achieves 80.6% accuracy on MATH and 62.5% on AMC, surpassing GPT-4o’s 77.2% and 57.5% accuracy.

Copied to clipboard

Taiqiang Wu, Runming Yang, Tao Liu, Jiahao Wang, Ngai Wong

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization (2026.acl-long)

Challenge:	Existing models that interpolate weights of two specialized models can be abused for efficient reasoning.
Approach:	They propose to merge two specialized models and create a model that combines efficiency and efficiency.
Outcome:	The proposed method outperforms existing models on efficiency and effectiveness.

Copied to clipboard

Junzhe Wang, Zhiheng Xi, Yajie Yang, Hao Luo, Shihan Dou, Tao Gui, Qi Zhang

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention (2020.coling-main)

Challenge:	Existing approaches to training large language models suffer from unstable value estimation, whereas outcome supervision struggles with credit assignment due to sparse, trajectory-level rewards.
Approach:	They propose a framework that integrates process supervision into group relative policy optimization.
Outcome:	The proposed framework outperforms standard GRPO on knowledge-intensive benchmarks by 5.0% and 6.3% on Qwen3-1.7B.

Copied to clipboard

Yang Li, Tao Shen, Guodong Long, Jing Jiang, Tianyi Zhou, Chengqi Zhang

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment (2026.acl-long)

Challenge:	Existing approaches to handle wrong labeling and long-tail relations are labor-intensive and scarce training data.
Approach:	They propose a neural network to handle wrong labeling and long-tail relations by collaborating relation-augmented attention.
Outcome:	The proposed neural network improves the state-of-the-art on the NYT dataset .

Copied to clipboard

Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao, Haijun Lv, Jian Tong, Yunhua Zhou, Yicheng Zou, Qipeng Guo, Tao Gui, Qi Zhang, Xuanjing Huang

DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators (2024.emnlp-main)

Challenge:	Existing methods assess suitability primarily through student likelihood, favoring trajectories that align closely with the student model’s current behavior but overlooking more informative ones.
Approach:	They propose a Rank–Surprisal Ratio metric that captures both alignment and informativeness to assess the suitability of a reasoning trajectory.
Outcome:	The proposed metric captures both alignment and informativeness to assess the suitability of a reasoning trajectory.

Copied to clipboard

Xinglin Lyu, Junhui Li, Yanqing Zhao, Min Zhang, Daimeng Wei, Shimin Tao, Hao Yang, Min Zhang

Parameter-efficient Continual Learning Framework in Industrial Real-time Text Classification System (2022.naacl-industry)

Challenge:	Concatenating large language models are adapted to context-aware neural machine translation in a concatenated way . a recent paradigm shift has been witnessed in discourse-related challenges such as zero pronoun translation .
Approach:	They propose an alternative adaptation approach to make large language models discriminately model and utilize inter- and intra-sentence contexts.
Outcome:	The proposed approach outperforms concatenation mode and improves performance in discourse modeling.

Copied to clipboard

Tao Zhu, Zhe Zhao, Weijie Liu, Jiachi Liu, Yiren Chen, Weiquan Mao, Haoyan Liu, Kunbo Ding, Yudong Li, Xuefeng Yang

FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models (2025.coling-main)

Challenge:	Existing continual learning methods use data replay, parameter isolation and regularization to mitigate catastrophic forgetting.
Approach:	They propose a parameter-efficient continual learning framework that updates parameters offline and then trains using an online regularization method.
Outcome:	The proposed framework reduces catastrophic forgetting and saves the model with the changed parameters instead of all parameters.

Copied to clipboard

Tao Fan, Guoqiang Ma, Yan Kang, Hanlin Gu, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang

Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models (2025.coling-main)

Challenge:	Recent research in large language models (LLMs) has focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLM to small language models at downstream clients.
Approach:	They propose a parameter-efficient federated mutual knowledge transfer framework for large and small language models that allows for token alignment and selective knowledge transfer between client-side LLMs and a server-side SLM.
Outcome:	The proposed framework enhances the performance of both LLMs and SLMs with clients' unique domain insights while preserving the server's LLM and client's unique domain insight.

Copied to clipboard

Taiqiang Wu, Chaofan Tao, Jiahao Wang, Runming Yang, Zhe Zhao, Ngai Wong

Lexical Translation Inconsistency-Aware Document-Level Translation Repair (2023.findings-acl)

Challenge:	Large Language Models (LLMs) have been used in Knowledge Distillation (KD) to compress large models.
Approach:	They propose a Kullback-Leiber divergence method which adaptively allocates weights to combine RKL and FKL to reduce the size of Large Language Models (LLMs).
Outcome:	The proposed method outperforms baselines and improves diversity and quality of generated responses.

Copied to clipboard

Zhen Zhang, Junhui Li, Shimin Tao, Hao Yang

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization (2021.naacl-main)

Challenge:	Experimental results show document-level translation repair improves translation consistency but still suffers from lexical translation inconsistency due to the lack of inter-sentence context.
Approach:	They propose a document-level translation repair model to model translation inconsistency via automatic post-editing.
Outcome:	The proposed model improves translation quality and lexical consistency on document-level translation datasets.

Copied to clipboard

Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir Radev

AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)

Challenge:	Existing work on meeting summarization tasks is limited to short summaries that cover all the content of a meeting.
Approach:	They propose a query-based multi-domain meeting summarization task that generates a single short summary of meetings based on a transcript.
Outcome:	The proposed task is based on 1,808 query-summary pairs over 232 meetings in multiple domains.

Copied to clipboard

Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, null Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian

Challenge:	Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs).
Approach:	They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say .
Outcome:	The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels.

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)

Copied to clipboard

Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou

FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion (2026.acl-long)

Challenge:	Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective.
Approach:	They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types.
Outcome:	The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment.

Copied to clipboard

Tao Fan, Guoqiang Ma, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang

Powering Verifiable Learning via Automated Evolutionary Data Synthesis (2026.acl-long)

Challenge:	Existing methods for fine-tuning Large Language Models (LLMs) suffer from a performance bottleneck . Existing approaches like Offsite-Tuning (OT) secure the LLMs IP .
Approach:	They propose a framework that replaces weak adapters with a unified, powerful Proxy Small Language Model (SLM) they propose 'resource-friendly' compression and 'robust optimization' to handle data heterogeneity.
Outcome:	Experiments show that FedProxy outperforms OT and centralized fine-tuning methods.

Copied to clipboard

He Du, Bowen Li, Aijun Yang, Siyang He, Qipeng Guo, Kai Chen, Dacheng Tao

Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction (2024.acl-long)

Challenge:	Existing approaches to building generalizable verifiable data are task-specific and lack a principled, universal evaluator of verifikatability.
Approach:	They propose a task-agnostic, strategy-guided, executably-checkable data synthesis framework that synthesizes problems, diverse candidate solutions and verification artifacts from a single source.
Outcome:	The proposed framework synthesizes problems, candidates, and verification artifacts from human-annotated and strategy-induced checks and iteratively discovers strategies.

Copied to clipboard

Yiren Jian, Tingkai Liu, Yunzhe Tao, Chunhui Zhang, Soroush Vosoughi, Hongxia Yang

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Challenge:	EVLGen is a framework for visual-language pre-training with high computational demands.
Approach:	They propose a streamlined framework for the pre-training of visually conditioned language generation models with high computational demands.
Outcome:	The proposed framework accelerates training of vision-language models by a factor of 5 without compromising performance.

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

Robustness in NLP

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

Collective Human Opinions in Semantic Textual Similarity (2023.tacl-1)

Copied to clipboard

Yuxia Wang, Shimin Tao, Ning Xie, Hao Yang, Timothy Baldwin, Karin Verspoor

Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints (2022.naacl-main)

Challenge:	Existing benchmarks for semantic textual similarity (STS) use averaged human ratings as gold standard.
Approach:	They propose to use a Chinese sentence-to-sentence dataset to study collective human opinions in semantic textual similarity (STS) neither a scalar nor a single Gaussian fits a set of observed judgments adequately, they argue .
Outcome:	The proposed dataset does not capture disagreements on individual instances, but rather the confidence over the aggregate dataset.

Copied to clipboard

Chun Zeng, Jiangjie Chen, Tianyi Zhuang, Rui Xu, Hao Yang, Qin Ying, Shimin Tao, Yanghua Xiao

UniCoder: Scaling Code Large Language Model via Universal Code (2024.acl-long)

Challenge:	Existing approaches to lexically constrained neural machine translation suffer from high latency.
Approach:	They propose a plug-in algorithm for non-autoregressive translation for this problem . they propose ACT to familiarize the model with the source-side context of constraints .
Outcome:	The proposed model improves over the backbone constrained NAT model in constraint preservation and translation quality, especially for rare constraints.

Copied to clipboard

Tao Sun, Linzheng Chai, Jian Yang, Yuwei Yin, Hongcheng Guo, Jiaheng Liu, Bing Wang, Liqun Yang, Zhoujun Li

Devil’s Advocate: Anticipatory Reflection for LLM Agents (2024.findings-emnlp)

Challenge:	Experimental results show that UniCoder with the universal code significantly outperforms the previous prompting methods by a large margin.
Approach:	They introduce the universal code (UniCode) as the intermediate representation of algorithm steps using conventions of programming languages.
Outcome:	The proposed model outperforms previous prompting methods by a large margin . the proposed model is based on a dataset of natural-language questions and code solutions .

Copied to clipboard

Haoyu Wang, Tao Li, Zhiwei Deng, Dan Roth, Yang Li

Low-Resource NLP

Challenge:	Introspection-driven approach equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks.
Approach:	They propose a zero-shot approach that equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks.
Outcome:	The proposed approach improves performance and efficiency by reducing the number of trials and plan revisions by 45%.

Domain Adaptation for Person-Job Fit with Transferable Deep Global Match Network (D19-1)

Copied to clipboard

Shuqing Bian, Wayne Xin Zhao, Yang Song, Tao Zhang, Ji-Rong Wen

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection (2026.findings-acl)

Challenge:	Existing methods to solve person-job fit in single-domain setting are limited by labeled data.
Approach:	They propose a deep global match network for capturing the global semantic interactions between two sentences from a job posting and a candidate resume respectively.
Outcome:	The proposed model is effective when there is not enough labeled data.

Copied to clipboard

Tao Liu, Taiqiang Wu, Runming Yang, Shaoning Sun, Junjie Wang, Yujiu Yang

Challenge:	Traditional fine-tuning ignores one-to-many nature of language, leading to overfitting . authors propose a method to fine- tune LLMs by leveraging tokens.
Approach:	They propose a method to fine-tune Large Language Models by leveraging tokens to mask low-probability tokens.
Outcome:	The proposed method outperforms baselines on general reasoning and mathematical benchmarks.

SAME: Signer-Aware Mixture-of-Experts for Test-Time Adaptation in Sign Language Translation (2026.acl-long)

Copied to clipboard

Lujia Yang, Weicai Yan, Yongbo He, Qifei Zhang, Tao Jin, Jinshan Zhang, Meng Xi, Jianwei Yin

Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance (2025.emnlp-main)

Challenge:	Existing methods for supervised fine-tuning are limited due to labeled data . existing methods require long adaptation times and batch statistics are unavailable in streaming settings .
Approach:	They propose a plug-and-play, signer-aware Mixture-of-Experts (MoE) TTA architecture for SLT . they use a combination of lightweight MoE modules and unsupervised regularizers to decouple domain shift .
Outcome:	The proposed test-time adaptation outperforms existing TTA methods in sign language translation . the proposed architecture can be used in real-world deployments without labeling .

Copied to clipboard

Yilun Liu, Minggui He, Feiyu Yao, Yuhe Ji, Shimin Tao, Jingzhou Du, Justin Li, Jian Gao, Zhang Li, Hao Yang, Boxing Chen, Osamu Yoshie

Low-Resource NLP

Challenge:	Existing solutions for text-to-image synthesis are sensitive on textual prompts, posing a challenge for novice users.
Approach:	They propose a dialogue-based TIS prompt generation model that emphasizes user experience for novice users.
Outcome:	The proposed model emphasizes user experience for novice users . it improves user-centricity score while maintaining a competitive quality of synthesized images.

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)

Copied to clipboard

Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu

Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement (2025.acl-long)

Challenge:	Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent.
Approach:	They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs.
Outcome:	The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models.

Copied to clipboard

Yichen Dong, Xinglin Lyu, Junhui Li, Daimeng Wei, Min Zhang, Shimin Tao, Hao Yang

Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding (2024.findings-acl)

Challenge:	Recent research has shown that large language models (LLMs) can enhance translation quality through self-refinement.
Approach:	They propose to extend translation refinement from sentence-level to document-level by using document-to-document (Doc2Doc) translations.
Outcome:	The proposed method improves translation quality across ten translation tasks with LLaMA-3-8B-Instruct and Mistral-Nemo-Instru.

Copied to clipboard

Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, Zhifang Sui

Supervised Optimism Correction: Be Confident When LLMs Are Sure (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have a high inference latency stemming from autoregressive decoding.
Approach:	They propose a novel decoding paradigm that drafts multiple tokens and verifies them in parallel . they aim to provide a catalyst for further research on Speculative Decoding .
Outcome:	The proposed method drafts multiple tokens and verifies them in parallel . it can be used to accelerate inference in large language models.

Copied to clipboard

Junjie Zhang, Rushuai Yang, Shunyu Liu, Ting-En Lin, Fei Huang, Yi Chen, Yongbin Li, Dacheng Tao

"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations (2026.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable success across diverse tasks such as instruction following, code generation, and medical diagnosis.
Approach:	They propose a supervised fine-tuning-based auxiliary loss for Q-value estimations during supervised refinement.
Outcome:	The proposed method outperforms beam search on GSM8K, MATH, and GAOKAO on reasoning benchmarks.

Copied to clipboard

Yang Wu, Jinhong Yu, Jingwei Xiong, Zhimin Tao, Xiaozhong Liu

Event Detection without Triggers (N19-1)

Challenge:	Existing large language models (LLMs) are reactive and respond only when prompted, limiting their effectiveness in collaborative settings.
Approach:	They introduce a proactive LLM assistant designed to enhance biomedical collaboration between AI systems and human experts through timely, context-aware interventions.
Outcome:	The proposed model outperforms baselines in intervention precision and collaborative task utility, highlighting the potential of proactive LLMs as intelligent scientific assistants.

Copied to clipboard

Shulin Liu, Yang Li, Feng Zhang, Tao Yang, Xinpeng Zhou

Measuring Human Contribution in AI-Assisted Content Generation (2026.acl-long)

Challenge:	Existing approaches to event detection require annotated triggers and event types in training data.
Approach:	They propose a framework that encodes the representation of a sentence based on target event types.
Outcome:	The proposed framework achieves competitive performances compared with state-of-the-art methods.

Copied to clipboard

Yueqi Xie, Tao Qi, Jingwei Yi, Xiyuan Yang, Ryan Whalen, Junming Huang, Qian Ding, Yu Xie, Xing Xie, Fangzhao Wu

Language Agents: Foundations, Prospects, and Risks (2024.emnlp-tutorials)

Challenge:	generative AI has created a new way to generate content with humans . varying degrees of human contribution in content generation poses significant challenges for the delineation of originality .
Approach:	They propose a framework to measure human contribution in AI-assisted content generation by calculating mutual information between human input and AI-aided output relative to self-information of AI-assist output.
Outcome:	The proposed measure discriminates between varying degrees of human contribution across multiple creative domains and is validated in real-world applications.

Copied to clipboard

Yu Su, Diyi Yang, Shunyu Yao, Tao Yu

Multiplex Graph Neural Network for Extractive Text Summarization (2021.emnlp-main)

Challenge:	Language agents are autonomous agents that can follow language instructions to perform diverse tasks in real-world or simulated environments.
Approach:	They propose to provide a conceptual framework for language agents and a comprehensive discussion on key topics.
Outcome:	The proposed tutorial provides a conceptual framework of language agents and comprehensive discussion on important topic areas.

Copied to clipboard

Baoyu Jing, Zeyu You, Tao Yang, Wei Fan, Hanghang Tong

MUG: Interactive Multimodal Grounding on User Interfaces (2024.findings-eacl)

Challenge:	Existing methods for extractive text summarization do not consider multiple types of inter-sentential relationships, nor model intra-sententential relationships.
Approach:	They propose a novel method to combine different types of relationships among sentences and words to model sentence embedding.
Outcome:	The proposed model is compared with existing methods on CNN/DailyMail benchmark dataset to demonstrate its effectiveness.

Copied to clipboard

Tao Li, Gang Li, Jingjie Zheng, Purple Wang, Yang Li

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit (2024.emnlp-industry)

Challenge:	Prior studies modeled multimodal UI grounding in one round, but such an interaction is inherently iterative.
Approach:	They propose a task where a user and an agent collaborate on an interface screen . they use a dataset of 77,820 sequences of human user-agent interaction on mobile interfaces .
Outcome:	The proposed task improves the absolute task completion by 18% over the entire test set and 31% over the challenging split.

Copied to clipboard

Ruihao Gong, Yang Yong, Shiqiao Gu, Yushi Huang, Chengtao Lv, Yunchen Zhang, Dacheng Tao, Xianglong Liu

CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification (2024.eacl-long)

Challenge:	Existing quantization techniques have been categorized as 'simple' and 'highly efficient' however, their configurations vary from each other and cannot be fairly compared .
Approach:	They propose a plug-and-play compression toolkit to explore the impact of quantization.
Outcome:	The proposed toolkit explores the impact of quantization on large language models.

Copied to clipboard

Yang Li, Canran Xu, Guodong Long, Tao Shen, Chongyang Tao, Jing Jiang

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)

Challenge:	Existing methods to improve pre-trained language models for many-class classification suffer from verbalizer ambiguity . a significant disparity exists between the pre-training and fine-tuning stages of the model .
Approach:	They propose a method to tune pre-trained language models to a broad spectrum of tasks . they use an instance-dependent soft prefix to complement language verbalizers in many-class classification .
Outcome:	The proposed method outperforms baselines on many-class datasets.

Copied to clipboard

Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu

Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking (2022.acl-long)

Challenge:	Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering.
Approach:	They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow.
Outcome:	The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow.

Copied to clipboard

Yingrui Yang, Yifan Qiao, Tao Yang

WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics (2026.acl-long)

Challenge:	Recent work has adopted a late interaction architecture with pre-computed contextual token representations at the cost of a large online storage.
Approach:	They propose to decouple document-specific and document-independent ranking contributions during codebook-based compression for effective online decompression and embedding composition for better search relevance.
Outcome:	The proposed model achieves high relevance and space efficiency with minimal computational cost and low computational complexity.

Copied to clipboard

Chenxu Liu, Yingjie Fu, Wei Yang, Ying Zhang, Tao Xie

Explainability & Interpretability in NLP

Challenge:	Web applications (web apps) are a key arena for large language models to demonstrate their code generation capabilities and commercial potential.
Approach:	a new benchmark for large language models (LLMs) is designed to provide real-world user requirements and generalizable evaluation metrics.
Outcome:	a new benchmark for large language models (LLMs) provides a real-world, generalizable, and interpretable evaluation score . the benchmark measures user requirements, expression styles and human-preference-aligned weights . a web application can be used to demonstrate its commercial potential, authors say .

A Zero-Shot Language Agent for Computer Control with Structured Reflection (2023.findings-emnlp)

Copied to clipboard

Tao Li, Gang Li, Zhiwei Deng, Bryan Wang, Yang Li

SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications (D18-1)

Challenge:	Recent works require a model to learn from trace examples of a task via supervised learning or few/many-shot prompting.
Approach:	They propose a model that iteratively learns from its mistakes via self-reflection and structured thought management.
Outcome:	The proposed model outperforms previous models on easy tasks with more efficient reasoning and self-reflection.

Copied to clipboard

Zexuan Zhong, Jiaqi Guo, Wei Yang, Jian Peng, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)

Challenge:	Existing approaches to generate programs from natural language do not address program aliasing . semantically equivalent programs may have many syntactically different forms .
Approach:	They propose a semantics-based approach to generate regular expressions from natural language.
Outcome:	The proposed approach improves on three public datasets.

Copied to clipboard

Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Challenge:	Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT).
Approach:	They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge.
Outcome:	The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples.

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation (2026.acl-long)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Hengyuan Zhang, Shiping Yang, Xiao Liang, Chenming Shang, Yuxuan Jiang, Chaofan Tao, Jing Xiong, Hayden Kwok-Hay So, Ruobing Xie, Angel X. Chang, Ngai Wong

Evaluation Dataset for Lexical Translation Consistency in Chinese-to-English Document-level Translation (2024.lrec-main)

Challenge:	Existing studies show that stronger models are not always optimal teachers, suggesting a mismatch between the teacher’s output and the student’s learning ability.
Approach:	They propose a method that routes each prompt to its optimal teacher via a query-level router that jointly considers the student models’ learnability and teacher models’ response quality.
Outcome:	The proposed method outperforms baselines on six benchmarks including instruct tuning and math reasoning settings.

Copied to clipboard

Xiangyu Lei, Junhui Li, Shimin Tao, Hao Yang

Multilinguality

Challenge:	Existing studies on document-level neural machine translation (NMT) assume that all repeated source words should be translated consistently.
Approach:	They construct a test set of 310 bilingual news articles to evaluate lexical translation consistency.
Outcome:	The proposed test sets show that translation consistency is consistent across multiple languages.

Improving Text Generation with Student-Forcing Optimal Transport (2020.emnlp-main)

Copied to clipboard

Jianqiao Li, Chunyuan Li, Guoyin Wang, Hao Fu, Yuhchen Lin, Liqun Chen, Yizhe Zhang, Chenyang Tao, Ruiyi Zhang, Wenlin Wang, Dinghan Shen, Qian Yang, Lawrence Carin

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)

Challenge:	Maximum likelihood estimation (MLE) is used to train models, but during testing, the model is conditioned on previously generated tokens, resulting in exposure bias.
Approach:	They propose to use optimal transport to match the sequences generated in MLE and test modes to reduce exposure bias.
Outcome:	The proposed method is validated on machine translation, text summarization, and text generation tasks.

Copied to clipboard

Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Safe-FedLLM: Delving into the Safety of Federated Large Language Models (2026.acl-long)

Challenge:	Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations.
Approach:	They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference.
Outcome:	The proposed method significantly mitigates object hallucinations across various model architectures.

Copied to clipboard

Mingxiang Tao, Yu Tian, Wenxuan Tu, Yue Yang, Xue Yang, Xiangyan Tang

Text Classification

Challenge:	Existing work on federated learning for large language models (FL) addresses privacy and data-silo issues in the training of large language model training.
Approach:	They propose a probe-based defense framework for FedLLM that constructs defenses across three levels: Step-Level, Client-Level and Shadow-Level.
Outcome:	The proposed framework improves FedLLM's robustness against malicious clients while maintaining competitive performance on benign data.

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors (2026.acl-long)

Copied to clipboard

Chenghao Yang, Yuning Zhang, Zhoufutu Wen, Tao Gong, Jiaheng Liu, Qi Chu, Nenghai Yu

Green & Sustainable NLP

Challenge:	Existing metrics fail to distinguish mandatory behaviors required for task success from non-mandatory patterns that reflect a model’s autonomous preferences.
Approach:	They propose to use response pattern similarity and action graph similarity to isolate non-mandatory behaviors from mandatory behaviors.
Outcome:	Evaluating 18 models from 8 providers on -Bench and 2-Bench against Claude Sonnet 4.5, the authors find that within-family model pairs score 5.9 pp higher in response pattern similarity and action graph similarity .

Polymorphic Universal Transformer (2026.acl-long)

Copied to clipboard

Yilong Chen, Zitian Gao, Yihao Xiao, Jason Klein Liu, Xinyu Yang, Yifan Luo, Haoming Luo, Zhengmao Ye, Tingwen Liu, Ran Tao, Bryan Dai

Data-Efficiently Learn Large Language Model for Universal 3D Scene Perception (2025.findings-naacl)

Challenge:	Compute Distribution Skew is a pathological phenomenon in ultra-deep recurrent models . it causes over-smoothing, representation rank collapse, and degraded reasoning performance.
Approach:	They propose a dynamic architecture that redefines recursive computation by decoupling parameter count from depth.
Outcome:	The proposed model significantly improves representation rank and reasoning robustness while reducing computation by 64.7%.

Copied to clipboard

Zehan Wang, Haifeng Huang, Yang Zhao, Ziang Zhang, Tao Jin, Zhou Zhao

EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval (2026.findings-acl)

Challenge:	Existing methods for 3D scene understanding are limited to specific downstream tasks, hindering their practicality in real-world applications.
Approach:	They propose a 3D visual perceptual ability and advanced reasoning capabilities for 3D scenes by aligning 3D representations into the feature space of advanced LLMs.
Outcome:	The proposed system achieves a 82.2% relative score compared with state-of-the-art methods with limited data.

Copied to clipboard

Yifan Song, Xingjian Tao, Zhicheng Yang, Yihong Luo, Jing Tang

NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application (2021.findings-emnlp)

Challenge:	Existing lightweight approaches to retrieval-augmented generation fail to capture latent semantic connections between disjoint entities.
Approach:	They propose a lightweight RAG framework that constructs a hypergraph capturing both structure and semantic relationships using a hybrid structural-semantic retrieval mechanism.
Outcome:	EHRAG outperforms state-of-the-art methods on four datasets while maintaining zero token consumption.

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Yang Yu, Tao Qi, Yongfeng Huang, Qi Liu

BPID: A Benchmark for Personal Identity Deduplication (2024.emnlp-industry)

Challenge:	Existing language models are pre-trained and distilled on general corpus like Wikipedia, which has gaps with the news domain and may be suboptimal for news intelligence.
Approach:	They propose a method to distill existing language models on Wikipedia to enable efficient news intelligence.
Outcome:	The proposed model can be used to build and test a news intelligence application on Wikipedia and Wikipedia.

Copied to clipboard

Runhui Wang, Yefan Tao, Adit Krishnan, Luyang Kong, Xuanqing Liu, Yuqian Deng, Yunzhao Yang, Henrik Johnson, Andrew Borthwick, Shobhit Gupta, Aditi Gundlapalli, Davor Golac

Multi-grained Named Entity Recognition (P19-1)

Challenge:	Data deduplication is a critical task in data management and mining, focused on consolidating duplicate records that refer to the same entity.
Approach:	They propose to use a dataset with 1,000,000 unlabeled synthetic PII profiles and a subset of 10,000 pairs curated and labeled as matches or non-matches.
Outcome:	The proposed datasets contain synthetic profiles built from publicly available sources that do not represent real individuals.

Copied to clipboard

Congying Xia, Chenwei Zhang, Tao Yang, Yaliang Li, Nan Du, Xian Wu, Wei Fan, Fenglong Ma, Philip Yu

OntoGuard: Enforcing Action Admissibility for LLM Agents in Complex Interactive Environments (2026.findings-acl)

Challenge:	Existing approaches treat Named Entity Recognition (NER) as a sequence labeling task.
Approach:	They propose a framework for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested.
Outcome:	The proposed framework outperforms current state-of-the-art frameworks by 4.4% in terms of the F1 score among nested/non-overlapping NER tasks.

Copied to clipboard

Pengxiang Liu, Tao Ren, Wei Xiong, Tingrui Yang, Junjie Wang, Jun HU

Challenge:	Existing approaches to large language models (LLMs) are limited by their ability to enforce environmental and behavioral admissibility.
Approach:	They propose an ontological framework to guard LLM agents by enforcing environmental and behavioral admissibility.
Outcome:	Experiments on ScienceWorld and VirtualHome show that OntoGuard can enforce environmental and behavioral admissibility while preventing invalid actions.

Navigating the OverKill in Large Language Models (2024.acl-long)

Copied to clipboard

Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin

KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)

Challenge:	Recent studies have highlighted a tendency among large language models to refuse to answer benign queries.
Approach:	They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding.
Outcome:	The proposed approach reduces the refusal rate by 20% while having little impact on safety.

Copied to clipboard

Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng Li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems (2026.acl-long)

Challenge:	Recent advances in pre-trained language models have made it possible to generate human-like text.
Approach:	They propose to integrate an open-ended text adventure game in Chinese, named KuiLeiXi, where players interact with the AI until the plot goals are reached.
Outcome:	The proposed game lacks incentives and relies on players to explore on their own.

Copied to clipboard

Shuhang Chen, Hangjie Yuan, Yunqiu Xu, Pengwei Liu, Tao Feng, Jun Cen, Zeying Huang, Yi Yang

ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models (2025.coling-main)

Challenge:	Existing multimodal large language models (MLLMs) exhibit significant limitations when extracting essential information and reasoned properties from diagrams and performing complex reasoning based on these visual inputs.
Approach:	They propose a benchmark that provides a fine-grained evaluation of MLLMs’ perception and reasoning capabilities.
Outcome:	The proposed benchmark shows that existing MLLMs exhibit limitations when extracting essential information and reasoned properties from diagrams and performing complex reasoning based on these visual inputs.

Copied to clipboard

Chenyang Song, Xu Han, Zhengyan Zhang, Shengding Hu, Xiyu Shi, Kuai Li, Chen Chen, Zhiyuan Liu, Guangli Li, Tao Yang, Maosong Sun