Papers by Hua Yang

PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt Learning (2022.emnlp-industry)

Challenge:	RL-friendly models exhibit intra-class compactness and inter-class separation in probability assignments . under identical training, Qwen models achieve substantial gains, while others like Llama yield limited improvements.
Approach:	They propose a method to quantify distributional clarity in probability space . they show distributional clearness is a trainable property underlying RL-Friendliness .
Outcome:	The proposed model families achieve substantial gains under identical training, while others like Llama yield limited improvements.

Copied to clipboard

Zeyang Lei, Chao Zhang, Xinchao Xu, Wenquan Wu, Zheng-yu Niu, Hua Wu, Haifeng Wang, Yi Yang, Shuanglong Li

Effective Convolutional Attention Network for Multi-label Clinical Document Classification (2021.emnlp-main)

Challenge:	Online advertisement text generation models have achieved remarkable success in generating high-quality text ads, but some challenges remain, such as low-resource scenarios and training efficiency for multiple ad tasks.
Approach:	They propose a unified text ad generation framework with multi-task prompt learning to tackle low-resource ade generation problem and a multi-step prompt learning mechanism to efficiently solve multiple aed generation tasks.
Outcome:	The proposed framework outperforms the state-of-the-art on offline and online metrics.

Copied to clipboard

Yang Liu, Hua Cheng, Russell Klopfer, Matthew R. Gormley, Thomas Schaaf

Information Retrieval

Challenge:	a large number of medical encounters need to be coded everyday due to long document sets and large label set.
Approach:	They propose a convolutional attention network for multi-label document classification problem . they use convolution-based encoders and convolution networks to aggregate information across documents .
Outcome:	The proposed model outperforms prior best model and multilingual Transformer model on a widely used dataset in the medical domain.

Universal Sentence Encoder for English (D18-2)

Copied to clipboard

Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St. John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, Brian Strope, Ray Kurzweil

Agentic Episodic Control (2026.findings-acl)

Challenge:	TensorFlow Hub sentence embedding models have good task transfer performance . model variants allow for trade-offs between accuracy and compute resources .
Approach:	They propose easy-to-use TensorFlow Hub sentence embedding models with good task transfer performance.
Outcome:	The proposed models outperform models without transfer learning and those that use only word-level transfer on a number of NLP tasks.

Copied to clipboard

Xidong Yang, Wenhao Li, Junjie Sheng, Yun Hua, Haosheng Chen, Chuyun Shen, Xiangfeng Wang

Green & Sustainable NLP

Challenge:	Existing methods for reinforcement learning (RL) are limited by poor data efficiency and weak generalization.
Approach:	They propose a novel architecture that integrates large language models into episodic RL.
Outcome:	The proposed architecture achieves 2–6 higher data efficiency than baselines and is the only method to solve complex tasks like UnlockLocal with over 90% success.

AttnPO: Attention-Guided Process Supervision for Efficient Reasoning (2026.acl-long)

Copied to clipboard

Shuaiyi Nie, null Dingsiyu, Wenyuan Zhang, Linhao Yu, Tianmeng Yang, Yao Chen, Weichong Yin, Yu Sun, Hua Wu, Tingwen Liu

SudokuFill: A Multi-Agent Progressive Filling Framework for Document-Level Scientific Information Extraction (2026.findings-acl)

Challenge:	Existing trajectory-level length penalties fail to effectively shorten reasoning length and degrade accuracy, as they treat all reasoning steps uniformly and lack fine-grained signals to distinguish redundancy from necessity.
Approach:	They propose a low-overhead process-supervised RL framework that leverages the model’s intrinsic attention signals for step-level credit assignment.
Outcome:	The proposed framework reduces reasoning length while improving performance across 9 benchmarks.

Copied to clipboard

Yang Li, Yajiao Wang, Yu Zhang, Yuanzhe Zhang, Maodi Hu, Mengting Zhang, Xi Sun, Hua Yue, Zhixiong Zhang

Information Extraction & Text Mining

Challenge:	Scientific information extraction (SciIE) is a key bottleneck for turning unstructured papers into computable knowledge bases.
Approach:	They propose a scientific information extraction framework that solves a Sudoku problem as a progressive filling problem.
Outcome:	The proposed framework outperforms the GPT-4o model on a document-level adjuvant dataset.

Morpheme Sense Disambiguation: A New Task Aiming for Understanding the Language at Character Level (2024.lrec-main)

Copied to clipboard

Yue Wang, Hua Zheng, Yaqi Yin, Hansi Wang, Qiliang Liang, Yang Liu

Visual Data in NLP

Challenge:	Morphemes are a strong linguistic feature to capture lexical semantics, but lack of morpheme-informed resources and the expense of manual annotations hinder morphme-enhanced methods.
Approach:	They propose a task of Morpheme Sense Disambiguation with two subtasks in-text and in-word to generalize morpheme features on more tasks.
Outcome:	The proposed tasks are based on two morpheme-annotated datasets for Chinese . the best model yields a promising precision of 77.66% on in-text and 88.19% on in word .

QDMR-based Planning-and-Solving Prompting for Complex Reasoning Tasks (2024.lrec-main)

Copied to clipboard

Jinfeng Huang, Qiaoqiao She, Wenbin Jiang, Hua Wu, Yang Hao, Tong Xu, Feng Wu

Reasoning

Challenge:	Existing Plan-and-Solve prompting methods are difficult to implement for complex questions.
Approach:	They propose a plan-and-solve prompting method based on Question Decomposition Meaning Representation (QDMR) it allows LLM to generate a QDMR graph to represent problem-solving logic .
Outcome:	The proposed method can represent and execute the problem-solving logic of complex questions more accurately than existing methods.

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense (2025.naacl-long)

Copied to clipboard

Yang Ouyang, Hengrui Gu, Shuhang Lin, Wenyue Hua, Jie Peng, Bhavya Kailkhura, Meijun Gao, Tianlong Chen, Kaixiong Zhou

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)

Challenge:	Existing methods to defend against jailbreak attacks exploit vulnerabilities to elicit unintended or harmful outputs.
Approach:	They propose a method to defend against jailbreak attacks by patching specific layers within large language models through self-augmented datasets.
Outcome:	The proposed approach reduces harmfulness and attack success rate of jailbreak attacks without compromising utility for benign queries compared to previous methods.

Copied to clipboard

Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

EoT: Evolution of Thoughts for Complex Reasoning Tasks (2025.findings-emnlp)

Challenge:	Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood.
Approach:	They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction .
Outcome:	The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones .

Copied to clipboard

Qin Hua, Jiaqi Sun, Shiyou Qian, Dingyu Yang, Jian Cao, Guangtao Xue

Reasoning

Challenge:	Existing studies focus on ensuring behavior fidelity, factuality or reliability in generated reasoning processes, but they neglect the simultaneous optimization of all three aspects for each thought.
Approach:	They propose a thought assessment method that is sensitive to knowledge and LLM behaviors . they use three scorers to evaluate each thought by considering domain context, semantic alignment, and behavior impact.
Outcome:	The proposed framework outperforms advanced approaches in knowledge-based complex tasks.

A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning (2022.findings-naacl)

Copied to clipboard

Yang Zhao, Hua Qin, Wang Zhenyu, Changxi Zhu, Shihan Wang

Dialogue Systems & Conversational Agents

Challenge:	Existing training paradigms for dialogue policy learning with brute-force random sampling are expensive and lack reliable evaluation of difficulty scores.
Approach:	They propose a flexible adaptive curriculum learning framework that integrates curriculum learning with a generic global curriculum.
Outcome:	The proposed framework improves learning performance and efficiency on three public dialogue datasets.

Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior (2020.findings-emnlp)

Copied to clipboard

Zi Lin, Jeremiah Liu, Zi Yang, Nan Hua, Dan Roth

Leveraging Word-Formation Knowledge for Chinese Word Sense Disambiguation (2021.findings-emnlp)

Challenge:	Spectral-normalized identity priors (SNIP) is a structured pruning approach for a Transformer model.
Approach:	They propose a structured pruning approach which penalizes an entire residual module toward an identity mapping.
Outcome:	The proposed method improves on 5 GLUE benchmark tasks while maintaining comparable performance.

Copied to clipboard

Hua Zheng, Lei Li, Damai Dai, Deli Chen, Tianyu Liu, Xu Sun, Yang Liu

Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models (2025.emnlp-main)

Challenge:	Word sense disambiguation (WSD) methods have not explored word-formations in parataxis languages like Chinese.
Approach:	They propose to leverage word-formation knowledge to enhance Chinese WSD by incorporating word-forms into sense disambiguation models.
Outcome:	The proposed model improves on baselines in Chinese word sense disambiguation (WSD) with word-formation knowledge, the results show.

Copied to clipboard

Mo Zhiqiang, Yang Hua, Jiahui Li, Yuan Liu, Shawn Wong, Jianmin Huang

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate (2024.findings-emnlp)

Challenge:	Existing approaches to integrating graph and language models face two key limitations: achieving robust semantic alignment and ensuring interpretability in outputs.
Approach:	They propose a framework to integrate graph and language modalities while enhancing transparency.
Outcome:	Extensive experiments on three benchmark datasets show that the proposed framework surpasses existing methods in efficiency and generates outputs that are significantly more interpretable.

Copied to clipboard

Alfonso Amayuelas, Xianjun Yang, Antonis Antoniades, Wenyue Hua, Liangming Pan, William Yang Wang

A Survey on LLM-powered Agents for Recommender Systems (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have shown exceptional results when working individually, and have reduced parameter size and inference times.
Approach:	They evaluate the behavior of a network of models collaborating through debate under the influence of an adversary and examine inference-time methods to generate more compelling arguments.
Outcome:	The proposed model-based model-driven analysis shows that the model-led model-mediated debates generate more compelling arguments and provide a defensive strategy.

Copied to clipboard

Qiyao Peng, Hongtao Liu, Hua Huang, Jian Yang, Qing Yang, Minglai Shao

TrustAgent: Towards Safe and Trustworthy LLM-based Agents (2024.findings-emnlp)

Challenge:	Large Language Models have demonstrated remarkable capabilities in natural language understanding, reasoning, and generation.
Approach:	They present a comprehensive synthesis of large language models and their applications . they dissect a four-module agent architecture and review representative designs .
Outcome:	The proposed models address fundamental challenges in traditional recommender systems . they include limited comprehension of complex user intents, insufficient interaction capabilities .

Copied to clipboard

Wenyue Hua, Xianjun Yang, Mingyu Jin, Zelong Li, Wei Cheng, Ruixiang Tang, Yongfeng Zhang

Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark (2024.emnlp-main)

Challenge:	Existing LLMs are primarily used for simple text-related tasks, but LLM-based agents can undertake more complex tasks that require planning and interaction with the physical world and humans.
Approach:	They propose an Agent-Constitution-based agent framework with a particular focus on improving the LLM-based agents' safety.
Outcome:	The proposed framework can enhance an LLM agent’s safety across multiple domains by identifying and mitigating potential dangers during the planning process.

Copied to clipboard

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xianfeng Tang, Chen Luo, Ming Zeng, Haoming Jiang, Yifan Gao, Priyanka Nigam, Sreyashi Nag, Bing Yin, Yining Hua, Xuan Zhou, Omid Rohanian, Anshul Thakur, Lei Clifton, David Clifton

CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality (2020.acl-main)

Challenge:	Existing studies focus on evaluating large language models in close-ended QA tasks, but many clinical decisions involve answering open-ended questions without pre-set options.
Approach:	They construct a benchmark to better understand large language models in the clinic . they use existing datasets to evaluate LLMs in clinical situations .
Outcome:	The proposed model outperforms human experts in multiple medical tasks.

Copied to clipboard

Wenmeng Yu, Hua Xu, Fanyang Meng, Yilin Zhu, Yixiao Ma, Jiele Wu, Jiyun Zou, Kaicheng Yang

Multimodality

Challenge:	Existing studies in multimodal sentiment analysis only use unified multimodal annotations, which do not reflect the independent sentiment of single modalities.
Approach:	They propose a Chinese single- and multi-modal sentiment analysis dataset with multimodal and independent unimodal annotations that can be used to study the interaction between modalities.
Outcome:	The proposed methods achieve state-of-the-art performance and learn more distinctive unimodal representations.

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment (2025.emnlp-main)

Copied to clipboard

Mengyu Bu, Shaolei Zhang, Zhongjun He, Hua Wu, Yang Feng

Mixup Decoding for Diverse Machine Translation (2021.findings-emnlp)

Challenge:	Multilingual large language models (LLMs) possess impressive multilingual understanding and generation capabilities, but performance and cross-lingual alignment often lag for non-dominant languages.
Approach:	They propose a representation-level framework to enhance multilingual performance of pre-trained LLMs by integrating multilingual semantic alignment and language feature integration.
Outcome:	The proposed framework improves multilingual capability of pre-trained LLMs by bringing representations closer and improving cross-lingual alignment.

Copied to clipboard

Jicheng Li, Pengzhi Gao, Xuanfu Wu, Yang Feng, Zhongjun He, Hua Wu, Haifeng Wang

Machine Translation

Challenge:	Existing methods for generating multiple translations for source and target languages neglect the one-to-many mapping between the source and the target languages.
Approach:	They propose a method to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding.
Outcome:	Experiments on WMT’16 en-ro, WMT'14 en de, and WMT ‘17 zh-en show that the proposed method outperforms all previous diverse machine translation methods.

Weights-Rotated Preference Optimization for Large Language Models (2025.emnlp-main)

Copied to clipboard

Chenxu Yang, Ruipeng Jia, Mingyu Zheng, Naibin Gu, Zheng Lin, Siyuan Chen, Weichong Yin, Hua Wu, Weiping Wang

Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech (2022.acl-long)

Challenge:	Existing methods to align large language models with high reward hacking are limited by the complexity of the parameter space and the complexity.
Approach:	They propose a weights-rotated preference optimization algorithm that constrains the output layer logits with the KL divergence inherited from DPO and fine-tunes the intermediate hidden states.
Outcome:	The proposed algorithm achieves a 3.27-point improvement on AlpacaEval 2 and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters.

Copied to clipboard

Yang Li, Cheng Yu, Guangzhi Sun, Hua Jiang, Fanglei Sun, Weiqin Zu, Ying Wen, Yang Yang, Jun Wang

Multimodality

Challenge:	Experimental results show that the proposed model improves naturalness and prosody diversity with clear margins.
Approach:	They propose a cross-utterance conditional VAE to estimate posterior probability distribution of latent prosody features for each phoneme by conditioning on acoustic features, speaker information, and text features from past and future sentences.
Outcome:	The proposed model improves naturalness and prosody diversity with clear margins.

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping (2026.findings-acl)

Copied to clipboard

Yao Chen, Yilong Chen, Yinqi Yang, Junyuan Shang, Zhenyu Zhang, Zefeng Zhang, Shuaiyi Nie, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang, Tingwen Liu

Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation (2021.naacl-main)

Challenge:	Existing approaches to increasing effective depth of LLMs rely on parameter reuse, extending computation through recursive execution.
Approach:	They propose a training-time sparse depth allocation framework that progressively increases depth for a small subset of parameters as training evolves.
Outcome:	The proposed model outperforms existing approaches to increasing the effective depth of language models while reducing training FLOPs overhead from approximately 16–20% to only 1–3% relative to a standard Transformer backbone.

Copied to clipboard

Hua Zheng, Damai Dai, Lei Li, Tianyu Liu, Zhifang Sui, Baobao Chang, Yang Liu

Challenge:	Existing definition generation methods take the source word as an indecomposable semantic unit, but in parataxis languages like Chinese, word meanings can be composed using the word formation process.
Approach:	They propose to use word formation features to enhance Definition Generation (DG) in Chinese to generate an explanatory text.
Outcome:	The proposed model enhances Definition Generation (DG) in Chinese by decomposing the word meaning into different semantic components.

Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (P19-1)

Copied to clipboard

An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)

Challenge:	Recent results show pre-trained language models (LMs) can improve machine reading comprehension (MRC) Experimental results indicate that KT-NET offers significant and consistent improvements over BERT .
Approach:	They propose a method that leverages external knowledge bases to improve machine reading comprehension (MRC) KT-NET employs an attention mechanism to select desired knowledge from KBs and fuses selected knowledge with BERT to enable context- and knowledge-aware predictions.
Outcome:	The proposed model outperforms baseline models on ReCoRD and SQuAD1.1 benchmarks and ranks 1st on the ReCoDR and SQUAD1.1 leaderboards.

Copied to clipboard

Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen