Papers by Yangyang Zhao

An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals (2025.acl-long)

Challenge:	Streaming automatic speech recognition models use high power consumption to improve usability and accuracy.
Approach:	They propose to optimize on-device speech recognition models by adjusting component energy sensitivities based on their specific energy sensitities to reduce power consumption.
Outcome:	The proposed approach achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods.

Copied to clipboard

Yangyang Zhao, Ben Niu, Libo Qin, Shihan Wang

From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models (2026.acl-long)

Challenge:	Evolutionary Algorithms (EAs) have been proven to effectively explore the solution space of neural networks by maintaining population diversity.
Approach:	They propose an elite individual injection mechanism to enhance EA’s search efficiency by adaptively introducing best-performing individuals into the population.
Outcome:	Experiments on four datasets show that the proposed approach significantly improves the balance between exploration and exploitation, boosting performance.

Copied to clipboard

Ling Shi, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Yangyang Liu, Linlong Xu, Longyue Wang, Deyi Xiong, Weihua Luo

Evolving Knowledge Distillation with Large Language Models and Active Learning (2024.lrec-main)

Challenge:	Recent research in mechanistic interpretability has revealed that Large Language models contain disentangled, human-understandable components.
Approach:	They propose a framework that first identifies causal task features through frequency recall and interventional filtering, then selects “Feature-Resonant Data” that maximally activates task features for fine-tuning.
Outcome:	The proposed framework outperforms existing models on mathematical reasoning, summarization, and translation tasks while using only 50% of the data.

Copied to clipboard

Chengyuan Liu, Fubang Zhao, Kun Kuang, Yangyang Kang, Zhuoren Jiang, Changlong Sun, Fei Wu

Semantic-Aware Action Space Compression via LLM-DRL Synergy for Efficient Task-oriented Dialogue Policy Exploration (2025.findings-emnlp)

Challenge:	Existing studies have focused on the direct use of large language models for text generation and labeling, without fully exploring their potential to comprehend the target task and acquire valuable knowledge.
Approach:	They propose to distill the knowledge of large language models into smaller models by generating annotated data.
Outcome:	The proposed method improves the performance of small domain models while enhancing the ability of large language models.

Copied to clipboard

Yangyang Zhao, Ben Niu, Yuxuan Tan, Shihan Wang, Libo Qin

Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy (2021.emnlp-main)

Challenge:	Pre-trained large language models (LLMs) with world knowledge and semantic understanding are promising for task-oriented dialogue systems.
Approach:	a framework that synergizes pre-trained large language models with DRL is proposed . a lightweight action pruning mechanism is employed to eliminate implausible actions .
Outcome:	a new framework synergizes pre-trained large language models with DRL to guide decision-making . the proposed framework eliminates semantically implausible or low-potential actions from multi-turn dialogue context .

Copied to clipboard

Yangyang Zhao, Zhenyu Wang, Changxi Zhu, Shihan Wang

Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow (2026.findings-acl)

Challenge:	Existing methods for training dialogue policies rely on a single learning system, but it requires many rounds of interaction.
Approach:	They propose a complementary policy learning framework which exploits the complementary advantages of the episodic memory (EM) policy and the deep Q-network (DQN) policy.
Outcome:	The proposed framework outperforms existing methods relying on a single learning system on three dialogue datasets.

Copied to clipboard

Yangyang Zhong, Yanmei Gu, Zhengqing Zang, Xiaomeng Li, Yuqi Ding, Xibei Jia, Yuting Shen, Zhenzhong Lan, Liwang Zhu, Weiping Liu, Junlin Zhou, Haisheng Liu, Zhong Xin Yu, Pengxin Luo, Donglian Qi, Yunfeng Yan, Junbo Zhao

M2PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation (2026.acl-long)

Challenge:	Autoregressive (AR) language models dominate modern natural language processing due to strong likelihood-based training objectives and reliable left-to-right decoding.
Approach:	They characterize MDLM behavior along two dimensions: parallelism strength and generation order . authors propose a Generate-then-Edit paradigm that mitigates dependency loss .
Outcome:	The proposed model improves on tasks that require "backward information" the Generate-then-Edit paradigm improves parallel decoding efficiency while reducing dependency loss.

Copied to clipboard

Hao Wang, Linlong Xu, Heng Liu, Yangyang Liu, Xiaohu Zhao, Bo Zeng, Liangying Shao, Yichen Dong, Xinwei Wu, Jiang Zhou, Tianyu Dong, Xiangxiang Zeng, Longyue Wang, Weihua Luo

Machine Translation

Challenge:	prevailing methods for machine translation are often hindered by misleading reward signals.
Approach:	They propose a framework that aligns large language models to human preferences . they propose 'M2PO' to correct the bias towards partial errors .
Outcome:	The proposed framework outperforms open-source models and achieves parity with proprietary models.

Revisiting Sample Size Determination in Natural Language Understanding (2023.findings-acl)

Copied to clipboard

Ernie Chang, Muhammad Hassan Rashid, Pin-Jie Lin, Changsheng Zhao, Vera Demberg, Yangyang Shi, Vikas Chandra

Towards Zero-Shot Multilingual Transfer for Code-Switched Responses (2023.acl-long)

Challenge:	Recent work has sought to reduce the annotation costs through the use of active learning and data sampling.
Approach:	They propose to estimate the training sample size needed to achieve a targeted model performance based on small amount of training samples.
Outcome:	The proposed approach predicts model performance within a small margin of mean absolute error (0.9%) with only 10% data.

Copied to clipboard

Ting-Wei Wu, Changsheng Zhao, Ernie Chang, Yangyang Shi, Pierce Chuang, Vikas Chandra, Biing Juang

Multilinguality

Challenge:	Recent task-oriented dialog systems have had great success building English-based personal assistants, but extending these systems to a global audience may take tremendous efforts.
Approach:	They propose a framework that allows for efficient transfer by learning task-specific representations and encapsulating source and target language representations.
Outcome:	The proposed framework is able to successfully transfer language knowledge even when the target language corpus is limited.

Scaling Parameter-Constrained Language Models with Quality Data (2024.emnlp-industry)

Copied to clipboard

Ernie Chang, Matteo Paltenghi, Yang Li, Pin-Jie Lin, Changsheng Zhao, Patrick Huber, Zechun Liu, Rastislav Rabatin, Yangyang Shi, Vikas Chandra

RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction (2023.findings-emnlp)

Challenge:	Scaling laws in language modeling quantify training loss as a function of dataset size and model parameters, but neglect the critical role of data quality in model generalization.
Approach:	They propose to use effective training tokens as a combination of text diversity and syntheticity as measured by a teacher model to calculate scaling laws.
Outcome:	The proposed term effective training tokens is a combination of two readily-computed indicators of text diversity and syntheticity as measured by a teacher model.

Copied to clipboard

Chengyuan Liu, Fubang Zhao, Yangyang Kang, Jingyuan Zhang, Xiang Zhou, Changlong Sun, Kun Kuang, Fei Wu

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (NER) and Relation Extraction (RE) models have limited success when extracting general schemas such as quadruples and quintuples.
Approach:	They propose a formal formulation that covers almost all extraction schemas and a Recursive Method with Explicit Schema Instructor for UIE.
Outcome:	The proposed method shows strong performance under full-shot and few-shot settings and achieves state-of-the-art results on the tasks of extracting complex schemas.

More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs (2024.emnlp-main)

Copied to clipboard

Chengyuan Liu, Yangyang Kang, Shihang Wang, Lizhi Qing, Fubang Zhao, Chao Wu, Changlong Sun, Kun Kuang, Fei Wu

LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination (2024.naacl-long)

Challenge:	a recent study shows that performance on general tasks decreases after Large Language Models are fine-tuned on domain-specific tasks.
Approach:	They propose a general capability integration approach to integrate general capabilities and domain knowledge within a single instance.
Outcome:	The proposed method improves performance on domain-specific tasks by integrating general capabilities and domain knowledge.

Copied to clipboard

Kai Zhang, Yangyang Kang, Fubang Zhao, Xiaozhong Liu

Challenge:	Existing studies have focused on learning and enhancing large language models to understand and generate natural language.
Approach:	They propose a computational bionic memory mechanism equipped with a parameter-efficient fine-tuning schema to personalize medical assistants.
Outcome:	The proposed method can enhance the response with aware of previous mistakes for new queries during a dialogue session, but the training costs are prohibitive.

Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection (2025.acl-long)

Copied to clipboard

Cilin Yan, Jingyun Wang, Lin Zhang, Ruihui Zhao, Xiaopu Wu, Kai Xiong, Qingsong Liu, Guoliang Kang, Yangyang Kang

Bootstrapped Policy Learning for Task-oriented Dialogue through Goal Shaping (2024.emnlp-main)

Challenge:	Recent work utilizes feedbacks generated from erroneous cases to guide prompt optimization . previous methods rely on computational resources and powerful GPUs .
Approach:	They propose an automatic prompt engineering method that leverages feedbacks from erroneous cases to guide prompt optimization.
Outcome:	The proposed method surpasses state-of-the-art methods with less steps and lower computational resources.

Copied to clipboard

Yangyang Zhao, Ben Niu, Mehdi Dastani, Shihan Wang

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Despite the promise of reinforcement learning, achieving seamless knowledge transitions in complex dialogue environments is difficult.
Approach:	They propose a Bootstrapped Policy Learning framework which adaptively tailors progressively challenging subgoal curriculum for each complex goal through goal shaping.
Outcome:	The proposed framework has shown to be effective across four publicly available datasets with different difficulty levels.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Bridging Reasoning and Action: Hybrid LLM–RL Framework for Efficient Cross-Domain Task-Oriented Dialogue (2026.findings-acl)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Yangyang Zhao, Linfan Dai, Li Cai, Bowen Xing, Libo Qin

Target-Aware Language Modeling via Granular Data Sampling (2024.emnlp-main)

Challenge:	Existing methods to solve cross-domain task-oriented dialogues are brittle when cross- domain constraints are not directly grounded in surface text or require commonsense inference.
Approach:	They propose a framework that makes LLM-derived constraint reasoning usable for RL.
Outcome:	Experiments show that the proposed framework outperforms single-model baselines on long-horizon tasks.

Copied to clipboard

Ernie Chang, Pin-Jie Lin, Yang Li, Changsheng Zhao, Daeil Kim, Rastislav Rabatin, Zechun Liu, Yangyang Shi, Vikas Chandra

LLM-QAT: Data-Free Quantization Aware Training for Large Language Models (2024.findings-acl)

Challenge:	Language model pretraining is the cornerstone of universal language models (LMs), creating generalpurpose representations to excel across a variety of downstream tasks.
Approach:	They propose to use multi-granular tokens to sample large-scale language models for domain-specific use cases.
Outcome:	The proposed model outperforms random sampled samples on eight benchmarks with 1% of the data and performs on par with the full RefinedWeb data.

Copied to clipboard

Zechun Liu, Barlas Oguz, Changsheng Zhao, Ernie Chang, Pierre Stock, Yashar Mehdad, Yangyang Shi, Raghuraman Krishnamoorthi, Vikas Chandra

STINMatch: Semi-Supervised Semantic-Topological Iteration Network for Financial Risk Detection via News Label Diffusion (2023.emnlp-main)

Challenge:	Several post-training quantization methods have been shown to perform well down to 8-bits.
Approach:	They propose a data-free distillation method that leverages generations produced by the pre-trained model to quantize any generative model independent of its training data.
Outcome:	The proposed method outperforms SoTA PTQ and LLaMA models at low bit precision.

Copied to clipboard

Xurui Li, Yue Qin, Rui Zhu, Tianqianjin Lin, Yongming Fan, Yangyang Kang, Kaisong Song, Fubang Zhao, Changlong Sun, Haixu Tang, Xiaozhong Liu

PDAMeta: Meta-Learning Framework with Progressive Data Augmentation for Few-Shot Text Classification (2024.lrec-main)

Challenge:	Commercial news provides rich semantics and timely information for automated financial risk detection.
Approach:	They propose a semi-supervised Semantic-Topological Iteration Network, STINMatch, along with a news-enterprise knowledge graph to endorse the risk detection enhancement.
Outcome:	The proposed model outperforms existing models in terms of generalization and semantics and annotation.

Copied to clipboard

Xurui Li, Kaisong Song, Tianqianjing Lin, Yangyang Kang, Fubang Zhao, Changlong Sun, Xiaozhong Liu

Low-Resource NLP

Challenge:	Existing text data augmentation methods can not ensure the diversity and quality of the generated data, which leads to sub-optimal performance.
Approach:	They propose a meta-learning framework with progressive data augmentation for few-shot text classification using prompt-based data augmented by attention-based methods.
Outcome:	The proposed framework outperforms state-of-the-art models and shows better robustness on four public few-shot text classification datasets.

An Efficient Dialogue Policy Agent with Model-Based Causal Reinforcement Learning (2025.coling-main)

Copied to clipboard

Kai Xu, Zhenyu Wang, Yangyang Zhao, Bopeng Fang

Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning (2021.findings-acl)

Challenge:	Existing models for dialogue policy training consider one-step dialogues, leading to inaccurate simulations.
Approach:	They propose a framework for dialogue policy learning that trains an agent to select dialogue actions via deep reinforcement learning.
Outcome:	The proposed framework achieves state-of-the-art performance on three dialogue datasets . it uses model-based reinforcement learning with automatically constructed causal chains .

Copied to clipboard

Fubang Zhao, Zhuoren Jiang, Yangyang Kang, Changlong Sun, Xiaozhong Liu

Low-Resource NLP

Challenge:	Existing models for relational fact extraction do not analyze the output data structure from the perspective of graph representation flexibility and heterogeneity.
Approach:	They propose a relational fact extraction model based on graph-oriented analytical perspective that outperforms other models.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets and shows that it is flexible and space-efficient.

Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation (2026.acl-long)

Copied to clipboard

Jiang Zhou, Xiaohu Zhao, Xinwei Wu, Tianyu Dong, Hao Wang, Yangyang Liu, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Deyi Xiong

Machine Translation

Challenge:	Current systems often fall short of this goal in settings where translation hinges on culturally grounded entities such as books, films, places, songs and idioms.
Approach:	They propose a framework that anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization.
Outcome:	The proposed framework improves on XC-Translate and shows that it can learn a robust reasoning process rather than imitating reference translations.

SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment (2026.findings-acl)

Copied to clipboard

Tianyu Dong, Yangyang Liu, Jiang Zhou, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Shaolin Zhu, Deyi Xiong

Multilinguality

Challenge:	Low-resource language tokens are often routed to different experts than those activated by high-resourced inputs, which hinders their efficacy in multilingual contexts.
Approach:	They propose a framework to transfer specialized capabilities from high-resource languages as anchors to low-resourced languages by using a symmetric Jensen-Shannon constraint.
Outcome:	The proposed framework outperforms standard instruction tuning on 5 low-resource languages and 3 benchmarks.

MultiAgentESC: A LLM-based Multi-Agent Collaboration Framework for Emotional Support Conversation (2025.emnlp-main)

Copied to clipboard

Yangyang Xu, Jinpeng Hu, Zhuoer Zhao, Zhangling Duan, Xiao Sun, Xun Yang

Rectifying the Emotional Flow: Aligning Priors and Dynamic Guidance for High-Arousal Text-to-Speech (2026.acl-long)

Challenge:	Existing studies focus on generating responses directly and neglect integration of domain-specific reasoning and expert interaction.
Approach:	They propose a training-free multi-agent collaboration framework for ESC to emulate human-like process of providing emotional support through dialogue analysis, strategy deliberation, and response generation.
Outcome:	The proposed framework excels at providing emotional support and diversifying support strategy selection.

Copied to clipboard

Fangming Feng, Dongjie Fu, Zequn Xie, Yu Zhang, Yangyang Wu, Zhou Zhao, Tao Jin