Papers by Dawei Zhang

DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation (2022.emnlp-main)

Challenge:	Current state-of-the-art neural dialogue models learn from human conversations . however, due to the open-ended nature of human conversations, the quality of training data varies .
Approach:	They propose a data manipulation framework to augment and highlight effective training samples . they also propose to increase its manipulation skills through gradient descent with validation samples a reshaping framework to proactively restructure the data distribution towards reliable samples is also proposed .
Outcome:	The proposed framework improves the performance of open-domain neural dialogue models with respect to evaluation metrics and human judgments.

Copied to clipboard

Hanqing Zhang, Dawei Song

Improving Knowledge-Aware Dialogue Response Generation by Using Human-Written Prototype Dialogues (2020.findings-emnlp)

Challenge:	Existing prompt tuning approaches for attribute-controllable text generation are difficult to implement due to the lack of interpretability of deep neural networks.
Approach:	They propose a new approach that incorporates attribute knowledge of discriminator to optimize prompt tuning by steering a frozen CLM to produce attribute-specific texts.
Outcome:	The proposed approach can achieve state-of-the-art control performance while maintaining high-quality text generation.

Copied to clipboard

Sixing Wu, Ying Li, Dawei Zhang, Zhonghai Wu

PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks (2025.emnlp-main)

Challenge:	Entity name matching always retrieves irrelevant facts from the view of local entity words.
Approach:	They propose a knowledge selection approach and a generative model that integrates commonsense knowledge into the dialogue response generation by integrating commonsensical knowledge into a query.
Outcome:	The proposed approach improves on the most metrics and comparable to baselines.

Copied to clipboard

Yunuo Liu, Dawei Zhu, Zena Al-Khalili, Dai Cheng, Yanjun Chen, Dietrich Klakow, Wei Zhang, Xiaoyu Shen

Reasoning

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, such as code generation, mathematical problem-solving, and general-purpose human instruction following.
Approach:	They propose to use large language models to process questions expressed in natural language to automate tourism-booking prices when multiple, overlapping farerules apply.
Outcome:	The proposed model can automate tourism-booking prices when multiple, overlapping farerules apply.

What Does Your Smile Mean? Jointly Detecting Multi-Modal Sarcasm and Sentiment Using Quantum Probability (2021.findings-emnlp)

Copied to clipboard

Yaochen Liu, Yazhou Zhang, Qiuchi Li, Benyou Wang, Dawei Song

Hierarchical Memory Organization for Wikipedia Generation (2025.acl-long)

Challenge:	Existing methods to model multi-modal sarcasm and sentiment are based on quantum probability . sarcasm and feelings embody intrinsic uncertainty of human cognition .
Approach:	They propose a quantum probability-driven multi-task learning framework for sarcasm and sentiment recognition using quantum superpositions and quantum interference.
Outcome:	The proposed model achieves state-of-the-art in multi-modal sarcasm and sentiment recognition.

Copied to clipboard

Eugene J. Yu, Dawei Zhu, Yifan Song, Xiangyu Wong, Jiebin Zhang, Wenxuan Shi, Xiaoguang Li, Qun Liu, Sujian Li

Challenge:	Existing methods for generating Wikipedia articles do not utilize memory directly for outline generation.
Approach:	They propose a method to generate Wikipedia articles autonomously by leveraging a hierarchical memory architecture.
Outcome:	The proposed framework outperforms baseline methods in producing informative and reliable articles.

Fine-grained Contrastive Learning for Definition Generation (2022.aacl-main)

Copied to clipboard

Hengyuan Zhang, Dawei Li, Shiping Yang, Yanran Li

Enhancing Retrieval-Augmented Generation via Evidence Tree Search (2025.acl-long)

Challenge:	Recent pre-trained transformer-based definition generation models lack effective representation learning to contain full semantic components of the given word, leading to under-specific definitions.
Approach:	They propose a novel contrastive learning method that encourages the model to capture more detailed semantic representations from the definition sequence encoding.
Outcome:	The proposed method could generate more specific definitions compared with state-of-the-art models.

Copied to clipboard

Hao Sun, Hengyi Cai, Yuchen Li, Xuanbo Fan, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Towards the Law of Capacity Gap in Distilling Language Models (2025.acl-long)

Challenge:	Evidence retrieval is used to enhance Large Language Models (LLMs) but in real-world applications, it often returns lengthy documents with redundant or irrelevant content, confusing downstream readers.
Approach:	They propose a framework that reformulates evidence retrieval as a dynamic tree expansion process.
Outcome:	The proposed framework outperforms existing methods on five datasets.

Copied to clipboard

Chen Zhang, Qiuchi Li, Dawei Song, Zheyu Ye, Yan Gao, Yao Hu

Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge (2025.emnlp-main)

Challenge:	Language model (LM) distillation aims at distilling knowledge in a large teacher LM to a small student one.
Approach:	They propose to use the law of capacity gap to distill knowledge from a large teacher to a small student model.
Outcome:	The proposed model outperforms other language models on a larger scale by using the law of capacity gap inducted from a preliminary study on small-scale (3B) LMs.

Copied to clipboard

Yi Sui, Chaozhuo Li, Chen Zhang, Dawei Song, Qiuchi Li

WIKIGENBENCH:Exploring Full-length Wikipedia Generation under Real-World Scenario (2025.coling-main)

Challenge:	Retrieval-augmented generation (RAG) aims to mitigate the hallucination of Large Language Models (LLMs) however, external knowledge may contain noise and conflict with parametric knowledge of LLMs, leading to degraded performance.
Approach:	They propose a Dual-Stream Knowledge-Augmented Framework for Shared-Private Semantic Synergy that refines the traditional self-attention into a mixed-attention that distinguishes shared and private semantics for a controlled knowledge integration.
Outcome:	Extensive experiments show that the proposed framework achieves a superior performance over baselines.

Copied to clipboard

Jiebin Zhang, Eugene J. Yu, Qinyu Chen, Chenhao Xiong, Dawei Zhu, Han Qian, Mingbo Song, Weimin Xiong, Xiaoguang Li, Qun Liu, Sujian Li

LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling (2026.acl-long)

Challenge:	Existing efforts to generate Wikipedia articles for new events fall short of real-world application.
Approach:	They propose a benchmark to generate Wikipedia articles for new events under real-world scenarios . they use systematic metrics and LLM-based metrics to assess verifiability, organization, and other aspects aligned with real-life scenarios.
Outcome:	The proposed benchmarks show that hierarchical-based methods generate more comprehensive content while fine-tuned methods achieve better verifiability.

Copied to clipboard

Dawei Xiang, Kexin Chu, Wenyan Xu, Wenhui Zhang, Wei Zhang

How Speculative Can Speculative Decoding Be? (2024.lrec-main)

Challenge:	Experiments show that LAS cuts token usage by 43% and reduces end-to-end latency by more than 36%, while causing at most a 1.4 percentage-point drop in accuracy compared with a strong fixed workflow.
Approach:	They propose a system that dynamically chooses the right workflow for each query.
Outcome:	Experiments show that LAS cuts token usage by 43% and reduces end-to-end latency by more than 36% while causing at most a 1.4 percentage-point drop in accuracy compared with a strong fixed workflow.

Copied to clipboard

Zhuorui Liu, Chen Zhang, Dawei Song

MasRouter: Learning to Route LLMs for Multi-Agent Systems (2025.acl-long)

Challenge:	Large language models (LLMs) have a largely increased latency due to their ability to autoregressively model . speculative decoding is a technique that trades generation quality for speed .
Approach:	They propose to use a draft model to draft tokens autoregressively and then verify them in parallel.
Outcome:	The proposed model could draft tokens autoregressively and then verify them in parallel . the proposed model trades quality for speed and could fail in verification stage .

Copied to clipboard

Yanwei Yue, Guibin Zhang, Boyang Liu, Guancheng Wan, Kun Wang, Dawei Cheng, Yiyan Qi

An Efficient Framework for Whole-Page Reranking via Single-Modal Supervision (2026.acl-industry)

Challenge:	Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often face significant costs and challenges in dynamic LLM selection.
Approach:	They propose a multi-agent system routing solution that integrates all components of MAS into a unified routing framework.
Outcome:	The proposed solution is high-performing, cost-effective, and efficient . it reduces overhead by up to 52.07 compared to current methods on HumanEval .

Copied to clipboard

Zishuai Zhang, Sihao Yu, null Xiewenyi, Ying Nie, Junfeng Wang, Zhiming Zheng, Dawei Yin, Hainan Zhang

Green & Sustainable NLP

Challenge:	Existing whole-page reranking methods require large-scale expert annotations to achieve high-quality results.
Approach:	They propose a whole-page reranking framework that converts single-modal rankers into page-level guidance by constructing budget-aware candidates for cross-modal annotations and distilling intra-modality preferences to align relevance scales across modalities.
Outcome:	The proposed framework reduces annotation costs by 70-90% while outperforming fully-annotated reranking baselines.

MOBA-E2C: Generating MOBA Game Commentaries via Capturing Highlight Events from the Meta-Data (2022.findings-emnlp)

Copied to clipboard

Dawei Zhang, Sixing Wu, Yao Guo, Xiangqun Chen

Challenge:	e-sports game competitions lack commentators because of the shortage of professional human commentators.
Approach:	They propose a data-driven MOBA commentary generation framework for MOBA games . they use a rule-based generator and a generative GPT generator to generate commentaries .
Outcome:	The proposed model generates commentaries based on the game meta-data and a rule-based generator and generative GPT generator.

How does Attention Affect the Model? (2021.findings-acl)

Copied to clipboard

Cheng Zhang, Qiuchi Li, Lingyu Hua, Dawei Song

Explainability & Interpretability in NLP

Challenge:	Existing studies on the effectiveness of attention in NLP do not consider changes in semantic capability of different components.
Approach:	They propose a framework that exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic.
Outcome:	The proposed framework exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic.

Multi-level Contrastive Learning for Script-based Character Understanding (2023.emnlp-main)

Copied to clipboard

Dawei Li, Hengyuan Zhang, Yanran Li, Shiping Yang

Structural Bias for Aspect Sentiment Triplet Extraction (2022.coling-1)

Challenge:	Scripts are written text for plays, movies, or broadcasts.
Approach:	They propose a multi-level contrastive learning framework to capture characters’ global information in a fine-grained manner.
Outcome:	The proposed framework improves on three character understanding sub-tasks by a considerable margin.

Copied to clipboard

Chen Zhang, Lei Ren, Fang Ma, Jingang Wang, Wei Wu, Dawei Song

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression (2025.findings-emnlp)

Challenge:	Existing structural bias adapters for aspect sentiment triplet extraction are under-confident . a large-scale dataset for ASTE shows the adapter is effective and efficient to a larger scale.
Approach:	They propose to use a structural adapter to integrate structural bias into pretrained language models . they propose to add a relative position structure in place of the syntactic dependency structure .
Outcome:	The proposed adapter achieves state-of-the-art performance over strong baselines, but with a light parameter demand and low latency.

Copied to clipboard

Jiebin Zhang, Dawei Zhu, Yifan Song, Wenhao Wu, Chuqiao Kuang, Xiaoguang Li, Lifeng Shang, Qun Liu, Sujian Li

Challenge:	storing more tokens in the KV cache at lower precision can enhance the long-context performance of large language models.
Approach:	They propose a token-precision trade-off strategy to optimize KV cache compression . they also propose storing more tokens in the KV at lower precision .
Outcome:	The proposed method achieves an optimal point within the Information Bottleneck compared to standalone KV pruning or KV quantization.

PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization (2025.emnlp-demos)

Copied to clipboard

Dawei Xiang, Wenyan Xu, Kexin Chu, Tianqi Ding, Zixu Shen, Yiming Zeng, Jianchang Su, Wei Zhang

Low-Resource NLP

Challenge:	PromptSculptor automates the iterative prompt optimization process for Text-to-Image models . previous work focused on generating detailed, high-quality prompts based on user feedback .
Approach:	They propose a framework that decomposes a task into four specialized agents . they use Chain-of-Thought reasoning to transform a short, vague user prompt into a comprehensive, refined prompt.
Outcome:	The proposed framework significantly improves output quality and reduces iterations needed for user satisfaction.

AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning (2024.emnlp-main)

Copied to clipboard

Hao Sun, Jiayi Wu, Hengyi Cai, Xiaochi Wei, Yue Feng, Bo Wang, Shuaiqiang Wang, Yan Zhang, Dawei Yin

AFRIDOC-MT: Document-level MT Corpus for African Languages (2025.emnlp-main)

Challenge:	Recent advances in large language models have been remarkable . users face a choice between using cloud-based LLMs for generation quality or local-based ones for lower computational cost .
Approach:	They propose a new LLM utilization paradigm that facilitates collaborative operation . they evaluate AdaSwitch across 7 benchmarks and compare it to other LLMs .
Outcome:	The proposed model improves performance of local and cloud agents across 7 benchmarks . it achieves competitive results compared to the cloud agent while utilizing less computational overhead.

Copied to clipboard

Jesujoba Oluwadara Alabi, Israel Abebe Azime, Miaoran Zhang, Cristina España-Bonet, Rachel Bawden, Dawei Zhu, David Ifeoluwa Adelani, Clement Oyeleke Odoje, Idris Akinade, Iffat Maab, Davis David, Shamsuddeen Hassan Muhammad, Neo Putini, David O. Ademuyiwa, Andrew Caines, Dietrich Klakow

Multilinguality

Challenge:	AFRIDOC-MT is a document-level multi-parallel translation dataset covering five languages . AFRITIC-MT models perform better on sentences than general-purpose LLMs .
Approach:	They propose a document-level multi-parallel translation dataset covering English and five African languages.
Outcome:	The proposed dataset covers 334 health and 271 information technology news documents . it shows that NLLB-200 achieves the best average performance among standard models .

Sparse Teachers Can Be Dense with Knowledge (2022.emnlp-main)

Copied to clipboard

Yi Yang, Chen Zhang, Dawei Song

Green & Sustainable NLP

Challenge:	Existing methods for transferring knowledge from a teacher of large scale to a student of smaller scale are limiting in overall knowledgeableness.
Approach:	They propose a sparse teacher trick to remove over-parameterized teachers that produce student-unfriendly knowledge and thus limit overall knowledgeableness.
Outcome:	The proposed trick removes the parameters that result in student-unfriendliness and leads to compelling performance in comparison with baselines.

EvoNarrator: Modeling Scientific Evolution for Feasible Hypothesis Generation (2026.acl-long)

Copied to clipboard

Xiaoying Le, Pengfei Qian, Yuanzhao Zhai, Xu Zhang, Qian Liu, Feng Dawei, Bo Ding

Challenge:	Scientific discovery evolution does not occur ex nihilo but is characterized by structural deepening and reconfiguration of existing functionalities.
Approach:	They propose a framework for hypothesis generation based on evolutionary narratives . they extract structured P-M-L-F quadruples from citation networks and introduce a mechanism to assess their semantic compatibility.
Outcome:	The proposed framework reduces logical disconnects by evaluating its semantic compatibility.

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) (2024.findings-acl)

Copied to clipboard

Shenglai Zeng, Jiankun Zhang, Pengfei He, Yiding Liu, Yue Xing, Han Xu, Jie Ren, Yi Chang, Shuaiqiang Wang, Dawei Yin, Jiliang Tang

Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task (2022.coling-1)

Challenge:	Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model generation with proprietary and private data, where data privacy is . a privacy issue that is currently under-explored, is posed by RAG.
Approach:	They propose to use retrieval-augmented generation (RAG) to facilitate language model generation with proprietary and private data where data privacy is a pivotal concern.
Outcome:	The proposed attack methods demonstrate that RAG can mitigate the old risks, i.e., leakage of the LLMs’ training data.

Copied to clipboard

Liang Wen, Juan Li, Houfeng Wang, Yingwei Luo, Xiaolin Wang, Xiaodong Zhang, Zhicong Cheng, Dawei Yin

Controllable Text Generation with Residual Memory Transformer (2024.findings-acl)

Challenge:	Existing answer selection approaches for community question answering lack additional answer summaries due to redundancy and lengthiness issues of crowdsourced answers.
Approach:	They constructed a dataset which contains a corresponding reference summary for each original lengthy answer.
Outcome:	The proposed model improves the performance of a question and candidate answer on a WikiHowQA dataset.

Copied to clipboard

Hanqing Zhang, Si Sun, Haiming Wu, Dawei Song

Adaptive Parameterization for Neural Dialogue Generation (D19-1)

Challenge:	Large-scale Causal Language Models (CLMs) have been successful in text generation, but there is still a challenge to control the generation process.
Approach:	They propose a non-intrusive, lightweight control plugin to control the generation process of a CLM at arbitrary time steps.
Outcome:	The proposed plugin can handle any type of control conditions and cooperate with the base CLM through a residual learning paradigm.

Copied to clipboard

Hengyi Cai, Hongshen Chen, Cheng Zhang, Yonghao Song, Xiaofang Zhao, Dawei Yin

C3KG: A Chinese Commonsense Conversation Knowledge Graph (2022.findings-acl)

Challenge:	Existing models of open-domain dialogue generate responses based on sequence-to-sequence paradigms.
Approach:	They propose an Adaptive Neural Dialogue generation model which manages various conversations with conversation-specific parameterization.
Outcome:	The proposed model performs better on a large-scale conversational dataset.

Copied to clipboard

Dawei Li, Yanran Li, Jiayi Zhang, Ke Li, Chen Wei, Jianwei Cui, Bin Wang

Natural Language Interfaces

Challenge:	Existing commonsense knowledge bases organize tuples in an isolated manner, causing problems for chatbots .
Approach:	They create a Chinese commonsense conversation knowledge graph which integrates social commonsensm and dialog flow information.
Outcome:	The proposed graph incorporates social commonsense knowledge and dialog flow information.

Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards (2025.emnlp-main)

Copied to clipboard

Xiaolong Wei, Bo Lu, Xingyu Zhang, Zhejun Zhao, Dongdong Shen, Long Xia, Dawei Yin

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)

Challenge:	Existing methods for enhancing Large Language Models (LLMs) struggle with novelty and Reinforcement Learning from human feedback (RLHF) is costly.
Approach:	They propose to use a Reward Model (RM) and a principle-guided LLM-as-a-Judge to enhance creative output over baselines.
Outcome:	The proposed approach significantly enhances creative output over baselines, but the principle-guided LLM-as-a-Judge yields superior generation quality.

Copied to clipboard

Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou

BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment (2025.naacl-long)

Challenge:	Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling.
Approach:	They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation.
Outcome:	The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes.

Copied to clipboard

Sizhe Wang, Yongqi Tong, Hengyuan Zhang, Dawei Li, Xin Zhang, Tianlong Chen

Challenge:	Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years.
Approach:	They propose a method to balance the number of prompts and responses to improve knowledge breadth and knowledge depth by introducing gradient-based clustering to estimate the knowledge informativeness and usefulness of each augmented sample.
Outcome:	The proposed method outperforms baseline methods while maintaining training efficiency.

Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model (2022.coling-1)

Copied to clipboard

Sixing Wu, Ying Li, Ping Xue, Dawei Zhang, Zhonghai Wu

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection (2024.emnlp-main)

Challenge:	Pre-trained language models can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding.
Approach:	They propose a two-stage framework to integrate a linearized knowledge into plan text using a ranking network PriorRanking to estimate the relevance of a retrieved knowledge fact.
Outcome:	The proposed framework improves the performance of pre-trained language models by using section-aware strategies to encode the linearized knowledge.

Copied to clipboard

Hao Sun, Hengyi Cai, Bo Wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Information Retrieval

Challenge:	Large language models (LLMs) often produce factually incorrect information, also known as hallucination.
Approach:	They propose a framework for verifiable text generation with evolving memory and self-reflection that incorporates long-term memory to retain documents and recent documents.
Outcome:	The proposed framework outperforms baselines on five datasets across three knowledge-intensive tasks.

Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model (2024.findings-acl)

Copied to clipboard

Hengyuan Zhang, Yanru Wu, Dawei Li, Sak Yang, Rui Zhao, Yong Jiang, Fei Tan

Task-agnostic Distillation of Encoder-Decoder Language Models (2024.lrec-main)

Challenge:	Aligned Large Language Models exhibit remarkable versatility, capable of handling diverse real-world tasks.
Approach:	They propose a coarse to fine framework to fine-tune aligned Large Language Models to achieve a balance between speciality and versatility.
Outcome:	The proposed framework outperforms baseline methods across diverse tasks and model scales.

Copied to clipboard

Chen Zhang, Yang Yang, Qiuchi Li, Jingang Wang, Dawei Song

Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding (2023.emnlp-main)

Challenge:	Existing distillation methods that focus on encoder-only LMs fail to handle the distillation of encoder decoder LM.
Approach:	They propose a method that finetunes pretrained language models (LMs) they propose 'MiniEnD' that allows for task-agnostic distillation of LMs.
Outcome:	The proposed distillation method is generally effective and competitive compared to other alternatives.

Copied to clipboard

Taolin Zhang, Ruyao Xu, Chengyu Wang, Zhongjie Duan, Cen Chen, Minghui Qiu, Dawei Cheng, Xiaofeng He, Weining Qian

MoDification: Mixture of Depths Made Easy (2025.naacl-long)

Challenge:	Existing methods for pre-training KEPLMs with relational triples are difficult to adapt to close domains due to the lack of sufficient domain graph semantics.
Approach:	They propose a Knowledge-enhanced language representation learning framework for various closed domains that captures the implicit graph structure among the entities.
Outcome:	The proposed framework outperforms existing methods for pre-training KEPLMs in closed domains significantly.

Copied to clipboard

Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song

Green & Sustainable NLP

Challenge:	Long-context efficiency is a trending topic in large language model (LLM) serving.
Approach:	They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory.
Outcome:	The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications.

RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)

Copied to clipboard

Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong yu

XPrompt: Exploring the Extreme of Prompt Tuning (2022.emnlp-main)

Challenge:	Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says .
Approach:	They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions.
Outcome:	a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures .

Copied to clipboard

Fang Ma, Chen Zhang, Lei Ren, Jingang Wang, Qifan Wang, Wei Wu, Xiaojun Quan, Dawei Song

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding (2026.acl-long)

Challenge:	Prompt tuning learns soft prompts to condition pre-trained Language Models for performing downstream tasks in a parameter-efficient manner.
Approach:	They propose a Prompt tuning model with an eXtremely small scale that learns soft prompts to condition the frozen Pre-trained Language Models for performing downstream tasks in a parameter-efficient manner.
Outcome:	The proposed model outperforms the vanilla Prompt-Tuning and can significantly improve across tasks and model scales.

Copied to clipboard

Shuang Cheng, Yuhua Jiang, Zineng Zhou, Dawei Liu, Tao Wang, Linfeng Zhang, Biqing Qi, Bowen Zhou

ConFiguRe: Exploring Discourse-level Chinese Figures of Speech (2022.coling-1)

Challenge:	Existing block-wise discrete diffusion models lack robust autoregressive (AR) decoders.
Approach:	They propose a block-wise discrete diffusion framework for large-scale vision-language understanding with a progressive beta noise curriculum.
Outcome:	The proposed framework improves training efficiency, convergence stability, and task performance over conventional block diffusion.

Copied to clipboard

Dawei Zhu, Qiusi Zhan, Zhejian Zhou, Yifan Song, Jiebin Zhang, Sujian Li

Speech & Audio in NLP

Challenge:	Figures of speech often deviate from their literal meanings to express deeper semantic implications.
Approach:	They propose a concept of figurative unit, which is the carrier of a figure, and build a Chinese corpus for Contextualized Figure Recognition.
Outcome:	The proposed model is based on 12 types of figures commonly used in Chinese . it shows that the proposed tasks are challenging for existing models .

LawBench: Benchmarking Legal Knowledge of Large Language Models (2024.emnlp-main)

Copied to clipboard

Zhiwei Fei, Xiaoyu Shen, Dawei Zhu, Fengzhe Zhou, Zhuo Han, Alan Huang, Songyang Zhang, Kai Chen, Zhixin Yin, Zongwen Shen, Jidong Ge, Vincent Ng

Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice? (2024.emnlp-main)

Challenge:	LegalBench evaluated 20 LLMs in 162 legal tasks in 20 countries and jurisdictions.
Approach:	They present a comprehensive evaluation of 21 popular Large Language Models and the first comparative analysis of the empirical results.
Outcome:	The proposed benchmarks are based on the Bloom’s cognitive taxonomy and are compared to 21 popular LLMs.

Copied to clipboard

Dawei Zhu, Pinzhen Chen, Miaoran Zhang, Barry Haddow, Xiaoyu Shen, Dietrich Klakow

A Multi-task Learning Framework for Opinion Triplet Extraction (2020.findings-emnlp)

Challenge:	Traditionally, success in multilingual machine translation depends on large volume, diverse directions, and high quality of training data.
Approach:	They revisit the importance of large language models for translation by fine-tuning on 32 parallel sentences.
Outcome:	The proposed model can be fine-tuned on as few as 32 parallel sentences . however, the choice of direction is critical to avoid misinterpretation, the authors say .

Copied to clipboard

Chen Zhang, Qiuchi Li, Dawei Song, Benyou Wang

Minimal Distillation Schedule for Extreme Language Model Compression (2024.findings-eacl)

Challenge:	Existing approaches to Aspect-based sentiment analysis (ABSA) use aspect terms and their corresponding sentiment polarities as a reference, but they lack opinion terms as .
Approach:	They propose a multi-task learning framework to extract aspect terms and opinion terms and parse their sentiment dependencies with a biaffine scorer.
Outcome:	The proposed framework outperforms baseline and state-of-the-art approaches on four SemEval benchmarks.

Copied to clipboard

Chen Zhang, Yang Yang, Qifan Wang, Jiahao Liu, Jingang Wang, Wei Wu, Dawei Song

Lifting the Curse of Capacity Gap in Distilling Language Models (2023.acl-long)

Challenge:	Existing methods for teacher assistant-based distillation require multiple trials to find the optimal teacher assistant.
Approach:	They propose a method that allows scheduling of an optimal teacher assistant in just one trial . they show that student performance is positively correlated with the scale-performance tradeoff .
Outcome:	The proposed method can select the optimal teacher assistant in just one trial . it can be used to compare performance of student and teacher assistants on GLUE benchmarks.

Copied to clipboard

Chen Zhang, Yang Yang, Jiahao Liu, Jingang Wang, Yunsen Xian, Benyou Wang, Dawei Song

KSAM: Infusing Multi-Source Knowledge into Dialogue Generation via Knowledge Source Aware Multi-Head Decoding (2022.findings-acl)

Challenge:	Existing studies have shown that pretrained language models require a tremendous amount of inference compute to perform.
Approach:	They propose to compress pretrained language models to small ones with a teacher-student paradigm to fill the capacity gap.
Outcome:	The proposed model achieves state-of-the-art performance at small FLOPs compared with competitive baselines.

Copied to clipboard

Sixing Wu, Ying Li, Dawei Zhang, Zhonghai Wu

Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization (2025.emnlp-main)

Challenge:	Existing knowledge-enhanced methods only seek knowledge from a single source, resulting in insufficient coverage of a given knowledge source.
Approach:	They propose to use multiple independent decoder heads to infuse multi-source knowledge into dialogue generation more efficiently by incorporating external knowledge into the dialogue generation.
Outcome:	The proposed approach overcomes three challenges in infusing multi-source knowledge into dialogue generation more efficiently.

Copied to clipboard

Jiulong Wu, Zhengliang Shi, Shuaiqiang Wang, Jizhou Huang, Dawei Yin, Lingyong Yan, Min Cao, Min Zhang

Multimodality

Challenge:	Existing preference alignment methods focus on aligning model responses with human preferences while neglecting image-text modality alignment.
Approach:	They propose Entity-centric Multimodal Preference Optimization to improve modality alignment . they use open-source instruction datasets to automatically construct high-quality preference data .
Outcome:	The proposed approach reduces hallucination rates by 80.4% on Object HalBench and 52.6% on MM HalBech.

Beyond Emotion: A Multi-Modal Dataset for Human Desire Understanding (2022.naacl-main)

Copied to clipboard

Ao Jia, Yu He, Yazhou Zhang, Sagar Uprety, Dawei Song, Christina Lioma

Multimodality

Challenge:	Desire is a primitive instinct and a need for strongly expressing human desires to get or possess something.
Approach:	They propose to use MSED to model and understand human desire . they propose to provide a benchmark for human desire analysis .
Outcome:	The proposed dataset contains 9,190 text-image pairs with English text.

Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness (2020.acl-main)

Copied to clipboard

Sixing Wu, Ying Li, Dawei Zhang, Yang Zhou, Zhonghai Wu

PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation (2022.emnlp-industry)

Challenge:	Generative dialogue systems tend to produce generic and boring responses, causing boring conversations . a novel commonsense knowledge-aware dialogue generation model is proposed to solve this problem .
Approach:	They propose to retrieve and introduce knowledge facts from knowledge graphs to reduce boring conversations . they use a Felicitous Fact mechanism to help the model focus on context-relevant knowledge facts .
Outcome:	The proposed model outperforms the state-of-the-art approach in most experiments.

Copied to clipboard

Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan, Daiting Shi, Yi Wu, Zhicong Cheng, Simiu Gu, Dawei Yin

The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models (2024.emnlp-main)

Challenge:	Pre-trained language models have been a key part of ranking systems . knowledge distillation is widely used to maintain high performance while keeping efficient computations.
Approach:	They propose an algorithm to combine knowledge from multi-teachers and label information to achieve competitive performance in offline and online experiments.
Outcome:	The proposed method has been deployed in a real-world commercial search system.

Copied to clipboard

Yanjun Chen, Dawei Zhu, Yirong Sun, Xinghao Chen, Wei Zhang, Xiaoyu Shen

Enhancing Metaphor Detection by Gloss-based Interpretations (2021.findings-acl)

Challenge:	Reinforcement Learning from Human Feedback (RLHF) significantly enhances Natural Language Processing by aligning language models with human expectations.
Approach:	They propose to integrate feedback from humans into RLHF to improve language models by capturing human-like preferences.
Outcome:	The proposed model outperforms models trained with moderately accurate reward models on relevance, factuality, and completeness tasks.

Copied to clipboard

Hai Wan, Jinxia Lin, Jianfeng Du, Dawei Shen, Manrong Zhang

AnchorCoT: Anchors Pave the Way for Multi-hop Reasoning (2025.findings-acl)

Challenge:	Existing approaches to metaphor detection are limited by ambiguous meanings of metaphorical substitute words.
Approach:	They propose a model that utilizes glosses to interpret metaphorical words by enhancing three datasets with gloss annotations.
Outcome:	The proposed model outperforms state-of-the-art models on three enhanced datasets and that gloss-based interpretation benefits metaphor detection.

Copied to clipboard

Tianshi Ming, Xian Wu, Yingying Zhang, Zichuan Fu, Dawei Cheng

Natural Language Interfaces

Challenge:	Large language models (LLMs) have demonstrated potential reasoning capabilities through prompt design, such as the Chain of Thought (CoT).
Approach:	They propose a new reasoning approach that predicts key entities which work as important “anchors” and employs a ranking algorithm to ensure the logical sequence of the predicted answers.
Outcome:	The proposed approach outperforms existing methods in multi-hop question reasoning and provides more accurate reasoning results in multihop question answering tasks.

InternLM-Law: An Open-Sourced Chinese Legal Large Language Model (2025.coling-main)

Copied to clipboard

Zhiwei Fei, Songyang Zhang, Xiaoyu Shen, Dawei Zhu, Xiao Wang, Jidong Ge, Vincent Ng

PsyPath: Psychologically-guided Self-Exploration for Personality Detection (2026.findings-acl)

Challenge:	InternLM-Law is a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws.
Approach:	They introduce a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws.
Outcome:	The proposed model performs better than existing models in a variety of legal tasks related to Chinese laws.

Copied to clipboard

Zheng Li, Hongxin Ding, Chenyu Zhang, Weimin Xiong, Dawei Zhu, Sujian Li

Bi-DCSpell: A Bi-directional Detector-Corrector Interactive Framework for Chinese Spelling Check (2024.findings-emnlp)

Challenge:	Personality detection aims to label traits via identifying linguistic cues from written text.
Approach:	They propose a framework that allows large language models to generate and answer psychologically meaningful questions and a hybrid scoring mechanism to evaluate the generated nodes in the reasoning paths.
Outcome:	The proposed framework outperforms baselines on two benchmark datasets and significantly improves performance and interpretability in downstream tasks.

Copied to clipboard

Haiming Wu, Hanqing Zhang, Richeng Xuan, Dawei Song

Text Error Correction

Challenge:	Chinese Spelling Check (CSC) aims to detect and correct potentially misspelled characters in Chinese sentences.
Approach:	They propose a bi-directional Detector-Corrector framework for Chinese Spelling Check which mutually enhances the feature representation for detection and correction subtasks.
Outcome:	The proposed framework reduces the risk of over-correction and under-corrections while preserving the knowledge learnt from correction.

More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge (2021.emnlp-main)

Copied to clipboard

Sixing Wu, Ying Li, Minghui Wang, Dawei Zhang, Yang Zhou, Zhonghai Wu

GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillation (2024.emnlp-industry)

Challenge:	Existing knowledge-enhanced methods use a single-source homogeneous knowledge base with limited knowledge coverage.
Approach:	They propose a multi-source heterogeneous knowledge-enhanced dialogue generation model that leverages multiple knowledge sources to improve knowledge coverage.
Outcome:	The proposed model outperforms existing knowledge-enhanced models on a Chinese dataset and shows that it can leverage multiple heterogeneous knowledge sources to improve knowledge coverage.

Copied to clipboard

Wenjie Zhou, Zhenxin Ding, Xiaodong Zhang, Haibo Shi, Junfeng Wang, Dawei Yin

Making Pretrained Language Models Good Long-tailed Learners (2022.emnlp-main)

Challenge:	Pre-trained language models have achieved remarkable performance in OpenQA, but for practical deployment, knowledge distillation is crucial to maintain high performance while operating under computational constraints.
Approach:	They propose an algorithm to perform unsupervised knowledge distillation without the guidance of labels to achieve 99.5% of performance.
Outcome:	The proposed algorithm achieves 99.5% of performance in a commercial question-answering system.

Copied to clipboard

Chen Zhang, Lei Ren, Jingang Wang, Wei Wu, Dawei Song

Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks (D19-1)

Challenge:	Prompt-tuning has shown appealing performance in few-shot classification . however, it is less promising in long-tailed classification due to long tail .
Approach:	They propose to use prompt-tuning to make pretrained language models at least good long-tailed learners by bridging the gap between prompt- and commonly used finetun.
Outcome:	The proposed method makes pretrained language models at least good long-tailed learners, bridging the gap between prompt-tuning and finetunation.

Copied to clipboard

Chen Zhang, Qiuchi Li, Dawei Song

Exploiting Position Bias for Robust Aspect Sentiment Classification (2021.findings-acl)

Challenge:	Existing aspects-based sentiment classification models lack a mechanism to account for relevant syntactical constraints and word dependencies.
Approach:	They propose to build a Graph Convolutional Network over the dependency tree of a sentence to exploit syntactical information and word dependencies.
Outcome:	The proposed model is comparable to state-of-the-art models on three benchmarking collections.

Copied to clipboard

Fang Ma, Chen Zhang, Dawei Song

HL-EncDec: A Hybrid-Level Encoder-Decoder for Neural Response Generation (C18-1)

Challenge:	Aspect sentiment classification models suffer from the issue of robustness when domains of test and training data are different or test data is adversarially perturbed.
Approach:	They propose two mechanisms for capturing position bias to reduce the probability of mis-attending . they propose position-biased weight and position-based dropout to enhance existing models .
Outcome:	The proposed approaches improve the robustness and effectiveness of existing models.

Copied to clipboard

Sixing Wu, Dawei Zhang, Ying Li, Xing Xie, Zhonghai Wu

Text Generation

Challenge:	Existing models for conversation systems operate sentences at word-level . word-based models suffer from Unknown Words Issue and Preference Issue .
Approach:	They propose a hybrid-level Encoder-Decoder model which utilizes word-level features and character-level ones.
Outcome:	The proposed model outperforms non-word-level models in automatic metrics and human annotations on a Chinese corpus.

Assessing “Implicit” Retrieval Robustness of Large Language Models (2024.emnlp-main)

Copied to clipboard

Xiaoyu Shen, Rexhina Blloshmi, Dawei Zhu, Jiahuan Pei, Wei Zhang

Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision (2025.findings-emnlp)

Challenge:	Retrieval-augmented generation (RAG) is a framework to enhance large language models with external knowledge, but its effectiveness is constrained by the retrieval robustness of the model.
Approach:	They propose to use gold and distracting context to fine-tune models to handle relevant or irrelevant retrieved context in an end-to-end manner.
Outcome:	The proposed model performs better when gold and distracting context are used, while still extracting correct answers when retrieval is accurate.

Copied to clipboard

Dawei Zhu, Xiyu Wei, Guangxiang Zhao, Wenhao Wu, Haosheng Zou, Junfeng Ran, null XWang, Lin Sun, Xiangzheng Zhang, Sujian Li