Papers by Dong Zhu

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis (2026.findings-acl)

Challenge:	Cross-modal retrieval tasks are used to retrieve data from one modality or another based on a query from another modality.
Approach:	They propose a generative cross-modal retrieval framework based on coarse-to-fine semantic modeling . they propose combining K-Means and RQ-VAE to discretize multimodal data into token sequences that support autoregressive generation.
Outcome:	The proposed framework achieves excellent performance and efficiency in multimodal retrieval tasks.

Copied to clipboard

Xiaoshuai Song, Haofei Chang, Guanting Dong, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou

Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent (2025.findings-acl)

Challenge:	Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but access to real systems is often restricted and manually built sandboxes are hard to scale.
Approach:	They propose an automated framework for scalable tool-interaction environments via programmatic synthesis that synthesizes 191 environments and about 7K scenarios and applies them to Supervised Fine-Tuning and Reinforcement Learning for Qwen3 series models.
Outcome:	The proposed framework significantly improves LLMs’ ability to solve tasks in complex environments involving multi-turn, multi-tool interactions.

Copied to clipboard

Xueyang Feng, Jingsen Zhang, Jiakai Tang, Wei Li, Guohao Cai, Xu Chen, Quanyu Dai, Yue Zhu, Zhenhua Dong

Learning When to Translate for Streaming Speech (2022.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have propelled the development of Conversational Recommendation Agents (CRAs).
Approach:	They propose a multi-turn preference optimization paradigm that leverages Expectation Confirmation Theory to explicitly model the evolution of user satisfaction throughout multi-turned dialogues.
Outcome:	The proposed paradigm eliminates the significant sampling overhead of existing MTPO methods while ensuring the optimization process drives meaningful improvements.

Copied to clipboard

Qian Dong, Yaoming Zhu, Mingxuan Wang, Lei Li

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching (2026.findings-acl)

Challenge:	Existing methods waiting-and-translating for a fixed duration break speech acoustic units . Existing models waiting-for a set duration and generating partial sentences are not effective .
Approach:	They propose a monotonic segmentation module inside an encoder-decoder model to detect proper speech unit boundaries for a streaming speech input.
Outcome:	The proposed method outperforms existing methods on a speech translation dataset and achieves the best trade-off between translation quality and latency.

Copied to clipboard

Han Zhu, Wei Kang, Liyong Guo, Zengwei Yao, Fangjun Kuang, Weiji Zhuang, Zhaoqing Li, Zhifeng Han, Dong Zhang, Xin Zhang, Xingchen Song, Lingxuan Ye, Long Lin, Daniel Povey

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Challenge:	Existing autoregressive models for dialogue generation suffer from high latency and stability issues.
Approach:	They propose a non-autoregressive (NAR) zero-shot spoken dialogue generation model based on flow-matching.
Outcome:	The proposed model outperforms existing models in speech generation due to poor speech intelligibility and turn-taking precision.

Copied to clipboard

Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang

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

Challenge:	Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach:	They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome:	The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.

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

Information Extraction & Text Mining

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.

MINER: Multi-Interest Matching Network for News Recommendation (2022.findings-acl)

Copied to clipboard

Jian Li, Jieming Zhu, Qiwei Bi, Guohao Cai, Lifeng Shang, Zhenhua Dong, Xin Jiang, Qun Liu

Representation Learning

Challenge:	Existing methods learn a single user embedding from user’s historical behaviors to represent the reading interest.
Approach:	They propose a poly attention scheme to learn multiple interest vectors for each user, which encodes the different aspects of user interest.
Outcome:	The proposed approach significantly outperforms existing state-of-the-art methods on the MIND news recommendation benchmark.

SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis (2025.coling-main)

Copied to clipboard

Senbin Zhu, ChenYuan He, Hongde Liu, Pengcheng Dong, Hanjie Zhao, Yuchen Yan, Yuxiang Jia, Hongying Zan, Min Peng

Low-Resource NLP

Challenge:	Currently, most sentiment analysis corpora use sequence-level annotation.
Approach:	They propose a two-stage approach to financial entity-level sentiment analysis called Self-aware In-context Learning Correction.
Outcome:	The proposed approach achieves state-of-the-art on the largest English and Chinese financial entity-level sentiment analysis datasets to date.

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

Copied to clipboard

Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang

Programming Languages in NLP

Challenge:	Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach:	They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome:	The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.

Multimodal Dual-Path Decoding for Medical Report Generation (2026.findings-acl)

Copied to clipboard

Jinghan Sun, Dong Wei, Zhihong Zhu, Yuyang Xue, Steven McDonagh, Xian Wu

SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models (2026.acl-long)

Challenge:	Current methods for radiology report generation rely on encoder-decoder based frameworks that fail to integrate multimodal clinical evidence with domain-specific knowledge.
Approach:	They propose a multimodal dual-path framework that synergistically integrates large vision-language models and large language models for radiology report generation.
Outcome:	The proposed framework improves on the public MIMIC-CXR benchmark and shows that it is superior to state-of-the-art models.

Copied to clipboard

Binxian Su, Haoye Lou, Shucheng Zhu, Weikang Wang, Ying Liu, Dong Yu, Pengyuan Liu

Learning to Ask Unanswerable Questions for Machine Reading Comprehension (P19-1)

Challenge:	Large language models (LLMs) are being used in urban planning but there is concern that they reproduce or amplify such biases.
Approach:	They propose a framework to evaluate spatial gender bias in large language models . they use a taxonomy of 62 urban micro-spaces, a prompt library and three diagnostic layers .
Outcome:	The proposed framework identifies structured gender-space associations that go beyond the public-private divide, forming nuanced micro-level mappings.

Copied to clipboard

Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu

Low-Resource NLP

Challenge:	Existing models for extractive reading comprehension are not good at deciding whether no answer is presented in the context.
Approach:	They propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question paired with its corresponding paragraph that contains the answer.
Outcome:	The proposed model performs better on the SQuAD 2.0 dataset than the baseline model and the BERT-large model.

Revisiting Interpolation Augmentation for Speech-to-Text Generation (2024.findings-acl)

Copied to clipboard

Chen Xu, Jie Wang, Xiaoqian Liu, Qian Dong, Chunliang Zhang, Tong Xiao, JingBo Zhu, Dapeng Man, Wu Yang

Text Generation

Challenge:	Existing approaches to speech-to-text generation tasks are limited by the lack of extensive labeled datasets.
Approach:	They propose to use interpolation augmentation to construct virtual training samples by transforming inputs and labels to enhance generalization in other domains.
Outcome:	The proposed approach significantly improves performance across diverse tasks, architectures, and data scales, offering a promising avenue for more robust S2T systems in resource-constrained settings.

Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model (2024.eacl-long)

Copied to clipboard

Andrew Brown, Jiading Zhu, Mohamed Abdelwahab, Alec Dong, Cindy Wang, Jonathan Rose

Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding (2026.acl-long)

Challenge:	Motivational Interviewing (MI) is a counselling technique used to guide people towards behaviour change.
Approach:	They propose a method for distilling reflections from a foundational language model into smaller models that can be owned and controlled.
Outcome:	The proposed method achieves 100% success rate on hold-out test set and 90% on the GPT-2 XL.

Copied to clipboard

Wenqing Hou, Hongkui Tu, Ye Wang, Yue Zhang, Yuying Liu, Dong Zhu, Liqun Gao, Bin Zhou

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection (2025.findings-acl)

Challenge:	Existing methods for identifying harmful memes rely on modal alignment or black-box classifiers . BPDMoE-Hate provides visual explanations for viewpoint selection and hierarchical structuring .
Approach:	They propose a framework that conceptualizes harmful meme detection as a process of "viewpoint decoupling and hierarchical fusion" they propose BPDMoE-Hate, which generates adversarial binary perspectives via VLMs and incorporates an adaptive viewpoint gating to facilitate viewpoint selection.
Outcome:	The proposed framework surpasses existing methods in performance and provides visual explanations for viewpoint selection and hierarchical structuring.

Copied to clipboard

Jiaqi Li, Xinyi Dong, Yang Liu, Zhizhuo Yang, Quansen Wang, Xiaobo Wang, Song-Chun Zhu, Zixia Jia, Zilong Zheng

Hierarchical Document Refinement for Long-context Retrieval-augmented Generation (2025.acl-long)

Challenge:	ReflectEvo-460k is a large-scale, comprehensive, self-generated reflection dataset with broadened instructions and diverse multi-domain tasks.
Approach:	They propose a pipeline that iteratively generates self-reflection for self-training and a large-scale reflection dataset with broadened instructions and diverse multi-domain tasks.
Outcome:	The proposed pipeline improves Llama-3 reasoning ability by up to 71.2% and Mistral by upto 44.4%.

Copied to clipboard

Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, Zhicheng Dou

Information Retrieval

Challenge:	Real-world RAG applications often encounter long-context input scenarios where redundant information and noise results in higher inference costs and reduced performance.
Approach:	They propose an efficient plug-and-play refiner that leverages the structural characteristics of long documents.
Outcome:	Experiments on seven QA datasets show that LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to baseline.

Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner (2022.findings-naacl)

Copied to clipboard

Danilo Neves Ribeiro, Shen Wang, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henghui Zhu, Xinchi Chen, Peng Xu, Zhiheng Huang, Andrew Arnold, Dan Roth

Question Answering

Challenge:	Large language models have achieved high performance on various natural language benchmarks, but the explainability of their output remains elusive.
Approach:	They propose an architecture called iterative retrieval-generation reasoner that generates an entailment tree that explains a given hypothesis by using premises from C.
Outcome:	The proposed model outperforms existing benchmarks on premise retrieval and entailment tree generation with around 300% gain in overall correctness.

FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models (2026.acl-long)

Copied to clipboard

Kehan Jiang, Haonan Dong, Zhaolu Kang, Zhengzhou Zhu, Guojie Song

Search-o1: Agentic Search-Enhanced Large Reasoning Models (2025.emnlp-main)

Challenge:	Recent Large Reasoning Models (LRMs) have demonstrated remarkable success in complex reasoning tasks.
Approach:	They propose a self-guided efficient reasoning framework that reduces FoE by pruning subs.
Outcome:	The proposed model outperforms eight competitive baselines while reducing token consumption by 37.7% 70.4%.

Copied to clipboard

Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, Zhicheng Dou

CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Challenge:	Large reasoning models (LRMs) have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning.
Approach:	They propose a framework that enhances large reasoning models with an agentic retrieval-augmented generation mechanism and a Reason-in-Documents module for refining retrieved documents.
Outcome:	The proposed framework enhances LRMs with an agentic retrieval-augmented generation mechanism and Reason-in-Documents module for refining retrieved documents.

Copied to clipboard

Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun, Yuhao Zhang, Murun Yang, Qianqian Dong, Tom Ko, Mingxuan Wang, Tong Xiao, Anxiang Ma, Jingbo Zhu

Machine Translation

Challenge:	End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach:	They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome:	The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity (2025.emnlp-main)

Copied to clipboard

Yu Zhang, Dong Guo, Fang Wu, Guoliang Zhu, Dian Ding, Yiming Zhang

Green & Sustainable NLP

Challenge:	Existing methods for large language models with extended context lengths face significant computational challenges during the prefill phase.
Approach:	They propose a difference-aware, dynamic sparse attention mechanism that efficiently identifies critical attention regions at a finer stripe granularity while adapting to global contextual information.
Outcome:	The proposed model achieves a speedup of 1.44 while maintaining higher recall rates.

Reason from Future: Reverse Thought Chain Enhances LLM Reasoning (2025.findings-acl)

Copied to clipboard

Yinlong Xu, Yanzhao Zheng, Shuoshuo Sun, Shuaihan Huang, Baohua Dong, Zhu Hangcheng, Ruohui Huang, Gang Yu, Hongxia Xu, Jian Wu

Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-main)

Challenge:	Existing reasoning paradigms that focus on local optimum reasoning lack global perspective.
Approach:	They propose a bidirectional reasoning paradigm that generates reasoning paths by bidirectional planning and bottom-up reasoning accumulation.
Outcome:	The proposed reasoning paradigm outperforms conventional paradigms with higher accuracy and less searching space to solve complex tasks.

Copied to clipboard

Zhenyu Lei, Zhen Tan, Song Wang, Yaochen Zhu, Zihan Chen, Yushun Dong, Jundong Li

YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Challenge:	Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data.
Approach:	They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students.
Outcome:	Experiments show that QR-Distill is superior to traditional methods.

Copied to clipboard

Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen

PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts (2023.findings-acl)

Challenge:	prevailing pre-training approaches for large language models involve several complexities.
Approach:	They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data .
Outcome:	The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data .

Copied to clipboard

Xiangjue Dong, Yun He, Ziwei Zhu, James Caverlee

Automated Generation of Accurate & Fluent Medical X-ray Reports (2021.emnlp-main)

Challenge:	Toward building more robust and reliable conversational systems, we introduce a prompt-based learning approach to automatically generate effective adversarial examples to probe DST models.
Approach:	They propose a prompt-based learning approach to automatically generate effective adversarial examples to probe DST models.
Outcome:	The proposed framework leads to the greatest reduction in accuracy and the best attack success rate while maintaining good fluency and a low perturbation ratio.

Copied to clipboard

Hoang Nguyen, Dong Nie, Taivanbat Badamdorj, Yujie Liu, Yingying Zhu, Jason Truong, Li Cheng

Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer (2024.acl-long)

Challenge:	Existing medical report generation efforts focus on producing human-readable reports, yet the generated text may not be well aligned to the clinical facts.
Approach:	They propose to automate the generation of medical reports from chest X-ray image inputs . medical reports are the primary medium, which physicians communicate findings from scans - authors say .
Outcome:	The proposed method achieves fluency and clinical accuracy on common metrics.

Copied to clipboard

Yongxin Zhu, Dan Su, Liqiang He, Linli Xu, Dong Yu

Speech & Audio in NLP

Challenge:	Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity.
Approach:	They propose a hierarchical transformer that quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a transformer architecture.
Outcome:	The proposed model outperforms existing speech language models in word error rate, speech quality, and speaker similarity.

MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Copied to clipboard

Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, Pengtao Xie

When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models (2026.acl-long)

Challenge:	telemedicine is a medical practice that provides patient care remotely using video conferencing tools.
Approach:	They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance .
Outcome:	The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues.

Copied to clipboard

Xuan Dong, Zhe Han, Tianhao Niu, Qingfu Zhu, Wanxiang Che

Robustness in NLP

Challenge:	Vision-Language-Action models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understood.
Approach:	They propose a step-wise inference-time intervention that aligns representations according to step language sensitivity, significantly improving performance under linguistic variation.
Outcome:	The proposed model significantly improves performance under linguistic variation under non-English instructions under language-agnostic steps.

RAG-Critic: Leveraging Automated Critic-Guided Agentic Workflow for Retrieval Augmented Generation (2025.acl-long)

Copied to clipboard

Guanting Dong, Jiajie Jin, Xiaoxi Li, Yutao Zhu, Zhicheng Dou, Ji-Rong Wen

Information Retrieval

Challenge:	Recent advances in large language models (LLMs) have demonstrated remarkable performance across a wide range of downstream tasks.
Approach:	They propose a framework that leverages a critic-guided agentic workflow to improve RAG capabilities autonomously.
Outcome:	The proposed framework improves RAG capabilities autonomously by leveraging a critic-guided agentic workflow.

NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons (2026.acl-long)

Copied to clipboard

Haonan Dong, Kehan Jiang, Haoran Ye, Wenhao Zhu, Zhaolu Kang, Guojie Song

ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models (2024.findings-acl)

Challenge:	Existing Large Reasoning Models (LRMs) lack explainability and controllability . Existing models target isolated levels without unification, while relying on RL .
Approach:	They propose an explainable, controllable, and unified reasoning framework driven by MoN.
Outcome:	The proposed framework achieves performance gains of 27.0% while reducing token consumption by 19.6% 63.3%.

Copied to clipboard

Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, Yifan Zhu, Anh Tuan Luu

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis (2024.findings-naacl)

Challenge:	Existing KBQA methods address inefficient knowledge retrieval and semantic parsing errors.
Approach:	They propose a generatethen-retrieve KBQA framework that generates logical form and replaces entities and relations with an unsupervised retrieval method to improve both generation and retrieval more directly.
Outcome:	Experimental results show that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and CWQ.

Copied to clipboard

Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, Lei Li

Evaluating Moral Beliefs across LLMs through a Pluralistic Framework (2024.findings-emnlp)

Challenge:	Existing studies show that large language models (LLMs) can handle multilingual machine translation (MMT) However, the multilingual translation ability of LLMs remains under-explored.
Approach:	They evaluate eight popular LLMs including ChatGPT and GPT-4 to determine their performance in multilingual machine translation.
Outcome:	The proposed model can generate moderate translation even on zero-resource languages and cross-lingual exemplars can provide better task guidance for low-resourced translation than exemplar in the same language pairs.

Copied to clipboard

Xuelin Liu, Yanfei Zhu, Shucheng Zhu, Pengyuan Liu, Ying Liu, Dong Yu

EffiQA: Efficient Question-Answering with Strategic Multi-Model Collaboration on Knowledge Graphs (2025.coling-main)

Challenge:	Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge.
Approach:	They propose a framework to evaluate the moral beliefs of four large language models . they use a dataset containing 472 moral choice scenarios in Chinese .
Outcome:	The proposed framework evaluates the moral beliefs of four large language models.

Copied to clipboard

Zixuan Dong, Baoyun Peng, Yufei Wang, Jia Fu, Xiaodong Wang, Xin Zhou, Yongxue Shan, Kangchen Zhu, Weiguo Chen

Structured Data in NLP

Challenge:	Existing approaches that integrate LLMs and KGs either underutilize the reasoning abilities of LLM or suffer from prohibitive computational costs due to tight coupling.
Approach:	They propose a framework that can strike a balance between performance and efficiency via an iterative paradigm.
Outcome:	The proposed framework can strike a balance between performance and efficiency via an iterative paradigm.

Enhancing Multimodal Unified Representations for Cross Modal Generalization (2025.findings-acl)

Copied to clipboard

Hai Huang, Yan Xia, Shengpeng Ji, Shulei Wang, Hanting Wang, Minghui Fang, Jieming Zhu, Zhenhua Dong, Sashuai Zhou, Zhou Zhao

Knowledge Graph-Enhanced Large Language Models via Path Selection (2024.findings-acl)

Challenge:	Existing studies on discrete unified representations overlook important distinctions between different dimensions of features.
Approach:	They propose to use a codebook to optimize unified representations from pretraining and fine- and coarse-grained disentangling to optimize the representations.
Outcome:	The proposed methods improve the interpretability of multimodal unified representations . they use training-free optimization of codebook and fine and coarse cross-modal disentangling .

Copied to clipboard

Haochen Liu, Song Wang, Yaochen Zhu, Yushun Dong, Jundong Li

Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective on Molecule Graphs (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) have shown unprecedented performance in various real-world applications, but they are known to generate factually inaccurate outputs.
Approach:	They propose a framework to integrate external knowledge extracted from Knowledge Graphs (KGs) they propose to generate scores for knowledge paths with input texts via latent semantic matching.
Outcome:	Experiments on real-world datasets validate the effectiveness of a framework to extract knowledge from Knowledge Graphs (KGs) incorporating external knowledge has become a promising strategy to improve the factual accuracy of LLM-generated outputs.

Copied to clipboard

Yinhan He, Zaiyi Zheng, Patrick Soga, Yaochen Zhu, Yushun Dong, Jundong Li

Data Augmentation with Adversarial Training for Cross-Lingual NLI (2021.acl-long)

Challenge:	Graph Neural Networks (GNNs) are successful in molecular property prediction tasks, but their outputs are often black-box and not easily understandable by humans.
Approach:	They propose a method to unleash the power of large language models (LLMs) to explain GNNs for molecular property prediction.
Outcome:	The proposed method uses autoencoder to generate the counterfactual graph topology from a set of counterfact text pairs based on an input graph.

Copied to clipboard

Xin Dong, Yaxin Zhu, Zuohui Fu, Dongkuan Xu, Gerard de Melo

AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives (2026.findings-acl)

Challenge:	Existing approaches to train cross-lingual models with labeled data are subpar, resulting in subpar results.
Approach:	They propose a data augmentation strategy that enriches data to reflect more diversity in a semantically faithful way and leverages adversarial training regimens to achieve greater robustness.
Outcome:	The proposed approach improves cross-lingual inference by leveraging the data to reflect more diversity in a semantically faithful way.

Copied to clipboard

Yanxi Chen, Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Xin Li, Peijie Qiu, Hao Wang, Xuanzhao Dong, Yujian Xiong, Anderson Schneider, Yuriy Nevmyvaka, Yalin Wang

ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment (2025.emnlp-main)

Challenge:	Large Audio-Language Models suffer from hallucinations, e.g., generating text not grounded in the audio input.
Approach:	They propose a framework to address hallucination problems in large audio-language models . they use a preference dataset to test the model's accuracy .
Outcome:	The proposed model outperforms the latest SOTA methods in terms of performance and generalization.

Copied to clipboard

Zhipeng Bian, Jieming Zhu, Qijiong Liu, Wang Lin, Guohao Cai, Zhaocheng Du, Jiacheng Sun, Zhou Zhao, Zhenhua Dong

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning (2026.findings-acl)

Challenge:	Large language models and diffusion models have opened new possibilities for AI-generated content . personalized cover image generation remains underexplored despite its critical role in boosting user engagement on digital platforms.
Approach:	They propose a framework that integrates MLLM-based prompting with personalized preference alignment to generate high-quality, contextually relevant covers.
Outcome:	The proposed framework improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy in downstream tasks.

Copied to clipboard

Xiwen Chen, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hao Wang, Haiyu Wu, Huayu Li, Aris Sotiras, Yalin Wang, Abolfazl Razi

FoldMoE: Efficient Long Sequence MoE Training via Attention-MoE Pipelining (2025.acl-long)

Challenge:	Existing methods for group-relative policy optimization rely on scalar correctness rewards that are often non-injective with respect to semantic content.
Approach:	They propose a framework that calibrates the reward signal using the semantic density of sampled groups.
Outcome:	The proposed framework outperforms strong baselines on five math benchmarks with 7,000 samples and 55 cost.

Copied to clipboard

Guichao Zhu, Lintian Lei, Yuhao Qing, Yichao Fu, Fanxin Li, Dong Huang, Zekai Sun, Heming Cui

Green & Sustainable NLP

Challenge:	Existing approaches to training LLMs with Mixture-of-Experts (MoE) architecture on long sequences are limited by the insufficient computation.
Approach:	They propose a MoE training system that enables token-level overlapping across entire Transformer blocks through novel attention-MoE pipelining.
Outcome:	The proposed system achieves 1.49x and 2.72x speedup over state-of-the-art token-level overlapping and non-overlapping baselines on GPT-MoE models with sequences up to 32K tokens.

Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks (2024.findings-acl)

Copied to clipboard

Wenyue Hua, Jiang Guo, Mingwen Dong, Henghui Zhu, Patrick Ng, Zhiguo Wang

AdaPrompt: Adaptive Model Training for Prompt-based NLP (2022.findings-emnlp)

Challenge:	Existing knowledge editing methods struggle to effectively propagate updates to interconnected facts, limiting the performance of reasoning tasks based on these updated facts.
Approach:	They propose a reasoning-based benchmark, ReCoE, which covers six common reasoning schemes in the real world.
Outcome:	The proposed reasoning-based benchmark shows that current models struggle to propagate updated knowledge within reasoning schemes.

Copied to clipboard

Yulong Chen, Yang Liu, Li Dong, Shuohang Wang, Chenguang Zhu, Michael Zeng, Yue Zhang

VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft (2024.findings-acl)

Challenge:	Prompt-based learning can tackle zero-shot and few-shot NLP tasks . authors propose a method that makes use of pre-trained language models .
Approach:	They propose to map NLP tasks into natural language prompts, which are then filled by pre-trained language models.
Outcome:	The proposed method outperforms standard prompt-based methods in few-shot settings.

Copied to clipboard

Yubo Dong, Xukun Zhu, Zhengzhe Pan, Linchao Zhu, Yi Yang

Structured Data in NLP

Challenge:	Multi-agent collaboration using LLMs is a challenging research topic that aims to enable multiple autonomous agents to coordinate their actions and achieve a common goal.
Approach:	They propose a benchmark for multi-agent collaboration in the Minecraft environment and introduce a Directed Acyclic Graph Multi-Agent Framework to resolve complex inter-ag dependencies.
Outcome:	The proposed framework outperforms existing ModelVerse, reducing hallucinations and improving task decomposition efficacy.

Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts (2025.naacl-long)

Copied to clipboard

Tong Zhu, Daize Dong, Xiaoye Qu, Jiacheng Ruan, Wenliang Chen, Yu Cheng

PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries (2025.naacl-long)

Challenge:	Mixture-of-Experts (MoE) models are constrained by their fixed model capacities when the number of tasks grows in instruction tuning.
Approach:	They propose to combine all training tasks and apply fixed sampling weights without considering the importance of different tasks as the model training state changes.
Outcome:	The proposed method can be used on knowledge & reasoning tasks and open-ended queries with limited training budget.

Copied to clipboard

Mingwen Dong, Nischal Ashok Kumar, Yiqun Hu, Anuj Chauhan, Chung-Wei Hang, Shuaichen Chang, Lin Pan, Wuwei Lan, Henghui Zhu, Jiarong Jiang, Patrick Ng, Zhiguo Wang

Programming Languages in NLP

Challenge:	Existing text-to-SQL systems focus on user questions with clear intentions that can be answered, but real user questions can be ambiguous with multiple interpretations or unanswerable due to a lack of relevant data.
Approach:	They construct a conversational text-to-SQL dataset called PRACTIQ, consisting of ambiguous and unanswerable questions inspired by real-world user questions.
Outcome:	The proposed system generates conversations with four turns, generating the user’s question, an assistant response seeking clarification, and the user's clarified SQL response with the natural language explanation of the execution results.

More than Text: Multi-modal Chinese Word Segmentation (2021.acl-short)

Copied to clipboard

Dong Zhang, Zheng Hu, Shoushan Li, Hanqian Wu, Qiaoming Zhu, Guodong Zhou

Co2PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning (2023.findings-emnlp)

Challenge:	Currently, word segmentation is performed in many languages without word delimiters.
Approach:	They propose to combine the multi-modality to perform Chinese word segmentation . they propose a time-dependent multi-module interactive model to integrate multi-modality information .
Outcome:	The proposed model integrates multi-modal information for word sequence labeling with Chinese language as target . the proposed model performs well on three training sets on Chinese and other languages without word delimiters.

Copied to clipboard

Xiangjue Dong, Ziwei Zhu, Zhuoer Wang, Maria Teleki, James Caverlee

RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation (2025.emnlp-main)

Challenge:	Pre-trained language models can encode unfair social biases from large pre-training corpora and even amplify biase in downstream applications.
Approach:	They propose a debias-while-prompt tuning method for mitigating biases via counterfactual contrastive prompt tuning on downstream tasks.
Outcome:	The proposed method can mitigate biases on three extrinsic bias benchmarks and adapt to existing debiased language models.

Copied to clipboard

Sashuai Zhou, Weinan Gan, Qijiong Liu, Ke Lei, Jieming Zhu, Hai Huang, Yan Xia, Ruiming Tang, Zhenhua Dong, Zhou Zhao

DecIF: Improving Instruction-Following through Decomposition (2026.acl-long)

Challenge:	Existing methods for addressing item-level user interests are lacking in cross-domain generalization . RecBase model is domain-agnostic and can be used to enhance recommender systems' effectiveness .
Approach:	They propose a domain-agnostic foundational model pretrained with a recommendation-oriented objective that leverages a large-scale, heterogeneous, cross-domain corpus with unified textual representations and feature mappings to enhance cross- domain generalization.
Outcome:	The proposed model matches or surpasses baselines in zero-shot and cross-domain recommendation tasks on eight real-world datasets.

Copied to clipboard

Tingfeng Hui, Pengyu Zhu, Bowen Ping, Ling Tang, Guanting Dong, Yaqi Zhang, Sen Su

Challenge:	Existing approaches to obtain high-quality instruction-following data rely heavily on existing documents and existing methods.
Approach:	They propose a data synthesis framework, DecIF, which automatically generates accurate and diverse instruction-following data from scratch for supervised fine-tuning and reinforcement learning.
Outcome:	Extensive experiments show that the proposed framework can synthesize accurate instruction-following data for both SFT and RL paradigms compared to baselines.

KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? (2026.acl-long)

Copied to clipboard

Xue Jiang, Ge Li, Jiaru Qian, Xianjie Shi, Chenjie Li, Hao Zhu, Ziyu Wang, Jielun Zhang, Zeyu Zhao, Kechi Zhang, Jia Li, Wenpin Jiao, Zhi Jin, Yihong Dong

Multi-modal Multi-label Emotion Detection with Modality and Label Dependence (2020.emnlp-main)

Challenge:	Existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge.
Approach:	They propose a benchmark to evaluate domain specialization methods in real-world software development.
Outcome:	KOCO-bench is a new benchmark for evaluating domain specialization methods in real-world software development.

Copied to clipboard

Dong Zhang, Xincheng Ju, Junhui Li, Shoushan Li, Qiaoming Zhu, Guodong Zhou

Sentiment Analysis

Challenge:	Existing studies on multi-label emotion detection focus on one modality . current studies focus on label dependence, but there is no consensus on the model .
Approach:	They propose a multi-modal sequence-to-set approach to model label dependence and modality dependence in a multiple-modal scenario.
Outcome:	The proposed approach is able to model the label dependence and the modality dependence in a multi-modal scenario.

Confidence Estimation for LLMs in Multi-turn Interactions (2026.findings-acl)

Copied to clipboard

Caiqi Zhang, Ruihan Yang, Xiaochen Zhu, Chengzu Li, Tiancheng Hu, Yijiang River Dong, Deqing Yang, Nigel Collier

Progressive Multimodal Reasoning via Active Retrieval (2025.acl-long)

Challenge:	Despite recent progress, most prior work studies confidence in single-turn question answering.
Approach:	They propose a logit-based probe that measures confidence in multi-turn dialogues . they propose 'infoECE' and a "hinter-guesser" paradigm for generating controlled evaluations based on data .
Outcome:	The proposed framework is grounded in calibration and monotonicity of confidence as more information becomes available.

Copied to clipboard

Guanting Dong, Chenghao Zhang, Mengjie Deng, Yutao Zhu, Zhicheng Dou, Ji-Rong Wen

Information Retrieval

Challenge:	Existing approaches to improve multimodal large language models' reasoning performance are limited.
Approach:	They propose a framework to progressively improve multimodal reasoning capabilities . they propose active retrieval and Monte Carlo tree search to improve MLLMs' reasoning .
Outcome:	The proposed framework improves multimodal reasoning capabilities in multimodal large language models.

Injecting Entity Types into Entity-Guided Text Generation (2021.emnlp-main)

Copied to clipboard

Xiangyu Dong, Wenhao Yu, Chenguang Zhu, Meng Jiang

Text Generation

Challenge:	Recent advances in deep generative modeling have led to significant advances in natural language generation (NLG).
Approach:	They propose to model the entity type carefully in the decoding phase to generate contextual words accurately.
Outcome:	The proposed model produces a target sequence based on a given list of entities.

GenProve: Learning to Generate Text with Fine-Grained Provenance (2026.acl-long)

Copied to clipboard

Jingxuan Wei, Xingyue Wang, Yanghaoyu Liao, Jie Dong, Yuchen Liu, Caijun Jia, Bihui Yu, Junnan Zhu

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

Challenge:	Existing methods for large language models (LLMs) are coarse-grained and fail to distinguish between direct quotes and complex reasoning.
Approach:	They propose a framework that combines supervised fine-tuning and group relative policy optimization to generate fluent answers while simultaneously producing sentence-level provenance triples.
Outcome:	The proposed framework outperforms 14 strong large language models in joint evaluation.

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

LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-Training (2024.emnlp-main)

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.

Copied to clipboard

Tong Zhu, Xiaoye Qu, Daize Dong, Jiacheng Ruan, Jingqi Tong, Conghui He, Yu Cheng

MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation (2025.acl-industry)

Challenge:	Mixture-of-Experts (MoE) has gained increasing popularity as a framework for scaling up large language models.
Approach:	They investigate how to build Mixture-of-Experts (MoE) models from existing large language models . they use expert construction, Continual pre-training and data sampling strategies .
Outcome:	The proposed model outperforms existing models with similar parameters on a wide range of tasks.

Copied to clipboard

Zhipeng Bian, Jieming Zhu, Xuyang Xie, Quanyu Dai, Zhou Zhao, Zhenhua Dong

MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine Translation (2025.acl-long)

Challenge:	generative AI is revolutionizing how users interact with smartphones, transforming how they interact with them.
Approach:	They propose a framework for task instruction recommendation that enables intuitive one-touch AI tasking on smartphones.
Outcome:	The proposed framework shows significant improvements in recommendation accuracy and coherence and intent alignment with predefined instruction candidates.

Copied to clipboard

Tianyu Dong, Bo Li, Jinsong Liu, Shaolin Zhu, Deyi Xiong