Papers by Shen Dong

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities (2024.emnlp-main)

Challenge:	OpenWebAgent integrates large language models and large multimodal models to improve web automation.
Approach:	They propose to integrate large language models and large multimodal models into an open toolkit to optimize web automation.
Outcome:	The open toolkit integrates both large language models (LLMs) and large multimodal models (LMMs) it enables the development of powerful, task-oriented web agents, significantly enhancing user experience and operational efficiency on the web.

Copied to clipboard

Ming Zhang, Caishuang Huang, Yilong Wu, Shichun Liu, Huiyuan Zheng, Yurui Dong, Yujiong Shen, Shihan Dou, Jun Zhao, Junjie Ye, Qi Zhang, Tao Gui, Xuanjing Huang

Dialogue Systems & Conversational Agents

Challenge:	Current datasets cater to user-led systems and are limited to predefined specific scenarios and slots.
Approach:	They propose to use a Chinese dialogue dataset to train a model that authentically simulates human-computer dialogues in 30 popular life service scenarios.
Outcome:	The proposed model achieves a joint accuracy of 75.09% in out-of-domain evaluations . it also achieves notable abilities in slot filling and questioning .

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

Copied to clipboard

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

Dialogue Systems & Conversational Agents

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

Tunable Soft Prompts are Messengers in Federated Learning (2023.findings-emnlp)

Copied to clipboard

Chenhe Dong, Yuexiang Xie, Bolin Ding, Ying Shen, Yaliang Li

Responsible & Trustworthy NLP

Challenge:	Existing methods to protect model privacy in federated learning (FL) are limited.
Approach:	They propose a federated learning approach that provides model privacy protection via tunable soft prompts.
Outcome:	The proposed approach provides protection for the global model while reducing communication and computation costs.

MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning (2020.acl-main)

Copied to clipboard

Jie Lei, Liwei Wang, Yelong Shen, Dong Yu, Tamara Berg, Mohit Bansal

Visual Data in NLP

Challenge:	Existing methods for generating paragraph descriptions for videos require a coherent paragraph and a higher level of coherence.
Approach:	They propose a new method that generates a summarized memory state from video segments and sentence history to help better predict the next sentence.
Outcome:	The proposed method generates more coherent and less repetitive paragraph captions while maintaining relevance to the input video events.

Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance (2025.emnlp-industry)

Copied to clipboard

Zixuan Wang, Yu Sun, Hongwei Wang, Baoyu Jing, Xiang Shen, Xin Dong, Zhuolin Hao, Hongyu Xiong, Yang Song

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

Challenge:	Existing approaches to identifying inappropriate content require extensive human-labeled data and lack cross-issue generalization.
Approach:	They propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection.
Outcome:	The proposed model improves the MLLM's performance in both zero-shot and supervised fine-tuning settings and shows strong generalization capabilities to emergent, previously unseen issues.

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.

Tree-of-Code: A Self-Growing Tree Framework for End-to-End Code Generation and Execution in Complex Tasks (2025.findings-acl)

Copied to clipboard

Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lyu, Daxiang Dong

Programming Languages in NLP

Challenge:	Effectively and efficiently handling complex realworld problems has become a key focus across industry and academia.
Approach:	They propose a tree-of-code framework that generates nodes through self-supervision and combines prompt and model exploration in a GT-free setting.
Outcome:	Experiments on two datasets with ten popular zero-shot LLMs show that Tree-of-Code boosts accuracy by nearly 20% over CodeAct with fewer than 1/4 turns.

Memory-Efficient Differentiable Transformer Architecture Search (2021.findings-acl)

Copied to clipboard

Yuekai Zhao, Li Dong, Yelong Shen, Zhihua Zhang, Furu Wei, Weizhu Chen

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression (2021.emnlp-main)

Challenge:	Current neural architecture search methods suffer from huge computational cost.
Approach:	They propose a reversible recursive backpropagation algorithm that uses the last layer to store the outputs of the network.
Outcome:	The proposed algorithm outperforms standard Transformers on three sequence-to-sequence datasets.

Copied to clipboard

Chenhe Dong, Yaliang Li, Ying Shen, Minghui Qiu

Summarize before Aggregate: A Global-to-local Heterogeneous Graph Inference Network for Conversational Emotion Recognition (2020.coling-main)

Challenge:	Large pre-trained language models (PLMs) have shown overwhelming performances on many tasks, but their large size and slow inference speed have hindered practical deployments.
Approach:	They propose a hierarchical relational knowledge distillation method to capture hierarchic and domain relational information.
Outcome:	The proposed method outperforms existing methods on multi-domain datasets and is highly reproducible.

Copied to clipboard

Dongming Sheng, Dong Wang, Ying Shen, Haitao Zheng, Haozhuang Liu

Structured Data in NLP

Challenge:	Existing studies focus on modeling emotion influences with utterance-level features, with little attention paid on phrase-level semantic connection between utterrances.
Approach:	They propose a two-stage Summarization and Aggregation Graph Inference Network which integrates inference for topic-related emotional phrases and local dependency reasoning over neighbouring utterances in a global-to-local fashion.
Outcome:	The proposed model outperforms the state-of-the-art models on three CER benchmark datasets.

Controllable Natural Language Generation with Contrastive Prefixes (2022.findings-acl)

Copied to clipboard

Jing Qian, Li Dong, Yelong Shen, Furu Wei, Weizhu Chen

Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)

Challenge:	Existing work on controllable natural language generation has focused on fine-tuning existing models or using attribute discriminators.
Approach:	They propose a lightweight framework for controllable GPT2 generation that utilizes attribute-specific vectors to steer natural language generation.
Outcome:	The proposed framework can guide generation towards desired attributes while keeping high linguistic quality.

Copied to clipboard

Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values.
Approach:	They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values .
Outcome:	The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets.

SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval (2022.emnlp-industry)

Copied to clipboard

Kun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-rong Wen, Nan Duan

Information Retrieval

Challenge:	Existing methods for sapping negatives from large document pool suffer from the uninformative or false negative problem.
Approach:	They propose a method to sample negatives from a large document pool using a new sampling probability distribution.
Outcome:	The proposed method can be used to sample more ambiguous negatives on four public and one industry datasets.

IPS: In-Prompt Process Supervision for Short Video Content Moderation (2026.acl-industry)

Copied to clipboard

Mingchao Liu, Yu Sun, Ruixiao Sun, Xin Dong, Xiang Shen, Hongwei Wang, Hongyu Xiong, Yang Song

Responsible & Trustworthy NLP

Challenge:	Multimodal large language models (MLLMs) capture semantics of short video content but fail to account for policy-specific details.
Approach:	They propose a framework that integrates In-prompt Process Supervision into MLLMs . they propose sequential reasoning over ancillary questions during fine-tuning .
Outcome:	IPS outperforms baseline MLLMs on public and proprietary benchmarks . replacing human-annotated ancillary labels with MLML-generated ones results in performance degradation.

Multimodal Language Models See Better When They Look Shallower (2025.emnlp-main)

Copied to clipboard

Haoran Chen, Junyan Lin, Xinghao Chen, Yue Fan, Jianfeng Dong, Xin Jin, Hui Su, Jinlan Fu, Xiaoyu Shen

PEAR: Planner-Executor Agent Robustness Benchmark (2026.findings-eacl)

Challenge:	Existing studies show that multimodal large language models extract visual features from the final layers of a pretrained Vision Transformer.
Approach:	They propose a feature fusion method that strategically incorporates shallower layers . they propose MLLMs that extract visual features from the final layers of a pretrained Vision Transformer .
Outcome:	The proposed method outperforms deep layers on fine-grained visual tasks . it is the first comprehensive study of visual layer selection for MLLMs .

Copied to clipboard

Shen Dong, Mingxuan Zhang, Pengfei He, Li Ma, Bhavani Thuraisingham, Hui Liu, Yue Xing

Robustness in NLP

Challenge:	Existing studies examine isolated attack surfaces or specific scenarios, leaving a lack of holistic understanding of MAS vulnerabilities.
Approach:	They propose a benchmark to evaluate the utility and vulnerability of planner–executor MAS.
Outcome:	The proposed benchmark evaluates planner–executor MAS on a widely adopted design.

ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains (2025.acl-long)

Copied to clipboard

Zilu Dong, Xiangqing Shen, Zinong Yang, Rui Xia

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training (2025.emnlp-main)

Challenge:	Existing knowledge editing methods for large language models struggle to maintain logical consistency when propagating ripple effects to associated facts.
Approach:	They propose a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates.
Outcome:	The proposed framework improves logical generalization and specificity while maintaining reliability and specificness.

Copied to clipboard

Haotian Dong, Jingyan Jiang, Rongwei Lu, Jiajun Luo, Jiajun Song, Bowen Li, Ying Shen, Zhi Wang

Text Clustering

Challenge:	Decentralized LLM training leverages dispersed resources at varying scales.
Approach:	They propose a resource-driven paradigm that leverages dispersed resources across clusters, datacenters and even regions.
Outcome:	The proposed model scales are 175 billion to 660 billion parameters, and the exponential growth in computational requirements poses significant challenges.

Scaling Laws for Linear Complexity Language Models (2024.emnlp-main)

Copied to clipboard

Xuyang Shen, Dong Li, Ruitao Leng, Zhen Qin, Weigao Sun, Yiran Zhong

ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding (2026.findings-acl)

Challenge:	Existing scaling laws for large language models are unclear, but they are useful for scalability.
Approach:	They propose scaling laws for linear complexity language models to establish a foundation for their scalability.
Outcome:	The proposed models demonstrate superior linguistic proficiency and knowledge retention.

Copied to clipboard

Tian Xueyun, Wei Li, Bingbing Xu, Heng Dong, Yuanzhuo Wang, Huawei Shen

Zero-Shot Cross-Domain Aspect-Based Sentiment Analysis via Domain-Contextualized Chain-of-Thought Reasoning (2025.findings-emnlp)

Challenge:	Existing omni-multimodal large language models lack incomplete modality support or lack autonomous proactive monitoring.
Approach:	They propose a real-time omni-multimodal assistant for unified reactive and proactive interaction that decouples response initiation from generation to ensure precise triggering without task conflict.
Outcome:	The proposed model achieves state-of-the-art performance on proactive tasks while competing in reactive settings.

Copied to clipboard

Chuming Shen, Wei Wei, Dong Wang, Zhong-Hao Wang

Low-Resource NLP

Challenge:	Cross-domain aspect-based sentiment analysis (ABSA) aims to learn specific knowledge from a source domain to perform various tasks on a target domain.
Approach:	a new framework is proposed to learn specific knowledge from a source domain . the framework uses domain adaptation techniques to transfer domain-agnostic features .
Outcome:	a new learning framework for cross-domain aspect-based sentiment analysis is proposed . it effectively eliminates dependency on target-domain annotations, authors say .

Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension (2020.acl-main)

Copied to clipboard

Hongyu Gong, Yelong Shen, Dian Yu, Jianshu Chen, Dong Yu

Document Hashing with Mixture-Prior Generative Models (D19-1)

Challenge:	Existing approaches to machine reading comprehension (MRC) on long texts typically chunk text into equally-spaced segments without considering information from other segments.
Approach:	They propose to let a model learn to chunk in a more flexible way via reinforcement learning.
Outcome:	The proposed model extracts a text span from document and query as answer . previous models can only take a fixed-length (e.g., 512) text as input .

Copied to clipboard

Wei Dong, Qinliang Su, Dinghan Shen, Changyou Chen

Challenge:	Existing generative hashing methods only consider the use of simple priors, which limits them to further improve their performance.
Approach:	They propose to use Gaussian and Bernoulli priors to generate hashing codes . they propose to cast a Gausssian latent representation into binary code .
Outcome:	The proposed models outperform existing methods on a benchmark dataset using Gaussian and Bernoulli priors.

CodeV: Issue Resolving with Visual Data (2025.findings-acl)

Copied to clipboard

Linhao Zhang, Daoguang Zan, Quanshun Yang, Zhirong Huang, Dong Chen, Bo Shen, Tianyu Liu, Yongshun Gong, Huang Pengjie, Xudong Lu, Guangtai Liang, Lizhen Cui, Qianxiang Wang

BanditSum: Extractive Summarization as a Contextual Bandit (D18-1)

Challenge:	Large Language Models (LLMs) have expanded to more complex repository-level tasks.
Approach:	They propose a first approach to leveraging visual data to enhance the issue-resolving capabilities of Large Language Models (LLMs) they demonstrate the effectiveness of CodeV and provide valuable insights into leveraging visualization to resolve GitHub issues.
Outcome:	The proposed approach improves the issue-resolving capabilities of Large Language Models (LLMs) by using visual data.

Copied to clipboard

Yue Dong, Yikang Shen, Eric Crawford, Herke van Hoof, Jackie Chi Kit Cheung

Information Extraction & Text Mining

Challenge:	Existing methods for extractive summarization are heuristically generated and require a set of binary labels to be selected.
Approach:	They propose a method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels.
Outcome:	The proposed method achieves better ROUGE scores than the state-of-the-art methods and significantly fewer update steps than competing approaches.

Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training (2026.acl-long)

Copied to clipboard

Changhao Jiang, Ming Zhang, Yifei Cao, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun, Yi Dong, Yujiong Shen, Jingqi Tong, Baoyu Fan, Tao Gui, Qi Zhang, Xuanjing Huang

When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables (2026.acl-long)

Challenge:	Existing methods to predict performance of large language models are lacking . authors propose a size-dependent mutual information predictor for closed-book question answering accuracy .
Approach:	They propose a size-dependent mutual information predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering accuracy.
Outcome:	The proposed method outperforms baseline models and achieves R2 > 0.7 in predicting QA accuracy without additional training.

Copied to clipboard

Shenghao Ye, Yu Guo, Dong Jin, Yuxiang Wang, Yikai Shen, Yunpeng Hou, Shuangwu Chen, null Jianyang, Xiaofeng Jiang