Papers by Shihan Wang
Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control (2026.findings-acl)
Copied to clipboard
Changhao Jiang, Jiahao Chen, Zhenghao Xiang, Zhixiong Yang, Hanchen Wang, Jiabao Zhuang, Xinmeng Che, Jiajun Sun, Hui Li, Yifei Cao, Shihan Dou, Ming Zhang, Junjie Ye, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Recent commercial systems such as Suno demonstrate strong capabilities in long-form song generation, but academic research remains non-reproducible due to the lack of publicly available training data. |
| Approach: | They propose a system for long-form song generation with fine-grained style conditioning that includes a licensed synthetic dataset and a song generation model, Muse. |
| Outcome: | The proposed system achieves competitive performance on phoneme error rate, text–music style similarity, and audio aesthetic quality while enabling controllable segment-level generation across different musical structures. |
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)
Copied to clipboard
Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM. |
| Approach: | They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks. |
| Outcome: | The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting. |
An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals (2025.acl-long)
Copied to clipboard
| Challenge: | Evolutionary Algorithms (EAs) have been proven to effectively explore the solution space of neural networks by maintaining population diversity. |
| Approach: | They propose an elite individual injection mechanism to enhance EA’s search efficiency by adaptively introducing best-performing individuals into the population. |
| Outcome: | Experiments on four datasets show that the proposed approach significantly improves the balance between exploration and exploitation, boosting performance. |
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective (2022.acl-long)
Copied to clipboard
Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, Xuanjing Huang
| Challenge: | Named Entity Recognition models are feature-engineering and machine learning based. |
| Approach: | They propose a new NER learning framework that uses entity mentions to improve model performance. |
| Outcome: | The proposed model achieves better performance on OOV entities on various settings and datasets. |
DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data (2026.acl-long)
Copied to clipboard
Shaofan Liu, Guoqiang Zhang, Shihan Dou, Huiyuan Zheng, Yiming Zhou, Junjie Ye, Shaowen Wang, Shichun Liu, Jiazheng Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods for training reward models are vulnerable to context neglect and degraded accuracy. |
| Approach: | They propose distribution-aware reward modeling that augments the RM objective with a conditional mutual information regularizer that maximizes context and the predicted reward conditioned on the response. |
| Outcome: | The proposed model improves performance in RLHF and improves accuracy in other settings. |
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
| 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. |
Semantic-Aware Action Space Compression via LLM-DRL Synergy for Efficient Task-oriented Dialogue Policy Exploration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained large language models (LLMs) with world knowledge and semantic understanding are promising for task-oriented dialogue systems. |
| Approach: | a framework that synergizes pre-trained large language models with DRL is proposed . a lightweight action pruning mechanism is employed to eliminate implausible actions . |
| Outcome: | a new framework synergizes pre-trained large language models with DRL to guide decision-making . the proposed framework eliminates semantically implausible or low-potential actions from multi-turn dialogue context . |
Multi-Programming Language Sandbox for LLMs (2025.acl-demo)
Copied to clipboard
Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang
| Challenge: | MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). |
| Approach: | They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models. |
| Outcome: | The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs). |
Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for training dialogue policies rely on a single learning system, but it requires many rounds of interaction. |
| Approach: | They propose a complementary policy learning framework which exploits the complementary advantages of the episodic memory (EM) policy and the deep Q-network (DQN) policy. |
| Outcome: | The proposed framework outperforms existing methods relying on a single learning system on three dialogue datasets. |
Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents (2024.acl-long)
Copied to clipboard
Shihan Deng, Weikai Xu, Hongda Sun, Wei Liu, Tao Tan, Liujianfeng Liujianfeng, Ang Li, Jian Luan, Bin Wang, Rui Yan, Shuo Shang
| Challenge: | Existing benchmarks for LLM-based mobile agents are insufficient to evaluate their capabilities. |
| Approach: | They propose a benchmark to evaluate LLM-based mobile agents' planning capabilities . they expand UI operations by incorporating 103 APIs to accelerate task completion . |
| Outcome: | The proposed benchmarks are based on 103 collected APIs and real user queries . the data is categorized into three distinct groups: SAST, SAMT, and MAMT . |
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)
Copied to clipboard
Ming Zhang, Yujiong Shen, Jingyi Deng, Yuhui Wang, Huayu Sha, Kexin Tan, Qiyuan Peng, Yue Zhang, Junzhe Wang, Shichun Liu, Yueyuan Huang, Jingqi Tong, Changhao Jiang, Yilong Wu, Zhihao Zhang, Mingqi Wu, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting. |
| Approach: | LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data . |
| Outcome: | LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm . |
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric (2025.acl-long)
Copied to clipboard
Yuming Yang, Yang Nan, Junjie Ye, Shihan Dou, Xiao Wang, Shuo Li, Huijie Lv, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing studies have explored various diversity-aware data selection methods to construct high-quality datasets and enhance model performance. |
| Approach: | They propose to use data diversity to measure instruction tuning of large language models. |
| Outcome: | The proposed diversity metric outperforms existing methods on simulated and real-world data and shows that it captures diversity variations and achieves a 0.97 correlation with instruction tuning. |
A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing training paradigms for dialogue policy learning with brute-force random sampling are expensive and lack reliable evaluation of difficulty scores. |
| Approach: | They propose a flexible adaptive curriculum learning framework that integrates curriculum learning with a generic global curriculum. |
| Outcome: | The proposed framework improves learning performance and efficiency on three public dialogue datasets. |
Bootstrapped Policy Learning for Task-oriented Dialogue through Goal Shaping (2024.emnlp-main)
Copied to clipboard
| Challenge: | Despite the promise of reinforcement learning, achieving seamless knowledge transitions in complex dialogue environments is difficult. |
| Approach: | They propose a Bootstrapped Policy Learning framework which adaptively tailors progressively challenging subgoal curriculum for each complex goal through goal shaping. |
| Outcome: | The proposed framework has shown to be effective across four publicly available datasets with different difficulty levels. |
JanusMM: A Benchmark for Self-Deprecation Understanding in Real-World Multimodal Conversations (2026.acl-long)
Copied to clipboard
Xinyi Xu, Bingguang Hao, Yongyi Xiong, Zimo Chen, Xinchen Liu, Hongxin Guo, Xuelong Wang, Silin Zhou, Shihan Dou
| Challenge: | Multimodal large language models (MLLMs) are a common communicative strategy in human society, often using image-text interplay to express emotions and intentions. |
| Approach: | They propose to evaluate multimodal large language models (MLLMs)' understanding of self-deprecation in real-world conversations using 2,016 bilingual memes. |
| Outcome: | The proposed framework evaluates MLLMs' understanding of self-deprecation in real-world conversations. |
Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to training large language models suffer from unstable value estimation, whereas outcome supervision struggles with credit assignment due to sparse, trajectory-level rewards. |
| Approach: | They propose a framework that integrates process supervision into group relative policy optimization. |
| Outcome: | The proposed framework outperforms standard GRPO on knowledge-intensive benchmarks by 5.0% and 6.3% on Qwen3-1.7B. |
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query. |
| Approach: | They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. |
| Outcome: | The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO. |
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)
Copied to clipboard
Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current medical benchmarks have limitations in question design, data sources and evaluation methods. |
| Approach: | They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records . |
| Outcome: | The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios. |
UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation (2025.findings-emnlp)
Copied to clipboard
Tianlong Li, Wenhao Liu, Muling Wu, Shihan Dou, Zhenghua Wang, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs). |
| Approach: | They propose a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM’s personality traits. |
| Outcome: | The proposed method can modulate the personality expression of large language models by dynamically altering their predicted probability of upcoming words in a pluggable fashion. |
METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for learning complex sentences with multiple aspects are ill-equipped to learn complex sentences . |
| Approach: | They propose a mutual enhanced transformation network for the ABSA task . it improves representation learning of the aspect with contextual semantic features . |
| Outcome: | The proposed model improves representation learning of the aspect with contextual semantic features, giving the aspect more abundant information. |
PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing persona-based dialogue models generate personalized responses using predefined persona information, but they lack personality. |
| Approach: | They propose a persona-based dual Alternating Learning Network that generates personalized responses using predefined persona information. |
| Outcome: | The proposed method produces more personalized responses than baseline methods. |
StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)
Copied to clipboard
Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective. |
| Approach: | They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality. |
| Outcome: | The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality. |
Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025.coling-main)
Copied to clipboard
Tianlong Li, Zhenghua Wang, Wenhao Liu, Muling Wu, Shihan Dou, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) however, limited research into the underlying mechanisms that make LLMs vulnerable to such attacks has been conducted. |
| Approach: | They propose that LLMs' self-safeguarding capability is linked to specific activity patterns within their representation space. |
| Outcome: | The proposed models can be detected with a few pairs of contrastive queries, and the robustness can be manipulated by weakening or strengthening these patterns. |
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026.acl-long)
Copied to clipboard
Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang
| Challenge: | Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete supervision. |
| Approach: | They propose a framework that enhances value modeling for robust RL in LLM post-training by integrating auxiliary losses guided by entropy and perplexity from a frozen language model and variational information bottleneck. |
| Outcome: | The proposed framework outperforms baselines on multi-turn dialogue, math reasoning, and science QA with rule-based and model-based rewards. |
From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling (2026.findings-acl)
Copied to clipboard
Yifei Cao, Changhao Jiang, Jiabao Zhuang, Jiajun Sun, Ming Zhang, Zhiheng Xi, Hui Li, Shihan Dou, Yuran Wang, Yunke Zhang, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that the MOS-aware GRM significantly improves fine-grained speech quality discrimination. |
| Approach: | They propose a MOS-aware reward model that incorporates MOS gap into reward function during reinforcement learning. |
| Outcome: | The proposed model significantly improves fine-grained speech quality discrimination. |
DocFusion: A Unified Framework for Document Parsing Tasks (2025.findings-acl)
Copied to clipboard
Mingxu Chai, Ziyu Shen, Chong Zhang, Yue Zhang, Xiao Wang, Shihan Dou, Jihua Kang, Jiazheng Zhang, Qi Zhang
| Challenge: | Existing methods for document parsing often employ multiple models, limiting performance . Existing models often employ discrete tokens, whereas recognition relies on continuous coordinates . |
| Approach: | They propose a Gaussian-Kernel Cross-Entropy Loss (GK-CEL) that unifies detection and recognition by enabling generative frameworks to handle both tasks simultaneously. |
| Outcome: | The proposed model performs competitively across four core document parsing tasks. |
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing adversarial training methods require multi-step gradient ascents or word substitutions to obtain adversarials, which impairs the effectiveness of adversariarial training. |
| Approach: | They propose a procedure for instead adversarial training with only clean data that estimates the adversarials loss by perturbing the input data’s probability distribution rather than their embeddings. |
| Outcome: | The proposed procedure reduces time consumption by up to 70% compared to current best-performing adversarial training methods. |