Papers by Mingxu Tao
Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable language generation capabilities, propelling advancements in various understanding/generation tasks, including opendomain question answering (QA). |
| Approach: | They propose a chain-of- Discussion framework to leverage synergy among multiple open-source Large Language Models (LLMs) aiming to provide more correct and more comprehensive answers for open-ended QA, although they are not strong enough individually. |
| Outcome: | The proposed framework leverages the synergy among multiple open-source Large Language Models (LLMs) to provide more correct and comprehensive answers for open-ended QA, although they are not strong enough individually. |
Probing Multimodal Large Language Models for Global and Local Semantic Representations (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have focused on the ability of MLLMs to generate single tokens one by one, while lacking studies about how their representation vectors can encode global multimodal information. |
| Approach: | They propose to use image-caption corpus to train Multimodal Large Language Models (MLLMs) . they find that the topmost layers encode more global semantic information . |
| Outcome: | The proposed models can encode more global semantic information, rather than the topmost layers, and perform better on visual-language entailment tasks. |
EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to enhance performance of Large language models are limited due to the cost of training data and privacy concerns. |
| Approach: | They propose a method that enhances a finetuned model with its inferior version and adopts contrastive decoding to reduce predicted errors. |
| Outcome: | The proposed method outperforms existing methods in data-scarcity scenarios across three domains and shows that it is more robust and robust. |
Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety (2025.emnlp-main)
Copied to clipboard
Chenhao Huang, Ziyu Shen, Yicong Ren, Huiyuan Zheng, Jiazheng Zhang, Mingxu Chai, Ming Zhang, Shihan Dou, Fan Mo, Jie Shi, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to align large language models with human preferences lack flexibility . static alignment preferences lack the ability to correct misaligned behaviors as they emerge . |
| Approach: | They propose a framework that enables dynamic and continuous alignment of large language models with human preferences. |
| Outcome: | The proposed framework improves safety and accuracy of a 7B model with human annotations. |
Unlocking the Potential of Model Merging for Low-Resource Languages (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Adapting large language models (LLMs) to new languages requires continual pre-training followed by supervised fine-tuning. |
| Approach: | They propose a model merging solution that integrates LLMs with distinct capabilities into a single model without additional training. |
| Outcome: | The proposed model merging outperforms CT-then-SFT in low-resource languages with scarce data. |
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)
Copied to clipboard
Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks. |
| Approach: | They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process. |
| Outcome: | The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS. |
MC2: Towards Transparent and Culturally-Aware NLP for Minority Languages in China (2024.acl-long)
Copied to clipboard
| Challenge: | MC2 is the largest open-source corpus of minority languages in china . MC2, however, includes four underrepresented languages: Tibetan, Uyghur, Kazakh, and Mongolian . |
| Approach: | They propose a multilingual corpus of minority languages in China that includes four underrepresented languages . they prioritize accuracy while enhancing diversity by using a quality-centric approach . |
| Outcome: | The proposed model prioritizes accuracy while enhancing diversity, the authors say . MC2 includes four underrepresented languages: Tibetan, Uyghur, Kazakh, and Mongolian . |
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 . |
Harder Task Needs More Experts: Dynamic Routing in MoE Models (2024.acl-long)
Copied to clipboard
Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng
| Challenge: | Unlike existing MoE approaches that rely on fixed TopK Routing, our dynamic expert selection framework dynamically allocates experts based on the confidence level in expert selection for each input. |
| Approach: | They propose a dynamic expert selection framework that dynamically allocates experts based on the confidence level in expert selection for each input. |
| Outcome: | The proposed method achieves an average improvement of 0.7% with less than 90% activated parameters and outperforms dense models in QA and machine translation tasks. |
MiLiC-Eval: Benchmarking Multilingual LLMs for China’s Minority Languages (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models excel in high-resource languages but struggle with low-resourced languages . minority languages such as Tibetan, Uyghur, Kazakh, and Mongolian are marginalized in NLP research due to limited digital representation and the scarcity of training data. |
| Approach: | They propose a benchmark for minority languages in China that tracks the progress of large language models on low-resource languages. |
| Outcome: | The proposed benchmark focuses on underrepresented writing systems and syntax-intensive tasks. |
When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing dense retrieval methods have achieved notable progress, but their effectiveness in legal case retrieval remains limited. |
| Approach: | They propose a self-evolving framework for rule-driven query rewriting that enhances BM25 without any parameter training. |
| Outcome: | The proposed framework outperforms non-evolutionary baselines, including human-designed rules and greedy rule selection, especially when powered by a high-capacity core LLM. |
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding (2024.emnlp-main)
Copied to clipboard
Chong Zhang, Yi Tu, Yixi Zhao, Chenshu Yuan, Huan Chen, Yue Zhang, Mingxu Chai, Ya Guo, Huijia Zhu, Qi Zhang, Tao Gui
| Challenge: | Existing models of layout reading order do not convey the complete reading order information in the layout. |
| Approach: | They propose to model layout reading order as ordering relations over layout elements . they propose a reading-order-relation-enhancing pipeline to improve model performance . |
| Outcome: | The proposed model outperforms existing models on a visual-rich document dataset and on eight cross-domain VrD-IE/QA tasks without targeted optimization. |
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. |
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. |