Papers by Ming Ma

RubricBench: Aligning Model-Generated Rubrics with Human Standards (2026.acl-long)

Challenge:	Existing speech codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks.
Approach:	They propose a neural speech codec with semantic-acoustic dual-stream quantization that disentangles semantic and acousian modeling into two dedicated streams.
Outcome:	The proposed codec outperforms state-of-the-art speech tokenizers in auto-propagating text-to-speech models.

Copied to clipboard

Junyi Zhou, Qiyuan Zhang, Yufei Wang, Fuyuan Lyu, Yidong Ming, Can Xu, Qingfeng Sun, Kai Zheng, Peng Kang, Xue Liu, Chen Ma

Challenge:	Existing benchmarks lack discriminative complexity and ground-truth rubric annotations required for rigorous evaluation.
Approach:	They propose a curated benchmark with 1,147 pairwise comparisons to assess the reliability of rubric-based evaluation.
Outcome:	The proposed benchmarks show that they support diverse domains, exhibit discriminative ability, provide high-quality annotations, and include human-authored rubrics.

A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation (2020.acl-main)

Copied to clipboard

Shuo Ren, Yu Wu, Shujie Liu, Ming Zhou, Shuai Ma

Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)

Challenge:	Recent work shows successful methods for unsupervised machine translation (UMT) initialization stage is important since bad initialization may wrongly squeeze the search space and too much noise may hurt the final performance.
Approach:	They propose a retrieval and rewriting based method to better initialize unsupervised translation models.
Outcome:	The proposed method improves translation performance by over 4 BLEU scores.

Copied to clipboard

Runxuan Liu, Xianhao Ou, Xinyan Ma, Jiyuan Wang, Jiafeng Liang, Jiaqi Li, Tao He, Zheng Chu, Rongchuan Mu, Zekun Wang, Baoxin Wang, Dayong Wu, Ming Liu, Shijin Wang, Guoping Hu, Bing Qin

TheoremQA: A Theorem-driven Question Answering Dataset (2023.emnlp-main)

Challenge:	Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization.
Approach:	They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach.
Outcome:	The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks.

Copied to clipboard

Wenhu Chen, Ming Yin, Max Ku, Pan Lu, Yixin Wan, Xueguang Ma, Jianyu Xu, Xinyi Wang, Tony Xia

Smart-Start Decoding for Neural Machine Translation (2021.naacl-main)

Challenge:	Recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90% accuracy.
Approach:	They propose to use theorem-driven question-answering dataset to evaluate AI models' ability to apply theoretic concepts to solving challenging science problems.
Outcome:	TheoremQA is curated by domain experts and contains 800 high-quality questions covering 350 theoremics from Math, Physics, EE&CS, and Finance.

Copied to clipboard

Jian Yang, Shuming Ma, Dongdong Zhang, Juncheng Wan, Zhoujun Li, Ming Zhou

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

Challenge:	Existing neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to left.
Approach:	They propose a method that starts decoding target words from the right side of a median word and generates words on the left.
Outcome:	The proposed method outperforms baseline models on three datasets.

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.

PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning (2026.acl-long)

Copied to clipboard

Rongchuan Mu, Zexin Wang, Qianyu Wang, MingHua Ma, Zekun Wang, Ming Liu, Bing Qin

Reasoning

Challenge:	Existing alignment methods struggle to balance general reasoning with instruction-following (IF) this is hindered by dependency on teacher models, reward hacking, and reasoning-answer inconsistencies.
Approach:	They propose a two-stage curriculum learning framework based on Reinforcement Learning from Verifiable Rewards to enhance both IF and general reasoning capabilities.
Outcome:	The proposed framework outperforms leading models on six representative IF tasks while achieving a 21.25% relative average improvement over the original model.

A Simple and Effective Unified Encoder for Document-Level Machine Translation (2020.acl-main)

Copied to clipboard

Shuming Ma, Dongdong Zhang, Ming Zhou

Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning (2025.acl-long)

Challenge:	Existing models for document-level machine translation use two separate encoders to model the source sentences and document- level contexts.
Approach:	They propose a unified encoder that can outperform existing models of dual-encoder models . they propose to use document-level contexts to model the interaction between the contexts and the source sentences .
Outcome:	The proposed model outperforms baseline models of dual-encoder models in terms of BLEU and METEOR scores.

Copied to clipboard

Yexing Du, Youcheng Pan, Ziyang Ma, Bo Yang, Yifan Yang, Keqi Deng, Xie Chen, Yang Xiang, Ming Liu, Bing Qin

Control Image Captioning Spatially and Temporally (2021.acl-long)

Challenge:	Existing studies on English-centric translation tasks have focused on multimodal large language models, but the exploration of many-to-many translation is limited by the scarcity of parallel data.
Approach:	They propose a three-stage curriculum learning strategy that leverages the machine translation capabilities of large language models and adapts them to S2TT tasks.
Outcome:	The proposed strategy achieves state-of-the-art average performance in 1514 language pairs, requiring fewer than 10 hours of speech data per language to achieve competitive results.

Copied to clipboard

Kun Yan, Lei Ji, Huaishao Luo, Ming Zhou, Nan Duan, Shuai Ma

GAP: a Global Adaptive Pruning Method for Large Language Models (2025.emnlp-main)

Challenge:	Existing methods to generate image captions with user intention are still under exploration.
Approach:	They propose a model that connects Contrastive constraints and Attention Guidance in a loop manner and engages explicit spatial and temporal constraints to the generating process.
Outcome:	The proposed model improves performance on a trace-controlled image captioning task.

Copied to clipboard

Zhihua Ban, Haotian Ma, Siheng Zhang, Shengyu Liu, Xichen Chen, Ming Yang

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning (2026.acl-long)

Challenge:	Existing structured pruning methods employ uniform compression rates across network layers, neglecting the varying importance of different network depths.
Approach:	They propose a pruning framework that minimizes global capability loss by layer-adaptive pruning rates.
Outcome:	The proposed approach achieves comparable performance with state-of-the-art methods at high pruning rates and shows significant advantages at low pruning rates.

Copied to clipboard

Yanrui Du, Fenglei Fan, Sendong Zhao, Jiawei Cao, Ming Ma, Danyang Zhao, Shuren Qi, Ting Liu, Bing Qin

Improving Neural Machine Translation with Soft Template Prediction (2020.acl-main)

Challenge:	Instruction Fine-Tuning (IFT) has emerged as a critical technique for customizing Large Language Models (LLMs) however, recent studies have revealed that IFT can compromise the built-in security mechanisms of LLMs, posing significant security risks.
Approach:	They propose a method that shifts learning burden onto security-robust parameters and propose 'warm-up' phase that preferentially trains Mods_Rob to learn low-level features with minimal security risk.
Outcome:	The proposed method reduces security risks without sacrificing performance gains across knowledge-intensive datasets.

Copied to clipboard

Jian Yang, Shuming Ma, Dongdong Zhang, Zhoujun Li, Ming Zhou

Explicit Cross-lingual Pre-training for Unsupervised Machine Translation (D19-1)

Challenge:	Recent advances in neural machine translation (NMT) depend on source text to generate translation.
Approach:	They propose to use extracted templates from tree structures as soft target templates to guide the translation procedure.
Outcome:	The proposed model outperforms baseline models on four benchmarks and demonstrates the effectiveness of soft target templates.

Copied to clipboard

Shuo Ren, Yu Wu, Shujie Liu, Ming Zhou, Shuai Ma

A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling (2025.findings-emnlp)

Challenge:	Existing approaches to build initial unsupervised machine translation models with cross-lingual n-gram embeddings are inexplicit and limited.
Approach:	They propose a cross-lingual pre-training method that incorporates cross-linguistic training signals into pre-trained models by randomly choosing source n-grams in the input text stream.
Outcome:	The proposed method significantly improves the performance of unsupervised machine translation.

Copied to clipboard

Shiyu Ji, Farnoosh Hashemi, Joice Chen, Juanwen Pan, Weicheng Ma, Hefan Zhang, Sophia Pan, Ming Cheng, Shubham Mohole, Saeed Hassanpour, Soroush Vosoughi, Michael Macy

Challenge:	Rhetorical strategies are important to persuasive communication, but their analysis relies on human annotation, which is costly, inconsistent and difficult to scale.
Approach:	They propose a framework that leverages large language models to generate and label debate data . they fine-tune transformer-based classifiers on this dataset and validate it against human data a .
Outcome:	The proposed model achieves high performance and strong generalization across topical domains.

Music Audio-Visual Question Answering Requires Specialized Multimodal Designs (2026.findings-acl)

Copied to clipboard

Wenhao You, Xingjian Diao, Wenjun Huang, Chunhui Zhang, Keyi Kong, Weiyi Wu, Chiyu Ma, Zhongyu Ouyang, Tingxuan Wu, Ming Cheng, Soroush Vosoughi, Jiang Gui

EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models (2025.acl-long)

Challenge:	Music audio-visual question answering presents unique challenges with dense audio-visual content, intricate temporal dynamics, and the need for domain-specific knowledge.
Approach:	They analyze Music AVQA datasets and analyze their results to identify key design patterns . they propose concrete future directions for incorporating musical priors .
Outcome:	The proposed architectures are critical for success in Music AVQA, the authors argue . they suggest concrete future directions for incorporating musical priors .

Copied to clipboard

Zekun Wang, MingHua Ma, Zexin Wang, Rongchuan Mu, Liping Shan, Ming Liu, Bing Qin

A Graph-based Coarse-to-fine Method for Unsupervised Bilingual Lexicon Induction (2020.acl-main)

Challenge:	Existing methods for accelerating Large Vision-Language Models lack comprehensive evaluation across diverse backbones, benchmarks, and metrics.
Approach:	They propose EffiVLM-BENCH framework for evaluating absolute performance and generalization and loyalty.
Outcome:	The proposed framework offers insights into optimal strategies for accelerating LVLMs.

Copied to clipboard

Shuo Ren, Shujie Liu, Ming Zhou, Shuai Ma

Exploring Continual Learning for Code Generation Models (2023.acl-short)

Challenge:	Recent methods for bilingual lexicon induction are based on unsupervised cross-lingual word embeddings . previous methods only use word-level information, which is limited and inaccurate .
Approach:	They propose a graph-based approach to induce bilingual lexicons in a coarse-to-fine way . they use word cliques from graphs and aligned clique-level words to find initial translation solution .
Outcome:	The proposed method improves the performance of bilingual lexicon induction compared with previous methods.

Copied to clipboard

Prateek Yadav, Qing Sun, Hantian Ding, Xiaopeng Li, Dejiao Zhang, Ming Tan, Parminder Bhatia, Xiaofei Ma, Ramesh Nallapati, Murali Krishna Ramanathan, Mohit Bansal, Bing Xiang

Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation (2023.acl-long)

Challenge:	Large-scale code generation models such as Copilot and CodeT5 are expensive to train and re-train.
Approach:	They propose a benchmark for Continual Learning (CL) that covers a wide range of tasks with different input and output programming languages.
Outcome:	The proposed method improves on Prompt Pooling with Teacher Forcing, which suffers catastrophic forgetting due to stark distribution shifts in coding tasks.

Copied to clipboard

Robert Giaquinto, Dejiao Zhang, Benjamin Kleiner, Yang Li, Ming Tan, Parminder Bhatia, Ramesh Nallapati, Xiaofei Ma

Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)

Challenge:	Existing methods for learning representations of structured knowledge are limited to the minority of people with technical skills.
Approach:	They propose a large pretraining dataset and strategy for learning representations of text, tables, and SQL code that leverages the entire context of the problem.
Outcome:	The proposed model improves on two SQL tasks and shows a 1.7 and 2.2 percentage point improvement over existing methods.

Copied to clipboard

Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu

Responsible & Trustworthy NLP

Challenge:	Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations.
Approach:	They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability.
Outcome:	The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants .

BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation (2022.naacl-main)

Copied to clipboard

Yuchen Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Jian Yang, Haoyang Huang, Rico Sennrich, Ryan Cotterell, Mrinmaya Sachan, Ming Zhou

SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation (2021.acl-long)

Challenge:	Standard evaluation metrics, e.g., BLEU, TER and METEOR, focus on the quality of translations at the sentence level and do not consider discourse-level features.
Approach:	They propose to use a metric to take discourse coherence into consideration by categorizing discourse-related spans and calculating the similarity-based F1 measure of categorized spans.
Outcome:	The proposed metric possesses better selectivity and interpretability at the document-level, and is more sensitive to document- level nuances.

Copied to clipboard

Shuo Ren, Long Zhou, Shujie Liu, Furu Wei, Ming Zhou, Shuai Ma

Triangular Architecture for Rare Language Translation (P18-1)

Challenge:	Using pre-training methods for NMT models is difficult because of the cross-attention module . cross-linguistic embeddings are not used to pretrain a decoder .
Approach:	They propose a semantic interface between pre-trained encoder and pre-train decoder to improve NMT performance.
Outcome:	The proposed method improves on translation and unsupervised translation tasks.

Copied to clipboard

Shuo Ren, Wenhu Chen, Shujie Liu, Mu Li, Ming Zhou, Shuai Ma

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization (2026.findings-acl)

Challenge:	Empirical results show that Neural Machine Translation (NMT) performs poor on low-resource pairs especially when Z is a rare language.
Approach:	They propose a triangular triangulation technique to leverage bilingual data to optimize the translation performance of low-resource pairs.
Outcome:	Empirical results show that the proposed architecture significantly improves translation quality of rare languages on MultiUN and IWSLT2012 datasets and even better when combining back-translation methods.

Copied to clipboard

Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang

Reasoning

Challenge:	Large Language Models (LLMs) can solve complex tasks through iterative information retrieval.
Approach:	They propose a turn-level stage-aware policy optimization approach to solve this problem . they introduce a first-occurrence latent reward mechanism to allocate partial rewards .
Outcome:	Experiments show that TSPO outperforms state-of-the-art models on Qwen2.5-3B and 7B models.

SPEAK: Spiking Neurons as an Entropy-Aware Tokenizer for Large Language Models (2026.acl-long)

Copied to clipboard

Ming Chen, Wenyao Li, Chao Liang, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan

Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization (2023.findings-eacl)

Challenge:	Existing tokenizers fail to explicitly leverage historical tokenization results . large language models (LLMs) have demonstrated remarkable effectiveness across NLP tasks .
Approach:	They propose a tokenizer that integrates spiking neurons to explicitly leverage historical tokenization results.
Outcome:	The proposed tokenizer leverages historical tokenization results, but does not selectively leverage history based on contextual relevance.

Copied to clipboard

Ming Shen, Jie Ma, Shuai Wang, Yogarshi Vyas, Kalpit Dixit, Miguel Ballesteros, Yassine Benajiba

Summarization

Challenge:	generating aspect-specific and general opinion summaries is challenging due to the lack of annotated data.
Approach:	They propose two unsupervised approaches to generate aspect-specific and general opinion summaries by training on synthetic datasets constructed with aspect-related review contents.
Outcome:	The proposed method outperforms existing methods on space and Oposum+ and on other metrics.

ContraCLM: Contrastive Learning For Causal Language Model (2023.acl-long)

Copied to clipboard

Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Bing Xiang

Language Models as Continuous Self-Evolving Data Engineers (2025.emnlp-main)

Challenge:	Existing studies show that causal language models lack expressiveness due to poor discrimination ability.
Approach:	They propose a contrastive learning framework that enhances discrimination of representations and bridges the gap with encoder-only models.
Outcome:	The proposed framework improves discrimination and source code generation capabilities on a variety of downstream tasks.

Copied to clipboard

Peidong Wang, Ming Wang, Zhiming Ma, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Kaisong Song

Label Words as Local Task Vectors in In-Context Learning (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their further evolution is often hampered by the scarcity of high-quality training data and the heavy reliance of traditional methods on expert-labeled data.
Approach:	They propose a paradigm that enables LLMs to train themselves by generating, cleaning, reviewing and annotating data with preference information.
Outcome:	The proposed model can generate, clean, review, and annotate data with preference information significantly reducing time and cost of post-training data construction.

Copied to clipboard

Bowen Zheng, Ming Ma, Zhongqiao Lin, Tianming Yang

Information Retrieval

Challenge:	Large Language Models (LLMs) have demonstrated remarkable abilities, one of the most important being in-context learning (ICL).
Approach:	They hypothesized that the network creates a task vector in specific positions during ICL, which can be computed by averaging across the dataset.
Outcome:	The proposed model can achieve zero-shot performance with dummy inputs comparable to few-shot learning by patching the global task vector.

CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information (2025.coling-main)

Copied to clipboard

Yuxin Wang, MingHua Ma, Zekun Wang, Jingchang Chen, Shan Liping, Qing Yang, Dongliang Xu, Ming Liu, Bing Qin

Green & Sustainable NLP

Challenge:	Existing LLM pruning works focus on unstructured pruning, which typically requires special hardware support for a practical speed-up.
Approach:	They propose a network pruning framework that leverages both coarse and fine-grained activation information as an importance criterion to guide pruning.
Outcome:	The proposed framework outperforms existing pruning methods on diverse models across sparsity budgets.

A Hybrid Detection and Generation Framework with Separate Encoders for Event Extraction (2023.eacl-main)

Copied to clipboard

Ge Shi, Yunyue Su, Yongliang Ma, Ming Zhou