Papers by Qian Ma

PUNR: Pre-training with User Behavior Modeling for News Recommendation (2023.findings-emnlp)

Challenge:	composition of pre-training datasets for large language models remains undisclosed . current methods for evaluating data quality are limited by single-dimensional evaluation or redundancy-focused strategies.
Approach:	They propose a multi-dimensional data selection method that integrates dimensions with existing quality metrics through learned optimal weightings.
Outcome:	The proposed method doubles convergence speed for 1.3B model models and improves downstream task performance by 3.23%.

Copied to clipboard

Guangyuan Ma, Hongtao Liu, Xing W, Wanhui Qian, Zhepeng Lv, Qing Yang, Songlin Hu

SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation (2025.emnlp-main)

Challenge:	Existing news recommendation methods use pre-trained language models to produce news vectors and user vectors.
Approach:	They propose an unsupervised pre-training paradigm with two tasks for user behavior modeling.
Outcome:	The proposed model improves on the real-world news benchmark.

Copied to clipboard

Qian Dong, Jia Chen, Qingyao Ai, Hongning Wang, Haitao Li, null Yiwu, Yao Hu, Yiqun Liu, Shaoping Ma

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint (2025.acl-long)

Challenge:	Existing retrieval-augmented code generation methods fail to accurately fetch the knowledge required for code generation for consecutive code fragments.
Approach:	They propose a paradigm that enables large language models to Self-express their information needs to enhance retrieval-augmented code generation methods.
Outcome:	Experiments show that SelfRACG can retrieve external knowledge that better aligns with the LLM’s own information needs, resulting in superior generation performance compared to vanilla RACG.

Copied to clipboard

Qianli Ma, Dongrui Liu, Qian Chen, Linfeng Zhang, Jing Shao

Challenge:	Existing methods for fine-tuning large language models for specialized tasks are costly and time-consuming.
Approach:	They propose a framework that locates task-specific neurons via gradient-based attribution and dynamically Elects critical neurons through multi-model importance fusion.
Outcome:	The proposed framework reduces harmful response rates while preserving 95% of utility performance.

LibEvolutionEval: A Benchmark and Study for Version-Specific Code Generation (2025.naacl-long)

Copied to clipboard

Sachit Kuhar, Wasi Uddin Ahmad, Zijian Wang, Nihal Jain, Haifeng Qian, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Recent code completion models focus on local file contexts, but do not fully capture the complexities of real-world software development.
Approach:	They propose a version-specific code-completion task across eight libraries as they evolve over the years and an in-depth analysis of two widely used public libraries: PyTorch and Matplotlib.
Outcome:	The proposed model improves performance with public libraries, compared with existing models.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

From Word to World: Can Large Language Models be Implicit Text-based World Models? (2026.acl-long)

Copied to clipboard

Yixia Li, Hongru Wang, Jiahao Qiu, Zhenfei Yin, Dongdong Zhang, Cheng Qian, Zeping Li, Xiaoteng Ma, Guanhua Chen, Heng Ji

Query-as-context Pre-training for Dense Passage Retrieval (2023.emnlp-main)

Challenge:	Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time.
Approach:	They propose a framework that reframes language modeling as next-state prediction under interaction.
Outcome:	The proposed framework evaluates world models in text-based environments . it shows that sufficiently trained models capture coherent environment dynamics .

Copied to clipboard

Xing W, Guangyuan Ma, Wanhui Qian, Zijia Lin, Songlin Hu

Information Retrieval

Challenge:	Existing methods to improve passage retrieval performance by using context-supervised pre-training are weakly correlated.
Approach:	They propose to use query-as-context pre-training to train passage-query pairs . they evaluate the pre-trained models on large-scale passage retrieval benchmarks .
Outcome:	The proposed technique improves performance on large-scale passage retrieval benchmarks and out-of-domain zero-shot benchmarks.

CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval (2026.findings-acl)

Copied to clipboard

Zhipeng Qian, Zihan Liang, Yufei Ma, Ben Chen, Huangyu Dai, Yiwei Ma, Jiayi Ji, Chenyi Lei, Han Li, Xiaoshuai Sun

Multimodality

Challenge:	Existing approaches to search for images using single-modality are limited by representation space fragmentation.
Approach:	They propose a unified representation framework that achieves efficient query-target alignment . they introduce a multi-level Chain-of-Thought prompting strategy that guides MLMs to generate discriminative, semantically compatible captions for target images .
Outcome:	The proposed framework achieves efficient query-target alignment through synergistic components.

Pub-LawBench: Public-Oriented Benchmarking for LegalAI (2026.acl-long)

Copied to clipboard

Qiaoyu Zheng, Zehan Ma, Yijing Zhang, Qiqi Wang, Huijia Li, Qian Liu

Challenge:	Existing evaluation frameworks focus on legal professionals, not legal professionals.
Approach:	They propose a public-oriented LegalAI benchmark grounded in legal functionalism and genre analysis to address this gap.
Outcome:	The proposed model evaluates 17 large language models on Pub-LawBench using simple prompts and Chain-of-Thought under a vanilla inference setting.

Multi-Hop Knowledge Editing via Critic-Guided Multi-Agent Reasoning (2026.findings-acl)

Copied to clipboard

Xudong Li, Yuhang Tian, Dandan Song, Zhijing Wu, Shuhao Zhang, Jun Yang, Yongyu Huo, Changzhi Zhou, Xinyu Zhang, Chenhao Li, Huipeng Ma, Luan Zhang, Yan Xu, Qian Liu

Reasoning

Challenge:	Existing knowledge editing methods rely on unidirectional, feed-forward pipelines . a minor retrieval error or logical mismatch at an early hop can become a silent failure .
Approach:	They propose a framework for closed-loop post-edit reasoning that uses a Critic agent to verify coherence and step-wise correctness.
Outcome:	Experiments on MQuAKE-2002 and MQuADE-hard show that CARE effectively mitigates error propagation . a minor retrieval error or logical mismatch at an early hop can become a silent failure .

BASS: Batched Attention-optimized Speculative Sampling (2024.findings-acl)

Copied to clipboard

Haifeng Qian, Sujan Kumar Gonugondla, Sungsoo Ha, Mingyue Shang, Sanjay Krishna Gouda, Ramesh Nallapati, Sudipta Sengupta, Xiaofei Ma, Anoop Deoras

AnyTrans: Translate AnyText in the Image with Large Scale Models (2024.findings-emnlp)

Challenge:	Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models.
Approach:	They propose a batched speculative decoding system that generates sequences at an average speed of 5.8ms per token and a batch size of 8 at a 2.15 speed-up over optimized regular decoding.
Outcome:	The proposed system achieves state-of-the-art latency and speed-up over optimized regular decoding.

Copied to clipboard

Zhipeng Qian, Pei Zhang, Baosong Yang, Kai Fan, Yiwei Ma, Derek Wong, Xiaoshuai Sun, Rongrong Ji

Multilinguality

Challenge:	Recent advances in natural language processing and computer vision have made it possible to translate images with text in one language into equivalent images displaying that text translated into another language.
Approach:	They propose an all-encompassing framework for the task–In-Image Machine Translation (IIMT) that incorporates contextual cues from both textual and visual elements during translation.
Outcome:	The proposed framework can be constructed using open-source models and requires no training, making it highly accessible and expandable.

Evaluating Large Language Models on Controlled Generation Tasks (2023.emnlp-main)

Copied to clipboard

Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu, Qian Hu, Rahul Gupta, John Wieting, Nanyun Peng, Xuezhe Ma

Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation (2026.findings-acl)

Challenge:	Recent studies have looked into the ability of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc. However, few studies investigate the controllability of large languages.
Approach:	They propose to compare large language models with state-of-the-start finetuned smaller models to find that large language model controls are comparable to smaller models.
Outcome:	The proposed model can meet hard constraints and perform better than state-of-the-art models.

Copied to clipboard

Qian Ma, Sarah Rajtmajer

LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection (2025.findings-acl)

Challenge:	Large language models (LLMs) are a powerful tool for creating synthetic replicas of private text.
Approach:	They propose a method for creating privacy-preserving synthetic data using private seeds and a formal differential privacy mechanism.
Outcome:	The proposed method achieves high fidelity to private data while providing strong privacy protection.

Copied to clipboard

Tianyi Ma, Yiyue Qian, Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye

Saber: Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model in Code Generation (2026.acl-long)

Challenge:	Existing approaches to combat illicit drug trafficking are impractical due to the scarcity of labeled samples and imbalance of classes.
Approach:	They propose a Large Language Model-empowered Heterogeneous Graph Prompt Learning framework for illicit drug trafficking detection that leverages LLM to facilitate heterogeneous graph neural networks to effectively identify minority classes.
Outcome:	The proposed framework is able to identify minority classes in class-imbalanced scenarios.

Copied to clipboard

Yihong Dong, Zhaoyu Ma, Xue Jiang, Zhiyuan Fan, Jiaru Qian, Yongmin Li, Jianha Xiao, Zhi Jin, Ge Li

Dynamic Open-book Prompt for Conversational Recommender System (2023.findings-emnlp)

Challenge:	Diffusion language models (DLMs) offer advantages in parallel generation and bidirectional context modeling, but they face a critical trade-off between inference speed and output quality for tasks with strict structural constraints such as code generation.
Approach:	They propose an efficient sampling algorithm that reduces the number of tokens unmasked per step based on the model’s evolving confidence.
Outcome:	The proposed method improves Pass@1 accuracy by 1.9% while achieving 251.4% inference speedup.

Copied to clipboard

Xuan Ma, Tieyun Qian, Ke Sun

Low-Resource NLP

Challenge:	Existing methods for prompt learning use only training samples for parameter training, limiting the performance of existing methods.
Approach:	They propose a Dynamic Open-book Prompt approach where the open book stores user's experiences in historical data and dynamically constructs the prompt to memorize the user' s current utterance.
Outcome:	The proposed model improves on the existing methods on the ReDial dataset and shows that it can be used to learn contextually relevant recommendations.

Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings (2023.emnlp-main)

Copied to clipboard

Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Chong Deng, Hai Yu, Jiaqing Liu, Yukun Ma, Chong Zhang

CodeFort: Robust Training for Code Generation Models (2024.findings-emnlp)

Challenge:	Prior studies diagnose the anisotropy problem in sentence embeddings from pre-trained language models without fine-tuning.
Approach:	They propose an unsupervised method that weights words with model-based importance estimations and computes the weighted average of word representations from pre-trained models as sentence embeddings.
Outcome:	Empirical evaluations show that the proposed method can alleviate the anisotropy problem and improve various pre-trained models on the STS benchmarks.

Copied to clipboard

Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras

Cross-Lingual Transfer Learning for Speech Translation (2025.naacl-short)

Challenge:	Existing research efforts to improve code generation models are inadequate . code generation model performance is degraded under small perturbations .
Approach:	They propose a framework to improve the robustness of code generation models by generalizing code perturbations to enrich training data and enabling various robust training strategies.
Outcome:	The proposed framework increases pass rates and robustness drop rate against code-syntax perturbations.

Copied to clipboard

Rao Ma, Mengjie Qian, Yassir Fathullah, Siyuan Tang, Mark Gales, Kate Knill

Multilinguality

Challenge:	Increasing interest in building multilingual foundation models for NLP and speech research has led to limited data collection for training ST systems.
Approach:	They propose to use Whisper to explore the behavior of multilingual speech foundation models with restricted data.
Outcome:	The proposed model can translate to Chinese with a single language, and it can perform transcriptions in other languages.

Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification (2026.findings-acl)

Copied to clipboard

Qian Ma, Qiong Wu, Zhengyi Zhou, Yao Ma

Multimodality

Challenge:	Existing multi-modal retrieval augmented generation (MM-RAG) methods tightly couple entity discrimination and section-level evidence ranking into a single re-ranking stage, leading to high cost and limited generalization.
Approach:	They propose a framework that decouples entity identification from section-level re-ranking.
Outcome:	The proposed framework outperforms fine-tuned multi-modal re-ranking baselines while reducing training and inference complexity.

Diff4TST: Masked Diffusion Language Model for Text Style Transfer (2026.acl-long)

Copied to clipboard

Xinchen Ma, Gaole He, Yunshi Lan, Weining Qian

Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models (2025.findings-emnlp)

Challenge:	Existing methods for text style transfer rely on task-specific training and expensive training stages.
Approach:	They propose a diffusion-based language model that formulates text style transfer as an explicit copy-and-edit process.
Outcome:	The proposed model improves style accuracy and controllability while maintaining strong content preservation and fluency.

Copied to clipboard

Zezhou Wang, Yaxin Du, Xingjun Ma, Yu-Gang Jiang, Zhuzhong Qian, Siheng Chen

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

Challenge:	Federated domain-specific instruction tuning (FedDIT) for large language models (LLMs) aims to enhance performance in specialized domains using distributed private and limited data.
Approach:	They introduce an algorithm that explicitly maximizes cross-client domain coverage through diversity-oriented client center selection and retrieval-based augmentation.
Outcome:	The proposed algorithm achieves performance gains of 29.19% and domain coverage improvements of 4.82%-21.36% over 11 baselines.

Copied to clipboard

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

Guangwei Zhang, Jianing Zhu, Cheng Qian, Neil Zhenqiang Gong, Rada Mihalcea, Zhaozhuo Xu, Jingrui He, Jiaqi W. Ma, Chaowei Xiao, Bo Li, Ahmed Abbasi, Dongwon Lee, Heng Ji, Denghui Zhang

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

Paraphrasing

Challenge:	Copyright Detective is the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs.
Approach:	They propose a system that detects copyright infringements and visualizes them . they use content recall testing, paraphrase-level similarity analysis and persuasive jailbreak probing .
Outcome:	The proposed system detects, analyzes, and visualizes potential copyright risks in LLM outputs.

Counterfactual Inference for Text Classification Debiasing (2021.acl-long)

Copied to clipboard

Chen Qian, Fuli Feng, Lijie Wen, Chunping Ma, Pengjun Xie

Robustness in NLP

Challenge:	Existing methods to capture unintended dataset biases are expensive and require elaborate balancing strategies.
Approach:	They propose a model-agnostic text classification debiasing framework which can effectively avoid employing data manipulations or designing balancing mechanisms.
Outcome:	The proposed framework can effectively avoid data manipulations or designing balancing mechanisms to capture unintended dataset biases.

How Can Synthetic Data Improve Multilingual Language Model Pretraining? A Data Quality Perspective (2026.acl-long)

Copied to clipboard

Tongyao Zhu, Qian Liu, Chang Ma, Jinghan Zhang, Longxu Dou, Junxian He, Shiqi Chen

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation (2025.acl-long)

Challenge:	Low-resource languages are a long-tail problem for multilingual LLMs due to limited high-quality training data.
Approach:	They propose a method that translates high-quality, knowledge-rich English data into low-resource languages . they propose SynRank, which leverages synthetic data as positive samples to train a classifier .
Outcome:	The proposed method matches handcrafted rule-based filtering by human experts and significantly improves knowledge-intensive tasks with less data.

Copied to clipboard

Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Weipeng Jiang, Qian Wang, Chao Shen, Yang Liu

Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation.
Approach:	They propose to use a dataset to investigate a new type of bias in Large Language Models for code generation, provider bias, to determine whether the model favors specific providers.
Outcome:	The proposed model favors services from Google and Amazon, but without explicit directives, and can modify input code to incorporate their preferred providers without user requests.

Copied to clipboard

Rao Ma, Mengjie Qian, Vyas Raina, Mark Gales, Kate Knill

Multimodality

Challenge:	acoustic adversarial attacks on speech LLMs may make them more vulnerable to adversarials . flexible speech encoders and large language models have enabled speech Llms to handle a wide range of processing tasks.
Approach:	They investigate universal adversarial attacks on speech LLMs by pre-trained speech encoders and large language models.
Outcome:	The proposed model can handle a wide range of spoken language processing tasks.

Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs (2024.findings-emnlp)

Copied to clipboard

Kexin Ma, Ruochun Jin, Wang Haotian, Wang Xi, Huan Chen, Yuhua Tang, Qian Wang