Papers by Zheng Ma

A Survey of LLM-based Agents in Medicine: How far are we from Baymax? (2025.findings-acl)

Challenge:	Existing code sandboxes fail to provide accurate verification and efficiency under high-concurrency workloads.
Approach:	They propose a high-fidelity code verification system that provides sandbox feedback for RL training and evaluation.
Outcome:	The proposed system outperforms heuristic-matching baselines on LiveCodeBench and training stability on high-concurrency workloads.

Copied to clipboard

Wenxuan Wang, Zizhan Ma, Zheng Wang, Chenghan Wu, Jiaming Ji, Wenting Chen, Xiang Li, Yixuan Yuan

MTA:A Merge-then-Adapt Framework for Personalized Large Language Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) are transforming healthcare through their ability to understand and assist with medical tasks.
Approach:	They analyze system profiles, clinical planning, medical reasoning frameworks, and external capacity enhancement.
Outcome:	The findings highlight the future directions in medical reasoning, physical system integration, and training simulations.

Copied to clipboard

Xiaopeng Li, Yuanjin Zheng, Wanyu Wang, Wenlin Zhang, Pengyue Jia, Yingyi Zhang, Haiying He, Mengyang Ma, Yiqi Wang, Maolin Wang, Xuetao Wei, Xiangyu Zhao

Unified Thinker: A General Reasoning Core for Image Generation (2026.acl-long)

Challenge:	Personalized Large Language Models (PLLMs) aim to align outputs with individual user preferences . current methods of fine-tuning a separate module for each user are unscalable .
Approach:	They propose a Merge-then-Adapt framework for Personalized Large Language Models . they construct a shared Meta-LoRA bank and propose an Adaptive LoRA Fusion stage .
Outcome:	The proposed framework outperforms existing SOTA methods on the LaMP benchmark.

Copied to clipboard

Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao

IMOL: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video Detection (2025.acl-long)

Challenge:	generative models struggle with logic-intensive instruction following, exposing a persistent reasoning–execution gap.
Approach:	They propose a task-agnostic reasoning architecture for general image generation . they propose pixel-level feedback to ground the Thinker's policy in pixel feedback .
Outcome:	The proposed system significantly improves image reasoning and generation quality.

Copied to clipboard

Zhi Zeng, Jiaying Wu, Minnan Luo, Herun Wan, Xiangzheng Kong, Zihan Ma, Guang Dai, Qinghua Zheng

Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization (2026.acl-long)

Challenge:	Existing methods for fake news video detection focus on a specific domain and assume multiple modalities.
Approach:	They propose an incomplete-modality-tolerant learning framework for fake news video detection . they use cross-modal consistency to reconstruct missing modalities and transferable knowledge through cross-sample reasoning .
Outcome:	The proposed framework improves performance and robustness of multi-domain fake news video detection while generalizing to unseen domains under incomplete modality conditions.

Copied to clipboard

Tian Xueyun, MingHua Ma, Bingbing Xu, Nuoyan Lyu, Wei Li, Heng Dong, Zheng Chu, Yuanzhuo Wang, Huawei Shen

Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters (2024.acl-long)

Challenge:	Recent studies show that supervised fine-tuning (SFT) is a common approach for reasoning in large language models.
Approach:	They propose to use supervised fine-tuning (SFT) on chain-of-thought trajectories demonstrations . they find that incorporating negative traxories yields substantial OOD generalization gains .
Outcome:	The proposed scheme yields 5.51% OOD gain over positive-only training.

Copied to clipboard

Yinghui Li, Zishan Xu, Shaoshen Chen, Haojing Huang, Yangning Li, Shirong Ma, Yong Jiang, Zhongli Li, Qingyu Zhou, Hai-Tao Zheng, Ying Shen

Visual Data in NLP

Challenge:	Existing studies focus on misspelled characters, ignoring faked characters which are more common and difficult to correct.
Approach:	They propose to use Chinese character checking to identify and correct wrong characters in texts by human annotation.
Outcome:	The proposed dataset is the first real-world visual and the largest human-crafted dataset for the Chinese character checking scenario.

XLM-E: Cross-lingual Language Model Pre-training via ELECTRA (2022.acl-long)

Copied to clipboard

Zewen Chi, Shaohan Huang, Li Dong, Shuming Ma, Bo Zheng, Saksham Singhal, Payal Bajaj, Xia Song, Xian-Ling Mao, Heyan Huang, Furu Wei

PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)

Challenge:	ELECTRA-style tasks are used to pretrain cross-lingual models for NLP tasks . masked language modeling tasks require massive computation resources, rendering such models quite expensive .
Approach:	They propose to use ELECTRA-style tasks to pre-train a cross-lingual language model . they propose to pretrain the model on multilingual and parallel corpora .
Outcome:	The proposed model outperforms baseline models on cross-lingual understanding tasks with much less computation cost.

Copied to clipboard

Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang

MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production (2024.findings-acl)

Challenge:	PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks.
Approach:	They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks.
Outcome:	The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods.

Copied to clipboard

Jian Ma, Wenguan Wang, Yi Yang, Feng Zheng

KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model’s Reasoning Path Aggregation (2025.findings-acl)

Challenge:	Existing solutions for sign language production are limited due to phonological differences and data scarcity.
Approach:	They propose a unified framework for continuous sign language production that generates sign predictions step by step from text or speech embeddings.
Outcome:	The proposed model achieves competitive performance on how2sign and PHOENIX14T datasets.

Copied to clipboard

Siyuan Fang, Kaijing Ma, Tianyu Zheng, Xeron Du, Ningxuan Lu, Ge Zhang, Qingkun Tang

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models (2023.acl-long)

Challenge:	Existing methods for large language models (LLMs) are limited by step-by-step decision-making on KGs, or require fine-tuning or pre-training on specific KG.
Approach:	They propose a framework that harnesses the global planning abilities of large language models (LLMs) for efficient and accurate KG reasoning.
Outcome:	Extensive experiments show that the proposed framework achieves state-of-the-art performance in KGQA tasks, delivering both high efficiency and accuracy.

Copied to clipboard

Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang, Shiqing Ma

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

Challenge:	Existing backdoor attacks against prompt-based learning involve injecting back doors into embedding layers or word embedders.
Approach:	They propose a backdoor attack against prompt-based learning that injects backdoors into embedding layers or word embeddable vectors.
Outcome:	The proposed backdoor attack outperforms two state-of-the-art models on six NLP tasks and three prompting strategies.

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.

LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Copied to clipboard

Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai

Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning (2025.findings-emnlp)

Challenge:	Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach:	They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome:	The proposed model achieves comparable performance to standard dense models with more parameters.

Copied to clipboard

Yihong Tang, Ao Qu, Zhaokai Wang, Dingyi Zhuang, Zhaofeng Wu, Wei Ma, Shenhao Wang, Yunhan Zheng, Zhan Zhao, Jinhua Zhao

Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation (D19-1)

Challenge:	Currently, vision-language models excel in many downstream tasks but struggle with spatial reasoning, which is crucial for navigation and interaction with physical environments.
Approach:	They propose a framework that generates synthetic data to provide targeted supervision for VLMs across these basic spatial capabilities.
Outcome:	The proposed framework disentangles 2D spatial reasoning into three core components: direction comprehension, distance estimation, and localization.

Copied to clipboard

Baigong Zheng, Renjie Zheng, Mingbo Ma, Liang Huang

CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction (2023.emnlp-main)

Challenge:	Recent work on simultaneous translation is difficult because of its latency and quality.
Approach:	They propose a supervised-learning framework to learn adaptive policies from parallel text sequences . they use a model that predicts when a target word is read or WRITE if context provides enough information .
Outcome:	Experiments on German=>English show that the proposed method can learn flexible policies with better BLEU scores and similar latencies compared to previous work.

Copied to clipboard

Jingheng Ye, Yinghui Li, Qingyu Zhou, Yangning Li, Shirong Ma, Hai-Tao Zheng, Ying Shen

Robustness in NLP

Challenge:	Evaluating the performance of Grammatical Error Correction systems is a challenging task due to its subjectivity.
Approach:	They propose a method to evaluate GEC systems in multi-reference evaluation setting . they use consistent edit boundaries to eliminate bias caused by inconsistent edit boundaries .
Outcome:	The proposed evaluation metric eliminates bias caused by inconsistent edit boundaries on six English reference sets.

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

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.

Automated Fine-Grained Mixture-of-Experts Quantization (2025.findings-acl)

Copied to clipboard

Zhanhao Xie, Yuexiao Ma, Xiawu Zheng, Fei Chao, Wanchen Sui, Yong Li, Shen Li, Rongrong Ji

Green & Sustainable NLP

Challenge:	specialized quantization framework for Mixture of Experts architectures is inadequate for model compression.
Approach:	They propose a specialized quantization framework for Mixture of Experts architectures . they find that expert networks exhibit distinctive channel-wise outlier distributions ."
Outcome:	The proposed framework improves on the Mixtral-8x7b-v0.1 architecture while maintaining minimal computational overhead.

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

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

Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR (2021.findings-acl)

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

Junkun Chen, Mingbo Ma, Renjie Zheng, Liang Huang

Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension (2022.acl-long)

Challenge:	Existing approaches to simultaneous speech-to-text translation suffer from error propagation and extra latency.
Approach:	They propose a new paradigm for simultaneous speech-to-text translation using two separate decoders . they use multitask learning to jointly learn these two tasks with a shared encoder .
Outcome:	The proposed method achieves substantially better translation quality at similar levels of latency.

Copied to clipboard

Ying Xu, Dakuo Wang, Mo Yu, Daniel Ritchie, Bingsheng Yao, Tongshuang Wu, Zheng Zhang, Toby Li, Nora Bradford, Branda Sun, Tran Hoang, Yisi Sang, Yufang Hou, Xiaojuan Ma, Diyi Yang, Nanyun Peng, Zhou Yu, Mark Warschauer

Question Answering

Challenge:	Existing QA datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements.
Approach:	They propose to use FairytaleQA to generate 10,580 questions based on 278 children-friendly stories to assess model's fine-grained learning skills.
Outcome:	The proposed dataset consists of 10,580 questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations.

Can LLMs Learn From Mistakes? An Empirical Study on Reasoning Tasks (2024.findings-emnlp)

Copied to clipboard

Shengnan An, Zexiong Ma, Siqi Cai, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen

PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization (2025.findings-acl)

Challenge:	Existing work has shown that simple learning can enhance the chain-of-thought (CoT) reasoning of large language models.
Approach:	They construct mistake-correction datasets to identify and correct mistakes in CoTs . they conclude that LLMs can learn from mistakes to enhance their CoT reasoning .
Outcome:	The proposed datasets show that LLMs can learn from mistakes to enhance their CoT reasoning performance.

Copied to clipboard

Zouying Cao, Runze Wang, Yifei Yang, Xinbei Ma, Xiaoyong Zhu, Bo Zheng, Hai Zhao

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

Challenge:	Existing LLM agents generate verbose and inefficient natural language plans to guide reasoning, which restricts agents’ ability to generalize across similar tasks.
Approach:	They propose a pseudocode-style planning guide optimization method that captures the structural logic of reasoning and uses two planning-oriented rewards to enhance agent learning.
Outcome:	The proposed method outperforms existing LLM agents on representative agent benchmarks and outperformed the current leading baselines.

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.

FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)

Copied to clipboard

Zichen Tang, Haihong E, Ziyan Ma, Haoyang He, Jiacheng Liu, Zhongjun Yang, Zihua Rong, Rongjin Li, Kun Ji, Qing Huang, Xinyang Hu, Yang Liu, Qianhe Zheng

Simultaneous Translation with Flexible Policy via Restricted Imitation Learning (P19-1)

Challenge:	Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity.
Approach:	They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems.
Outcome:	The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging.

Copied to clipboard

Baigong Zheng, Renjie Zheng, Mingbo Ma, Liang Huang

Machine Translation

Challenge:	Existing approaches to simultaneous translation have been limited and use fixed-latency policies or a complicated two-staged model.
Approach:	They propose a single model that adds a “delay” token to the target vocabulary and a restricted dynamic oracle to greatly simplify training.
Outcome:	The proposed model achieves better BLEU scores and lower latencies compared to fixed and RL-learned policies on Chinese -> English simultaneous translation.

Incremental Sequence Labeling: A Tale of Two Shifts (2024.findings-acl)

Copied to clipboard

Shengjie Qiu, Junhao Zheng, Zhen Liu, Yicheng Luo, Qianli Ma

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning (2026.findings-acl)

Challenge:	Existing approaches to incremental sequence labeling have focused on the E2O and O2E issues, but neglect the O2e issue.
Approach:	They propose a framework for incremental sequence labeling without semantic shifts that mitigate catastrophic forgetting in models by using knowledge distillation to maintain the model’s discriminative ability for old entities.
Outcome:	The proposed framework mitigates catastrophic forgetting in models while maintaining discriminative ability for old entities while minimizing the model’s bias towards new entities.

Copied to clipboard

Zheng Li, Qingxiu Dong, Jingyuan Ma, Di Zhang, Kai Jia, Zhifang Sui

Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)

Challenge:	Recent large reasoning models have shown exceptional performance on various tasks, but they consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency.
Approach:	They propose a self-adaptive reasoning strategy that automatically allocates budgets according to problem complexity and introduces GRPO for reinforcement learning to reduce output length.
Outcome:	The proposed model achieves an average response length compression of 61% on math reasoning tasks while maintaining accuracy.

Copied to clipboard

Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye, Shengjie Ma, Jianping Zhang

Logic: Long-form Outline Generation via Imitative and Critical Self-refinement (2025.findings-emnlp)

Challenge:	Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps.
Approach:	They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level.
Outcome:	Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models.

Copied to clipboard

Hengwei Liu, Yongliang Shen, Zhe Zheng, Haoyuan Ma, Xingyu Wu, Yin Zhang, Weiming Lu

Information Retrieval

Challenge:	Existing methods for long-form outline generation have low knowledge density and lack detail . retrieval-augmented approaches struggle to maintain logical coherence across retrieved information .
Approach:	They propose a system that mimics human writers' refinement process by mimicking outlines through imitation and critical self-refinement.
Outcome:	The proposed system improves on the FreshWiki and WikiOutline datasets and establishes a coherent planning framework and structured knowledge base.

STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)

Copied to clipboard

Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang

emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation (2024.findings-acl)

Challenge:	Simultaneous translation is notoriously dif- ficult due to word-order differences.
Approach:	They propose a prefix-to-prefix framework that implicitly learns to anticipate in a single translation model.
Outcome:	The proposed framework achieves low latency and reasonable qual- ity on 4 directions.

Copied to clipboard

Ziyang Ma, Zhisheng Zheng, Jiaxin Ye, Jinchao Li, Zhifu Gao, ShiLiang Zhang, Xie Chen

Well Begun Is Half Done: An Implicitly Augmented Generative Framework with Distribution Modification for Hierarchical Text Classification (2024.lrec-main)

Challenge:	Existing models for speech emotion recognition are not suitable for emotional tasks.
Approach:	They propose a universal speech emotion representation model that is pre-trained on open-source emotion data.
Outcome:	euphoria2vec outperforms state-of-the-art models and emotion specialist models . it shows consistent improvements among 10 different languages of speech emotion recognition datasets .

Copied to clipboard

Huawen Feng, Jingsong Yan, Junlong Liu, Junhao Zheng, Qianli Ma

Simultaneous Translation Policies: From Fixed to Adaptive (2020.acl-main)

Challenge:	Hierarchical Text Classification (HTC) is a challenging task which aims to extract the labels in a tree structure corresponding to a given text.
Approach:	They propose an explicit-agmented-generativ-e framework with distribution modification for hierarchical text classification.
Outcome:	The proposed framework improves on the initial distributions of tail classes and avoids misinterpreting predictions on unbalanced data.

Copied to clipboard

Baigong Zheng, Kaibo Liu, Renjie Zheng, Mingbo Ma, Hairong Liu, Liang Huang

Opportunistic Decoding with Timely Correction for Simultaneous Translation (2020.acl-main)

Challenge:	Adaptive policies can balance translation quality and latency based on context information . previous methods on obtaining adaptive policies rely on complicated training process .
Approach:	They propose to obtain adaptive policies by a simple heuristic composition of fixed policies . they propose to use a heurism to obtain policies that can outperform fixed ones .
Outcome:	Experiments on Chinese -> English and German -> english show that adaptive policies outperform fixed policies by up to 4 BLEU points for the same latency.

Copied to clipboard

Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Liang Huang

Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training (2020.findings-emnlp)

Challenge:	Existing approaches to balancing translation quality and latency are either too aggressive or too conservative.
Approach:	They propose an opportunistic decoding technique that always (over-)generates a certain mount of extra words at each step to keep the audience on track with the latest information.
Outcome:	The proposed technique reduces latency and increases BLEU with no over-generating . it also corrects mistakes in the overgenerated words when observing more context .

Copied to clipboard

Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Jiahong Yuan, Kenneth Church, Liang Huang

Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation (D18-1)

Challenge:	Current approaches to simultaneous speech-to-speech translation accumulate more and more latencies in later sentences when the speaker talks faster.
Approach:	They propose a method which generates more fluent target speech latency than the baseline . they propose to use self-adaptive translation to adjust the length of translations to accommodate different source speech rates.
Outcome:	Xiong et al., 2019) show that the proposed method generates more fluent target speech latency than baseline . authors say it provides more natural communication process than speech-to-text translation . xiong and colleagues say the proposed technique is more efficient than current approaches .

Copied to clipboard

Renjie Zheng, Mingbo Ma, Liang Huang

MKT: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain Chinese Spelling Correction (2025.emnlp-industry)

Challenge:	Neural text generation has been quite successful recently, but during training time, only one reference is considered for each example, even though there are often multiple references available.
Approach:	They propose an algorithm to generate exponentially many pseudo-references by compressing existing references into lattices and traversing them to generate new pseudo-References.
Outcome:	The proposed model significantly improves on baselines in machine translation and image captioning, and is comparable to existing models.

Copied to clipboard

Peng Xing, Yinghui Li, Shirong Ma, Xinnian Liang, Haojing Huang, Yangning Li, Shu-Yu Guo, Hai-Tao Zheng, Wenhao Jiang, Ying Shen

Green & Sustainable NLP

Challenge:	Chinese Spelling Correction (CSC) is a model that detects and corrects spelling errors in given sentences.
Approach:	They propose a model-agnostic model with an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain rather than focusing solely on new domain knowledge.
Outcome:	The proposed model-agnostic framework is based on an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain, rather than focusing solely on new domain knowledge.

Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference (2026.findings-eacl)

Copied to clipboard

Han Yuan, Yue Zhao, Li Zhang, Wuqiong Luo, Zheng Ma

From Conversation to Evaluation: Benchmarking LLMs on Development Knowledge via SimpleDevQA (2026.findings-acl)

Challenge:	Prior studies have examined the impact of structured output on LLMs’ generation quality, often presenting one-way findings.
Approach:	They propose to derive five potential causal structures characterizing the influence of structured output on LLMs’ generation using one assumed and two guaranteed constraints.
Outcome:	The proposed pipeline can be extended to other modules and is not limited to structured output but can be used in industrial applications.

Copied to clipboard

Jing Zhang, Lianghong Guo, Yanlin Wang, Terry Yue Zhuo, Yong Wang, Mingwei Liu, Jiachi Chen, Ensheng Shi, Yuchi Ma, Hongyu Zhang, Zibin Zheng

Natural Language Interfaces

Challenge:	Existing Dev Knowledge QA benchmarks are limited in development knowledge scope and often not built from real user queries.
Approach:	They conduct preliminary analysis of real user–LLM dialogues from WildChat to investigate the importance of Dev Knowledge QA in AI-assisted software development scenarios.
Outcome:	The proposed benchmark is based on real user–LLM dialogues from WildChat.

SMARTMiner: Extracting and Evaluating SMART Goals from Low-Resource Health Coaching Notes (2025.findings-emnlp)

Copied to clipboard

Iva Bojic, Qi Chwen Ong, Stephanie Hilary Xinyi Ma, Lin Ai, Zheng Liu, Ziwei Gong, Julia Hirschberg, Andy Hau Yan Ho, Andy W. H. Khong

MixRED: A Mix-lingual Relation Extraction Dataset (2024.lrec-main)

Challenge:	SMARTMiner extracts specific, measurable, attainable, relevant, time-bound (SMART) goals from unstructured health coaching notes.
Approach:	They propose a framework for extracting and evaluating specific, measurable, attainable, relevant, time-bound (SMART) goals from unstructured health coaching notes.
Outcome:	The framework extracts behavior change goal spans and categorizes their SMARTness.

Copied to clipboard

Lingxing Kong, Yougang Chu, Zheng Ma, Jianbing Zhang, Liang He, Jiajun Chen

Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Challenge:	Existing research focuses on monolingual relation extraction, but there is a significant gap in understanding relation extraction in the mix-lingual scenario.
Approach:	They propose a task of considering relation extraction in the mix-lingual scenario . they construct a human-annotated dataset to support the task .
Outcome:	The proposed task evaluates state-of-the-art supervised models and large language models on the human-annotated dataset MixRED.

Copied to clipboard

Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li

Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings (2021.emnlp-main)

Challenge:	Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach:	They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome:	The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.

Copied to clipboard

Junkun Chen, Renjie Zheng, Atsuhito Kita, Mingbo Ma, Liang Huang

HiGoE: Hierarchical Graph of Evidence to Enhance Retrieval-Augmented Generation for Long-context Summarization (2026.acl-long)

Challenge:	Existing systems for simultaneous translation are still trained on full-sentence bitexts due to the abundance of unnecessary long-distance reorderings.
Approach:	They propose to rewrite target side of existing full-sentence corpora into simultaneous-style translation by adding generated pseudo-references to the target side.
Outcome:	Experiments on ZhEn and JaEn simultaneous translation show that the proposed method improves on existing full-sentence corpora.

Copied to clipboard

Long Yuan, Kaiwen Tian, Zi Chen, Bolong Zheng, Chuan Ma

Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning (2026.findings-acl)

Challenge:	Existing methods for long-context summarization fail to capture high-level thematic structures and long-range dependencies.
Approach:	They propose a hierarchical Graph of Evidence to reduce hallucination and attention dilution by replacing unreliable chunk-based methods with a filtered proposition–evidence graph.
Outcome:	Experiments show that HiGoE surpasses baselines in quality and efficiency.

Copied to clipboard

Zheng Wu, Xingyu Lou, Xinbei Ma, Yansi Li, Weiwen Liu, Weinan Zhang, Jun Wang, Zhuosheng Zhang

ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization (2026.findings-acl)

Challenge:	Large Language Model (LLM)-based agents extend the utility of LLMs by interacting with dynamic environments.
Approach:	They propose a parameter fusion framework based on directional consensus evaluation that disentangles knowledge updates through a two-stage process.
Outcome:	The proposed framework disentangles knowledge updates through a two-stage process with minimal computational overhead and parameter updates.

Copied to clipboard

null Liaokunpeng, Yuexiao Ma, Yisheng Lin, Hualin Zeng, Xiawu Zheng, Rongrong Ji

PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents (2026.eacl-industry)

Challenge:	Recent LLM-based systems require simulation of algorithm flow and video rendering constraints.
Approach:	They propose a paradigm that decouples algorithm execution from rendering.
Outcome:	The proposed paradigm reduces execution success rates, element overlap, and inter-frame inconsistencies.

Copied to clipboard

Minjia Wang, Yunfeng Wang, Xiao Ma, Dexin Lv, Qifan Guo, Lynn Zheng, Benliang Wang, Lei Wang, Jiannan Li, Yongwei Xing, Junzhe Xu, Zheng Sun

Challenge:	Publicly available corpora cover only slivers of human activity, such as email threads, chat logs, purchase histories, sensor traces, and provide large-scale supervision for data-hungry machine-learning pipelines.
Approach:	They propose a method for synthesizing realistic digital footprints using large language model agents from a structured user profile.
Outcome:	The proposed method generates diverse sequences of user events, producing corresponding digital artifacts such as emails, messages, calendar entries, reminders, etc.

Retrieve-and-Sample: Document-level Event Argument Extraction via Hybrid Retrieval Augmentation (2023.acl-long)

Copied to clipboard

Yubing Ren, Yanan Cao, Ping Guo, Fang Fang, Wei Ma, Zheng Lin

Information Retrieval

Challenge:	Recent studies show the effectiveness of retrieval augmentation in many generative NLP tasks.
Approach:	They investigate retrieval settings from the input and label distribution views . they further augment document-level EAE with pseudo demonstrations sampled from event semantic regions .
Outcome:	The proposed methods can augment document-level EAE with pseudo demonstrations . the methods can be used in generative NLP tasks such as dialogue response generation .

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

Joint Constrained Learning with Boundary-adjusting for Emotion-Cause Pair Extraction (2023.acl-long)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Huawen Feng, Junlong Liu, Junhao Zheng, Haibin Chen, Xichen Shang, Qianli Ma

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (2025.findings-acl)

Challenge:	Emotion-Cause Pair Extraction (ECPE) aims to identify the document’s emotion clauses and corresponding cause clauses.
Approach:	They propose a constrained learning framework with boundary-adjusting for Emotion-Cause Pair Extraction that summarizes prior rules and forces the model to take them into consideration in optimization.
Outcome:	The proposed framework achieves competitive results compared with state-of-the-art methods on unbalanced data and proves robustness on unbalancing data.

Copied to clipboard

Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen

Characterizing the Impacts of Instances on Robustness (2023.findings-acl)

Challenge:	Image captioning has been a challenge for vision-language researchers for decades . current VLMs focus on tasks like visual question answering (YA) but image captioning is not as advanced as expected.
Approach:	They evaluate VLMs' performance on image captioning using human annotations . they find that some metrics show high caption-level agreement with humans .
Outcome:	The proposed model outperforms open-source models on image captioning . it achieves 93.4% correlation with human rankings at $4 per test .

Copied to clipboard

Rui Zheng, Zhiheng Xi, Qin Liu, Wenbin Lai, Tao Gui, Qi Zhang, Xuanjing Huang, Jin Ma, Ying Shan, Weifeng Ge

Robustness in NLP

Challenge:	Existing defense approaches focus on developing new model structures or training algorithms, but they do little to tap the potential of training instances.
Approach:	They propose a method that can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training.
Outcome:	The proposed method can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training.

EERPD: Leveraging Emotion and Emotion Regulation for Improving Personality Detection (2025.coling-main)

Copied to clipboard

Zheng Li, Sujian Li, Dawei Zhu, Qilong Ma, Weimin Xiong

Sentiment Analysis

Challenge:	Existing methods for personality detection ignore the connection between psychological knowledge “emotion regulation” and personality traits.
Approach:	They propose to use emotion regulation and emotion features to retrieve few-shot samples and provide process CoTs for inferring labels from text.
Outcome:	The proposed method outperforms SOTA by 15.05/4.29 on the two benchmark datasets.

MindAgent: Emergent Gaming Interaction (2024.findings-naacl)

Copied to clipboard

Ran Gong, Qiuyuan Huang, Xiaojian Ma, Yusuke Noda, Zane Durante, Zilong Zheng, Demetri Terzopoulos, Li Fei-Fei, Jianfeng Gao, Hoi Vo

When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation (2026.findings-acl)

Challenge:	Large foundation models (LFMs) can perform complex scheduling in a multi-agent system and can coordinate agents to complete complex tasks that require extensive collaboration.
Approach:	They propose a gaming-based infrastructure that evaluates LFMs' planning and coordination capabilities in the context of gaming interaction.
Outcome:	The proposed infrastructure can be deployed in a customized VR version of Cuisineworld and adapted in the “Minecraft” domain.

Copied to clipboard

Yahan Zheng, John J. Guerrerio, Soroush Vosoughi, Weicheng Ma

Cross-domain Named Entity Recognition via Graph Matching (2022.findings-acl)

Challenge:	Preprocessing-based methods for stereotype mitigation are widely used in NLP . preprocessing methods cause unintended shifts in attention flow, authors say .
Approach:	They propose to use preprocessing-based methods to reduce stereotypes for targeted groups . they find that stereotyping or counter-stereotyping can increase for other demographics .
Outcome:	The proposed methods often induce unintended shifts across demographics, the authors show . they show that such side effects are not accompanied by large changes in attention flow .

Copied to clipboard

Junhao Zheng, Haibin Chen, Qianli Ma

Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition (2022.emnlp-main)

Challenge:	Empirical results show that our method outperforms a series of transfer learning, multitask learning, and few-shot learning methods due to the data scarcity in the real-world scenario.
Approach:	They propose to model the label relationship as a probability distribution and construct label graphs in both source and target label spaces.
Outcome:	Empirical results show that the proposed method outperforms transfer learning, multi-task learning, and few-shot learning methods on four datasets.

Copied to clipboard

Junhao Zheng, Zhanxian Liang, Haibin Chen, Qianli Ma

Speculative Beam Search for Simultaneous Translation (D19-1)

Challenge:	Existing methods for Named Entity Recognition (NER) are not able to learn Other-Class in the same way as new entity types.
Approach:	They propose a unified causal framework to retrieve causality from new entity types and Other-Class.
Outcome:	The proposed method outperforms the state-of-the-art method on three benchmark datasets.

Copied to clipboard

Renjie Zheng, Mingbo Ma, Baigong Zheng, Liang Huang

StableMoE: Stable Routing Strategy for Mixture of Experts (2022.acl-long)

Challenge:	Beam search is widely used in (full-sentence) machine translation but its application to simultaneous translation remains highly non-trivial.
Approach:	They propose a beam search algorithm that hallucinates several steps into the future to reach a more accurate decision by implicitly benefiting from a target language model.
Outcome:	The proposed method improves on language models over diverse language pairs and shows significant improvements over greedy search.

Copied to clipboard

Damai Dai, Li Dong, Shuming Ma, Bo Zheng, Zhifang Sui, Baobao Chang, Furu Wei

Challenge:	Existing learning-to-route methods suffer from the routing fluctuation issue . with the model scale growing, training speed will go slower and memory requirements are heavy .
Approach:	They propose a Mixture-of-Experts technique that can scale up the model size of Transformers with an affordable computational overhead.
Outcome:	The proposed method outperforms existing learning-to-route methods on language modeling and multilingual machine translation.

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy (2026.acl-long)

Copied to clipboard

Zhaoxin Feng, Zheng Chen, Jianfei Ma, Yip Tin Po, Emmanuele Chersoni, Bo Li

A Survey on In-context Learning (2024.emnlp-main)

Challenge:	Recent studies have identified a critical drawback of aligning models with human judgments and outputs that are flawed or incorrect.
Approach:	They evaluate a range of LLMs to examine whether CoT reasoning mitigates sycophancy . they find that reasoning masks a tendency to scophage in some cases .
Outcome:	The proposed model models show that CoT reasoning reduces sycophancy but masks it in some cases.

Copied to clipboard

Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, Xu Sun, Lei Li, Zhifang Sui

Low-Resource NLP

Challenge:	In-context learning (ICL) is a new paradigm for natural language processing . large language models (LLMs) demonstrate the ability to learn from a few examples .
Approach:	They propose to explore ICL to evaluate and extrapolate the ability of large language models.
Outcome:	The proposed methods can be used to evaluate and extrapolate the ability of large language models.

Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference (2023.acl-long)

Copied to clipboard

Junhao Zheng, Qianli Ma, Shengjie Qiu, Yue Wu, Peitian Ma, Junlong Liu, Huawen Feng, Xichen Shang, Haibin Chen

CycleOIE: A Low-Resource Training Framework For Open Information Extraction (2025.coling-main)

Challenge:	Existing studies attribute catastrophic forgetting to fine-tuning, and they retain pre-trained knowledge indiscriminately without identifying what knowledge is transferable.
Approach:	They propose a unified objective for fine-tuning to retrieve the causality back from pre-trained data and use it to mitigate negative transfer while preserving knowledge.
Outcome:	The proposed method outperforms state-of-the-art fine-tuning methods on commonsense QA datasets and can be implemented as a plug-in module to inflate the performance of existing QA models.

Copied to clipboard

Zhihong Jin, Chunhong Zhang, Zheng Hu, Jibin Yu, Ruiqi Ma, Qingyun Chen, Xiaohao Liao, Yanxing Zhang

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

Challenge:	Open Information Extraction (OpenIE) models rely heavily on large amounts of annotated data.
Approach:	They propose a training framework that maximizes data efficiency through a cycle-consistency mechanism.
Outcome:	The proposed approach improves the quality of training data by curating low-quality datasets annotated by a large language model.

Copied to clipboard

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

Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

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

Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong

Traces in the Brain: Neural Evidence for Syntactic Movement in English and Chinese (2026.findings-acl)

Challenge:	Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach:	They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome:	The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.

Copied to clipboard

Yuhan Huang, Zhengwu Ma, Yuqi Jin, Beth Chan, Zheng Shen, Jackie Yan-Ki Lai, John T. Hale, Jixing Li

Syntactic Text Processing

Challenge:	Syntactic movement is a core concept in generative linguistics to account for word-order variation and long-distance dependencies.
Approach:	They annotated every sentence in the audiobook The Little Prince using X-bar style tree annotations.
Outcome:	The proposed model shows that deep structure significantly predicts neural responses in English but not in Chinese.

Probing Cross-modal Semantics Alignment Capability from the Textual Perspective (2022.findings-emnlp)

Copied to clipboard

Zheng Ma, Shi Zong, Mianzhi Pan, Jianbing Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen

Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction (2022.findings-emnlp)

Challenge:	In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks.
Approach:	They propose a new probing method that is based on image captioning to first empirically study the cross-modal semantics alignment of VLP models.
Outcome:	The proposed method analyzes captions generated by five popular VLP models to reveal how well they align with visual words and how well these align with images.

Copied to clipboard

Shirong Ma, Yinghui Li, Rongyi Sun, Qingyu Zhou, Shulin Huang, Ding Zhang, Li Yangning, Ruiyang Liu, Zhongli Li, Yunbo Cao, Haitao Zheng, Ying Shen

Syntactic Text Processing

Challenge:	Chinese Grammatical Error Correction (CGEC) is a challenging NLP task and a common application in human daily life.
Approach:	They propose a linguistic rules-based approach to construct large-scale CGEC training corpora with automatically generated grammatical errors.
Outcome:	The proposed method improves performance of existing CGEC models and the benchmark is excellent resource for further development.

Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition (2025.acl-long)

Copied to clipboard

Kehua Feng, Keyan Ding, Tan Hongzhi, Kede Ma, Zhihua Wang, Shuangquan Guo, Cheng Yuzhou, Ge Sun, Guozhou Zheng, Qiang Zhang, Huajun Chen

CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction (2022.coling-1)

Challenge:	Existing methods for evaluation of large language models are inefficient and inefficient due to inaccuracy of standard metrics in human perception of text quality and inefficiency in sampling informative test examples.
Approach:	They propose a sample-efficient human evaluation method for large language models based on the principle of MAximum Discrepancy (MAD) competition.
Outcome:	The proposed method achieves the “golden” ranking of LLMs with a minimum set of input instructions, which in turn reveal their relative strengths and weaknesses.

Copied to clipboard

Yubing Ren, Yanan Cao, Fang Fang, Ping Guo, Zheng Lin, Wei Ma, Yi Liu

A Law Reasoning Benchmark for LLM with Tree-Organized Structures including Factum Probandum, Evidence and Experiences (2025.findings-acl)

Challenge:	Existing methods for document-level event extraction struggle due to two intrinsic challenges: nested arguments and multiple events.
Approach:	They propose a role-interactive multi-event head attention network to solve two challenges . they map different events to multiple subspaces and then determine whether the current event exists .
Outcome:	The proposed model improves on two widely used DEE datasets on the Internet.

Copied to clipboard

Jiaxin Shen, Jinan Xu, Huiqi Hu, Luyi Lin, Guoyang Ma, Fei Zheng, Fandong Meng, Jie Zhou, Wenjuan Han

Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking (2022.findings-emnlp)

Challenge:	a recent study focuses on generating impartial and interpretable judicial judgments based on established criminal fact.
Approach:	They propose a law reasoning schema enriched with hierarchical factum probandum, evidence, and implicit experience that enables public scrutiny and preventing bias.
Outcome:	The proposed schema enables public scrutiny and prevents bias in the "Intelligent Court" it employs a suite of legal analysis tools to address the challenge task.

Copied to clipboard

Yinghui Li, Shirong Ma, Qingyu Zhou, Zhongli Li, Li Yangning, Shulin Huang, Ruiyang Liu, Chao Li, Yunbo Cao, Haitao Zheng

Syntactic Text Processing

Challenge:	Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors.
Approach:	They propose a framework which renders Chinese Spell Checking model to learn heterogeneous knowledge from the dictionary in terms of phonetics, vision, and meaning.
Outcome:	The proposed framework renders the CSC model to learn heterogeneous knowledge from the dictionary in terms of phonetics, vision, and meaning.

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

Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models (2026.findings-acl)

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

Qiyuan Zhang, Yufei Wang, Tianhe Wu, Can Xu, Qingfeng Sun, Kai Zheng, Xue Liu, Chen Ma

A Study of the Attention Abnormality in Trojaned BERTs (2022.naacl-main)

Challenge:	Recent advances in Generative Reward Models have demonstrated that scaling the length of Chain-of-Thought reasoning enhances reliability of evaluation.
Approach:	They propose a framework that reconfigures raw rationales into structured Breadth-CoT and Depth-Co T through a modular synthesis pipeline.
Outcome:	The proposed framework surpasses open-source RMs by an average of 8.2%.

Copied to clipboard

Weimin Lyu, Songzhu Zheng, Tengfei Ma, Chao Chen

HAUNTATTACK: When Attack Follows Reasoning as a Shadow (2026.findings-acl)

Challenge:	In computer vision, the trigger can be a fixed pattern overlaid on the images or videos.
Approach:	They propose an attention-based Trojan detector to distinguish Trojaned models from clean ones by observing the attention focus drifting behavior of Trojanes.
Outcome:	The proposed detector is based on transformer’s attention and can distinguish Trojan models from clean ones.

Copied to clipboard

Jingyuan Ma, Rui Li, Zheng Li, Junfeng Liu, Heming Xia, Lei Sha, Zhifang Sui

Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models (2025.acl-long)

Challenge:	Emerging Large Reasoning Models (LRMs) excel in mathematical and reasoning tasks, showcasing remarkable capabilities.
Approach:	They propose a framework that embeds harmful instructions into reasoning questions . they evaluate 11 LRMs and observe an average attack success rate of over 70% .
Outcome:	The proposed framework improves reasoning models by 13 percentage points over baseline.

Copied to clipboard

Naibin Gu, Peng Fu, Xiyu Liu, Ke Ma, Zheng Lin, Weiping Wang

Understanding Gender Bias in Knowledge Base Embeddings (2022.acl-long)

Challenge:	Parameter-efficient fine-tuning (PEFT) is a common method for fine- tuning large language models . however, once updated, PEFT modules suffer performance degradation on newer versions .
Approach:	They propose a method that enhances the PEFT module by focusing on the task-specific pattern while reducing its dependence on certain knowledge in the base model.
Outcome:	Experiments show that PEFT modules can maintain performance on updated models without re-tuning . the proposed approach can be used in real-world applications with large model sizes .

Copied to clipboard

Yupei Du, Qi Zheng, Yuanbin Wu, Man Lan, Yan Yang, Meirong Ma

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

Challenge:	Knowledge base (KB) embeddings have been shown to contain gender biases . authors develop two new bias measures to quantify them and trace their origins in KB .
Approach:	They propose two ways to quantify gender biases in knowledge base (KB) embeddings . they use the influence function to inspect the contribution of each triple in KB to the overall group bias .
Outcome:	The proposed measures are compared with real-world census data to examine gender biases.

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.

KEPL: Knowledge Enhanced Prompt Learning for Chinese Hypernym-Hyponym Extraction (2023.emnlp-main)

Copied to clipboard

Ningchen Ma, Dong Wang, Hongyun Bao, Lei He, Suncong Zheng

LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles (2024.lrec-main)

Challenge:	Existing work on hypernym-hyponym (“is-a”) relations is mostly in the English language.
Approach:	They propose a Knowledge Enhanced Prompt Learning method for Chinese hypernym-hyponym relation extraction using Hearst-like patterns as the prior knowledge.
Outcome:	The proposed method is able to extract hypernym-hyponym relations from Chinese unstructured texts using Hearst-like patterns and embed patterns and text simultaneously.

Copied to clipboard

Shulin Huang, Shirong Ma, Yinghui Li, Mengzuo Huang, Wuhe Zou, Weidong Zhang, Haitao Zheng

Look and Think: Efficient Multimodal Reasoning via Modality-Decoupled Compression (2026.findings-acl)

Challenge:	Existing evaluation benchmarks, such as MMLU, C-Eval, and GSM8K, evaluate models by posing a variety of problems, including problems about mathematics, science, law, and general knowledge.
Approach:	They propose a benchmark which assesses the model’s lateral thinking within an interactive framework.
Outcome:	The proposed evaluation benchmark assesses the model’s lateral thinking within an interactive framework.

Copied to clipboard

Xidi Cai, Junhao Zheng, Jingye Li, Boyuan Li, Shaowei Zhang, Qianli Ma

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Challenge:	Multimodal large language models have strong performance on visual question answering benchmarks . however, their inference efficiency is severely constrained by the rapidly growing context .
Approach:	They propose a modality-decoupled compression method that enables efficient multimodal inference . they propose to evict visual tokens whenever visual grounding is unnecessary .
Outcome:	The proposed method reduces the average context length by up to 57% while maintaining comparable performance to the standard MLLM baseline.

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

Learning to Stop in Structured Prediction for Neural Machine Translation (N19-1)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Mingbo Ma, Renjie Zheng, Liang Huang

Machine Translation

Challenge:	Beam search optimization solves many problems in neural machine translation, but lacks principled stopping criteria and does not learn how to stop during training.
Approach:	They propose a ranking method which enables an optimal beam search stop-ping criteria and a structured prediction loss function which penalizes suboptimal finished candidates produced by beam search during training.
Outcome:	Experiments on synthetic and real languages show that the proposed methods improve translation quality and length.

Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework (2020.findings-emnlp)

Copied to clipboard

Mingbo Ma, Baigong Zheng, Kaibo Liu, Renjie Zheng, Hairong Liu, Kainan Peng, Kenneth Church, Liang Huang

ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs (2026.acl-long)

Challenge:	Text-to-speech synthesis (TTS) has seen rapid progress in recent years, but still suffers from latencies.
Approach:	They propose a neural incremental TTS approach that synthesizes speech in an online fashion, playing a segment of audio while generating the next.
Outcome:	Experiments on English and Chinese TTS show that the proposed approach achieves similar speech naturalness compared to full sentence TTS, but with a constant (1-2 words) latency.

Copied to clipboard

Hongxin Ding, Baixiang Huang, Yue Fang, Weibin Liao, Xinke Jiang, Jinyang Zhang, Yinghao Zhu, Zheng Li, Liantao Ma, Junfeng Zhao, Yasha Wang

Challenge:	Existing medical Large Language Models (LLMs) follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient details.
Approach:	They propose a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making.
Outcome:	Experiments on partial-information medical benchmarks show that ProMed outperforms state-of-the-art methods by 6.29% on average and delivers a 54.45% gain over the reactive paradigm.

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision (2026.acl-long)

Copied to clipboard

Ge Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang, Yuhao Shang, Huiwen Zheng, Hongli Ma, Yan Liang, Yuanchun Li, Yunxin Liu