Papers by Yuan Ma

EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks (2026.findings-acl)

Challenge:	Current pre-training techniques rely on a limited scope of medical data, limiting the range of downstream tasks.
Approach:	They propose a pre-training strategy that unifies patient data within individual sources and captures explicit and implicit correlations between patients across different sources.
Outcome:	The proposed strategy bridges the gap between multimodal medical sources by aggregating patient data within individual sources and capturing explicit and implicit correlations between patients across sources.

Copied to clipboard

Yijie Lu, Manman Zhao, Tianjie Ju, Zihe Yan, Xinbei Ma, Yuan Guo, Daizong Ding, Gongshen Liu, Zhuosheng Zhang

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

Challenge:	Existing methods for red-teaming face a trade-off between requiring target-specific knowledge and incurring prohibitive computational costs.
Approach:	They propose a framework that evolves payloads exclusively on the semantic dimension via a discovery-deployment pipeline.
Outcome:	Experiments show that EVA outperforms baselines in terms of attack success rate while evolving benign seeds into successful attacks within 1.18 to 1.71 iterations.

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

Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users based on Weakly Supervised Learning (2020.coling-main)

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

Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han, Songlin Hu

GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models (2026.acl-industry)

Challenge:	Existing models for fake news detection are often insufficient or lacking in features . a novel structure-aware multi-head attention network can detect fake news in 4 hours .
Approach:	They propose a structure-aware multi-head attention network to detect fake news in mass news . they use credibility of publishers and users as prior weakly supervised information .
Outcome:	The proposed model can detect fake news in 4 hours with an accuracy of over 91% . the proposed model is faster than the state-of-the-art models .

Copied to clipboard

Yuan Zhong, Chuanwei Ruan, Moein Hasani, Tejaswi Tenneti, Haixun Wang, Fenglong Ma

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

Challenge:	a growing number of online grocery shoppers are using category-level recommendation systems . traditional item-level methods face scalability and accuracy challenges .
Approach:	a new language model is developed to encode cyclical purchasing patterns into model parameters . the model is scalable and more business-aligned than traditional item-level methods .
Outcome:	a new language model outperforms standard methods in a live production environment . the proposed model achieves a 7.5% relative improvement in cart-adds per impression .

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.

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction (2026.findings-acl)

Copied to clipboard

Yulin Chen, Haoran Li, Yuan Sui, Yue Liu, Yufei He, Xiaoling Bai, Chi Fei, Li Yabo, Haozhe Ma, Yangqiu Song, Bryan Hooi

RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners (2024.lrec-main)

Challenge:	Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions.
Approach:	They propose a prompt injection defense method that suppresses the model's instruction-following tendencies rather than suppressing them.
Outcome:	The proposed method outperforms prompt-engineering-based approaches and fine-tuning methods and reduces the ASR to nearly 0% in some scenarios.

Copied to clipboard

Chi Hu, Yuan Ge, Xiangnan Ma, Hang Cao, Qiang Li, Yonghua Yang, Tong Xiao, Jingbo Zhu

Dialogue Systems & Conversational Agents

Challenge:	Existing solutions to reasoning tasks require extensive human annotations or fail in scenarios with inconsistent responses.
Approach:	They propose a new method that enables LLMs to self-rank their responses without additional resources.
Outcome:	The proposed method improves reasoning performance of ChatGPT and GPT-4 with 13% improvement over existing methods.

AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering (2026.acl-long)

Copied to clipboard

Zheyuan Zhang, Kaiwen Shi, Zhengqing Yuan, Zehong Wang, Tianyi Ma, Keerthiram Murugesan, Vincent Galassi, Chuxu Zhang, Yanfang Ye

ParaCook: On Time-Efficient Planning for Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing approaches to agent routing emphasize cost efficiency while overlooking the fine-grained contextual and relational structure inherent in QA tasks.
Approach:	They propose a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.
Outcome:	The proposed framework outperforms single-agent and ensemble baselines while generalizing across benchmarks and LLM backbones.

Copied to clipboard

Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang

Green & Sustainable NLP

Challenge:	Existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations.
Approach:	They propose a framework for large language models that allows agents to plan long-horizon tasks in a scalable way.
Outcome:	The proposed framework is based on the Overcooked game and can be used to evaluate time efficiency-aware multi-agent planning.

ThinkLinker: From Low-Rank Interaction to Knowledge-Aware Verification for Multimodal Entity Linking (2026.findings-acl)

Copied to clipboard

Yingyao Ma, Yuanyuan Zhou, Congyu Zhang, Yi Yuan, Jiasong Wu, Lotfi Senhadji, Huazhong Shu

Information Retrieval

Challenge:	Existing methods for multimodal entity linking rely on textual context for disambiguation . textual contextual information alone fails to resolve ambiguity, leading to unreliable disambiguations in weak contexts.
Approach:	They propose a two-stage multimodal entity linking framework called ThinkLinker . they propose fusion mechanism to model joint dependencies among features .
Outcome:	The proposed framework outperforms state-of-the-art models on public benchmark datasets.

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

Copied to clipboard

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

KS-Lottery: Finding Certified Lottery Tickets for Multilingual Transfer in Large Language Models (2025.naacl-long)

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

Fei Yuan, Chang Ma, Shuai Yuan, Qiushi Sun, Lei Li

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

Challenge:	Existing studies have shown that a small subset of parameters is highly effective in fine-tuning . prior work shows that there are a few additional parameters corresponding to an intrinsic dimension in a well-trained Large Language Model.
Approach:	They propose a method to identify a small subset of LLM parameters highly effective in multilingual fine-tuning.
Outcome:	The proposed method can find the certified winning tickets in the embedding layer, and fine-tuning on the found parameters is guaranteed to perform as well as full fine- tuning.

Copied to clipboard

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

KAPALM: Knowledge grAPh enhAnced Language Models for Fake News Detection (2023.findings-emnlp)

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 Ma, Chen Chen, Chunyan Hou, Xiaojie Yuan

Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models (2024.acl-long)

Challenge:	Existing methods of fake news detection focus on news entity information and ignore structured knowledge among news entities.
Approach:	They propose a model that fuses coarse- and fine-grained representations of entity knowledge from Knowledge Graphs (KGs) they identify entities in news content and link them to entities in KGs.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets and is competitive in the few-shot scenario.

Copied to clipboard

Weihong Zhong, Xiaocheng Feng, Liang Zhao, Qiming Li, Lei Huang, Yuxuan Gu, Weitao Ma, Yuan Xu, Bing Qin

CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)

Challenge:	Large Vision-Language Models (LVLMs) suffer from multimodal hallucinations . however, the generated hallucines could influence the models’ subsequent generation .
Approach:	They propose a framework to evaluate LVLMs' behaviors when encountering generated hallucinations and a method to revise the output distribution of LVLs with the one derived from the residual visual input.
Outcome:	The proposed framework reduces the performance of open-source LVLMs by 31%, indicating that they are prone to accept the generated hallucinations and make false claims that they would not have supported without distractions.

Copied to clipboard

Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, Jie Fu

PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models (2023.findings-emnlp)

Challenge:	a recent study shows that large language models have limited generalization in low-resource languages like Chinese.
Approach:	They propose to evaluate the zero-shot generalizability of large language models to the Chinese language . they release only half of the dataset publicly, with the remainder kept private .
Outcome:	The Chinese Instruction-Following Benchmark evaluates the generalizability of LLMs to the Chinese language.

Copied to clipboard

Xingwei He, A-Long Jin, Jun Ma, Yuan Yuan, Siu Yiu

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

Challenge:	Existing methods for Factual Error Correction (FEC) use mask-then-correct paradigms . however, the lack of datasets containing false claims has impeded progress .
Approach:	They propose a method that enhances few-shot FEC with a pivot task approach using large language models.
Outcome:	The proposed method outperforms its few-shot counterpart by 7.9 points in SARI . it improves widely-adopted SARI metrics by 11.3 compared to the best-performing methods .

Copied to clipboard

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

Text Generation

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.

OpenAttack: An Open-source Textual Adversarial Attack Toolkit (2021.acl-demo)

Copied to clipboard

Guoyang Zeng, Fanchao Qi, Qianrui Zhou, Tingji Zhang, Zixian Ma, Bairu Hou, Yuan Zang, Zhiyuan Liu, Maosong Sun

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

Challenge:	Various attack models are distinct and implemented with different programming frameworks and settings, which hinders quick utilization and fair comparison of attack models.
Approach:	They propose an open-source textual adversarial attack toolkit to solve these issues by combining 15 typical attack models into one toolkit.
Outcome:	The proposed toolkit supports all attack types, multilinguality, and parallel processing.

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

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment (2026.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

Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin Sun

CAST: Corpus-Aware Self-similarity Enhanced Topic modelling (2025.naacl-long)

Challenge:	Existing approaches to safety alignment of large language models rely on costly manual annotations or human review.
Approach:	They propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative collaboration among three roles with near-zero manual annotation.
Outcome:	The proposed framework achieves 20%–50% improvement in adversarial effectiveness while preserving high output diversity while achieving 10%–30% gains in safety performance without degrading general reasoning capability.

Copied to clipboard

Yanan Ma, Chenghao Xiao, Chenhan Yuan, Sabine N Van Der Veer, Lamiece Hassan, Chenghua Lin, Goran Nenadic

Information Extraction & Text Mining

Challenge:	Existing topic modelling methods encode contextual information of documents while ignoring contextual details of candidate centroid words. Existing methods are limited by the contextualization gap.
Approach:	They propose a topic modelling method that builds upon candidate centroid word embeddings contextualized on the dataset and a self-similarity-based method to filter out less meaningful tokens.
Outcome:	The proposed method significantly enhances the coherence and diversity of generated topics, and handles noisy data, outperforming strong baselines.

Multi-lingual Argumentative Corpora in English, Turkish, Greek, Albanian, Croatian, Serbian, Macedonian, Bulgarian, Romanian and Arabic (L18-1)

Copied to clipboard

Alfred Sliwa, Yuan Ma, Ruishen Liu, Niravkumar Borad, Seyedeh Ziyaei, Mina Ghobadi, Firas Sabbah, Ahmet Aker

Information Retrieval

Challenge:	Argumentative corpora are costly to create and available only in few languages with English dominating the area.
Approach:	They use 8 different argument mining classifiers trained for English to build a parallel corpora in which the source language is English and the target language is either a Balkan language or Arabic.
Outcome:	The proposed method is based on 8 different argument mining classifiers trained for English and project the decision to the target language.

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation (2026.findings-acl)

Copied to clipboard

Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, Weiming Hu

Text-to-Text Automatic Story Generation: A Survey (2026.eacl-srw)

Challenge:	Multimodal Large Language Models (MLLMs) are increasingly being deployed as content moderators . however, they exploit the Human-AI capability gap and create adversarial environments . smuggling attacks exploit the human-AI gap and exploit the vulnerability .
Approach:	They construct a benchmark to evaluate the vulnerability of MLLMs as content moderators . they identify three root causes: limited capabilities of vision encoders, robustness gap in OCR .
Outcome:	The proposed model exploits the Human-AI capability gap and is vulnerable to smuggling attacks.

Copied to clipboard

Yuan Ma, Richard Susilo, Patrik Haslum, Hanna Suominen

Text Generation

Challenge:	Automated story generation aims to produce coherent, engaging, and contextually consistent narratives with minimal or no human involvement . despite advances in large language models, maintaining narrative coherence, character consistency, storyline diversity, and plot controllability in generating stories is still challenging.
Approach:	They propose to develop new evaluation metrics and better data sets to support automatic story generation.
Outcome:	The proposed evaluation metrics and better datasets will improve narrative coherence and consistency and explore practical applications of story generation.

FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)

Copied to clipboard

Yusong Hu, Runmin Ma, Yue Fan, Jinxin Shi, Zongsheng Cao, Yuhao Zhou, Jiakang Yuan, Shuaiyu Zhang, Shiyang Feng, Xiangchao Yan, Shufei Zhang, Wenlong Zhang, Lei Bai, Bo Zhang

x1: Learning to Think Adaptively Across Languages and Cultures (2026.findings-acl)

Challenge:	FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Approach:	They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Outcome:	The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download.

Copied to clipboard

Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Yichong Huang, Zekun Yuan, Lei Huang, Weitao Ma, Qichen Hong, Yunfei Lu, Dandan Tu, Bing Qin

Reasoning

Challenge:	Existing large language models (LLMs) ignore this diversity by reasoning in a single dominant language.
Approach:	They propose a family of reasoning models that can adaptively reason in an advantageous language on a per-instance basis.
Outcome:	The proposed model can reason in a single dominant language on a per-instance basis.

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets (2026.findings-acl)

Copied to clipboard

Yuan Xiao, Jiaming Wang, Yuchen Chen, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang, Jin Song Dong, Zhenyu Chen

Programming Languages in NLP

Challenge:	Existing methods for dataset poisoning require full-dataset poison, which breaks code compilability.
Approach:	They propose a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths.
Outcome:	The proposed method contaminates 10% of the dataset while maintaining 100% compilability and functional correctness.

AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)

Copied to clipboard

Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E

An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism (2022.acl-long)

Challenge:	AEGIS examines whether current models can effectively audit AI-generated images in academic papers.
Approach:	They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics.
Outcome:	AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis.

Copied to clipboard

Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan

Structured Data in NLP

Challenge:	Existing methods focus on graph representation learning, but decoding is a key part of the process.
Approach:	They propose an EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI) they combine two sets of isomorphic equations to enhance the decoding process .
Outcome:	The proposed algorithm can deliver significant performance improvements even on the most advanced methods while the extra required time is less than 3 seconds.

ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks (2024.eacl-long)

Copied to clipboard

Bolei Ma, Ercong Nie, Shuzhou Yuan, Helmut Schmid, Michael Färber, Frauke Kreuter, Hinrich Schuetze

CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning (2025.acl-long)

Challenge:	Prompt-based methods have been successfully applied to multilingual pretrained language models for zero-shot cross-lingual understanding.
Approach:	They propose a prompt-based method for token-level sequence labeling tasks . they propose to decompose an input sentence into single tokens and apply one prompt template to each token.
Outcome:	The proposed method outperforms Vanilla fine-tuning and Prompt-Tuning in zero-shot cross-lingual transfer . the method also attains state-of-the-art performance when employed with the mT5 model .

Copied to clipboard

Yangfan Ye, Xiaocheng Feng, Zekun Yuan, Xiachong Feng, Libo Qin, Lei Huang, Weitao Ma, Yichong Huang, Zhirui Zhang, Yunfei Lu, Xiaohui Yan, Duyu Tang, Dandan Tu, Bing Qin

Multilinguality

Challenge:	Existing fine-tuning approaches that focus on English-centric training corpora often introduce implicit cross-lingual alignment, overlooking the potential for more profound, latent-level cross-linguistic interactions.
Approach:	They propose a multilingual fine-tuning paradigm that explicitly establishes a cross-lingual connection mechanism at the latent level.
Outcome:	The proposed model outperforms vanilla SFT and offers a strong latent-level alternative to data-level augmentation methods.

Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions (2025.acl-long)

Copied to clipboard

Xinbei Ma, Yiting Wang, Yao Yao, Tongxin Yuan, Aston Zhang, Zhuosheng Zhang, Hai Zhao

Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens (2025.emnlp-main)

Challenge:	Experimental results show that multimodal GUI agents are susceptible to environmental distractions.
Approach:	They propose a scenario where both user and agent are benign and environment is not malicious . they implement an adversarial environment injection and analyze the approach to improve faithfulness .
Outcome:	The proposed approach improves faithfulness of multimodal large language model agents in a graphical user interface environment.

Copied to clipboard

Ziyang Ma, Qingyue Yuan, Zhenglin Wang, Deyu Zhou

Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks (2025.emnlp-main)

Challenge:	Existing studies have focused on the cognitive error detection capabilities of Large Language Models (LLMs), but few studies have examined the meta-cognitive abilities of LLMs.
Approach:	They propose an automated meta-cognition evaluation framework for evaluation of LLMs and a Markovian Intrinsic Reward Adjustment strategy to boost current lenses.
Outcome:	The proposed framework can be used to evaluate the meta-cognition abilities of LLMs and improve them.

Copied to clipboard

Gaurav Bagwe, Saket Sanjeev Chaturvedi, Xiaolong Ma, Xiaoyong Yuan, Kuang-Ching Wang, Lan Emily Zhang

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

Challenge:	Retrieval-augmented generation (RAG) enhances factual grounding but introduces new attack surfaces, particularly through backdoor attacks.
Approach:	They propose a framework that exposes fairness vulnerabilities in RAG through a two-phase backdoor attack.
Outcome:	Empirical results show that BiasRAG achieves high attack success rates while remaining undetectable under standard fairness evaluations.

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

SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning (2026.acl-long)

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

Peidong Wang, Zhiming Ma, Xin Dai, YongKang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang

What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning (2026.acl-long)

Challenge:	Existing methods for fraud detection rely on transcribed text, lacking acoustic cues . a proposed framework for audio-based slow-thinking fraud detection eliminates transcription errors .
Approach:	They propose a framework for audio-based slow-thinking fraud detection that eliminates transcription errors and rewards slow-thought reasoning by capturing fine-grained audio details.
Outcome:	The proposed method improves accuracy, inference efficiency, and real-time processing capabilities.

Copied to clipboard

Yaning Jia, Chunhui Zhang, Xingjian Diao, Xiangchi Yuan, Zhongyu Ouyang, Chiyu Ma, Soroush Vosoughi

Reasoning

Challenge:	Curriculum learning (CL) orders data corpus by difficulty, but prior work employs disparate difficulty metrics and training setups.
Approach:	They propose a framework that decomposes curriculum difficulty into five dimensions: Problem Difficulty, Model Surprisal, Confidence Margin, Predictive Uncertainty and Decision Variability.
Outcome:	The proposed framework decomposes curriculum difficulty into five dimensions . the results show that no curriculum strategy dominates universally .

Label-Specific Dual Graph Neural Network for Multi-Label Text Classification (2021.acl-long)

Copied to clipboard

Qianwen Ma, Chunyuan Yuan, Wei Zhou, Songlin Hu

Information Extraction & Text Mining

Challenge:	Existing studies for multi-label text classification do not explore label-specific semantic components from documents.
Approach:	They propose a label-specific dual graph neural network that incorporates category information to learn label-related components from documents.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark datasets and achieves better performance with respect to tail labels.

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)

Copied to clipboard

Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui

UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt (2024.lrec-main)

Challenge:	Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows.
Approach:	They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system.
Outcome:	Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks.

Copied to clipboard

Yucheng Cai, Wentao Ma, Yuchuan Wu, Shuzheng Si, Yuan Shao, Zhijian Ou, Yongbin Li

Hierarchical Pretraining on Multimodal Electronic Health Records (2023.emnlp-main)

Challenge:	Recent studies have shown that multi-task instruction tuning after pre-training greatly improves the model’s robustness and transfer ability, which is crucial for building a high-quality dialog system.
Approach:	They propose to use Task-aware Automatic Prompt generation (TAP) to automatically generate high-quality prompts from 15 dialog-related tasks.
Outcome:	The proposed model is robust to input prompts and capable of various dialog-related tasks.

Copied to clipboard

Xiaochen Wang, Junyu Luo, Jiaqi Wang, Ziyi Yin, Suhan Cui, Yuan Zhong, Yaqing Wang, Fenglong Ma

A Simple Temporal Information Matching Mechanism for Entity Alignment between Temporal Knowledge Graphs (2022.coling-1)

Challenge:	Existing pretraining models on EHR data are too specific, limiting their transferability.
Approach:	They propose a general, unified pretraining framework for hierarchically multimodal EHR data that can be used to train models on a large dataset before fine-tuning it on 'upstream' tasks.
Outcome:	The proposed model performs on eight downstream tasks spanning three levels and compares with baselines on 18 different tasks.

Copied to clipboard

Li Cai, Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, Man Lan

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

Challenge:	Existing methods for EA between temporal KGs incorporate relational and temporal information into entity embeddings.
Approach:	They propose a method to generate unsupervised alignment seeds using temporal information from TKGs.
Outcome:	The proposed method outperforms the previous methods by using temporal information.

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

DavIR: Data Selection via Implicit Reward for Large Language Models (2025.acl-long)

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.

Copied to clipboard

Haotian Zhou, Tingkai Liu, Qianli Ma, Yufeng Zhang, Jianbo Yuan, Pengfei Liu, Yang You, Hongxia Yang