Papers by Fei Xu

Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency (2022.acl-long)

Challenge:	Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored.
Approach:	They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios.
Outcome:	The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC.

Copied to clipboard

Yanyang Li, Fuli Luo, Runxin Xu, Songfang Huang, Fei Huang, Liwei Wang

Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2026.acl-long)

Challenge:	Structured pruning has been extensively studied on monolingual pre-trained models . but little attention has been paid to evaluating the effectiveness of structured pruning on multilingual models.
Approach:	They investigate settings, algorithms, and efficiency of structured pruning on multilingual models . authors propose a simple approach that allows training the model once and adapting to different model sizes at inference .
Outcome:	The proposed approach allows training the model once and adapting to different model sizes at inference.

Copied to clipboard

Zhong-Zhi Li, Xiao Liang, Zihao Tang, Lei Ji, Peijie Wang, Haotian Xu, Xing W, Haizhen Huang, Weiwei Deng, Yeyun Gong, Zhijiang Guo, Xiao Liu, Fei Yin, Cheng-Lin Liu

MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs (2026.acl-long)

Challenge:	Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques.
Approach:	They propose a method that uses Extended Chain-of-Thought (EFT) to reduce the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
Outcome:	The proposed method reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.

Copied to clipboard

Xiangyu Zhao, Wanghan Xu, Bo Liu, Yuhao Zhou, Fenghua Ling, Ben Fei, Xiaoyu Yue, Lei Bai, Wenlong Zhang, Xiao-Ming Wu

Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting (2022.naacl-main)

Challenge:	Existing datasets often rely on synthetic data or figure-caption pairs, failing to capture the depth and complexity of geoscientific reasoning.
Approach:	They propose a multimodal scientific dataset and benchmark curated from open-access publications.
Outcome:	MSEarth features over 289K figures with captions enriched by contextual discussions and reasoning from original papers.

Copied to clipboard

Qingfeng Sun, Can Xu, Huang Hu, Yujing Wang, Jian Miao, Xiubo Geng, Yining Chen, Fei Xu, Daxin Jiang

Text Generation

Challenge:	Existing knowledge-grounded dialogue generation models only produce pedantic responses, which lacks emotion and attraction compared with the responses with polite style, positive and negative sentiments.
Approach:	They propose a method which generates responses via combing disentangled style templates and content templates.
Outcome:	The proposed method improves on evaluation metrics compared with state-of-the-art methods.

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States (2024.findings-emnlp)

Copied to clipboard

Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Yongbin Li

STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation (2025.findings-acl)

Challenge:	Large language models (LLMs) rely on safety alignment to avoid malicious user inputs.
Approach:	They employ weak classifiers to explain LLM safety through the intermediate hidden states.
Outcome:	The proposed model can identify malicious and normal inputs and detect malicious ones without jailbreak.

Copied to clipboard

Wenxiang Guo, Yu Zhang, Changhao Pan, Zhiyuan Zhu, Ruiqi Li, ZheTao Chen, Wenhao Xu, Fei Wu, Zhou Zhao

Speech & Audio in NLP

Challenge:	Existing automated singing annotation (ASA) methods tackle isolated aspects of the annotation pipeline.
Approach:	They propose a framework that addresses transcription, alignment, and refined style annotations.
Outcome:	The proposed framework delivers comprehensive multi-level annotations encompassing: (1) precise phoneme-audio alignment, (2) robust note transcription and temporal localization, (3) expressive vocal technique identification, and (4) global stylistic characterization including emotion and pace.

When Words Smile: Generating Diverse Emotional Facial Expressions from Text (2025.emnlp-main)

Copied to clipboard

Haidong Xu, Meishan Zhang, Hao Ju, Zhedong Zheng, Erik Cambria, Min Zhang, Hao Fei

Challenge:	Existing systems that generate only coarse facial expressions ignore the rich and dynamic nature of face-to-face communication.
Approach:	They propose an end-to-end text-to expression model that explicitly focuses on emotional dynamics.
Outcome:	The proposed model outperforms baselines on 15,000 text–3D expression pairs on a large-scale dataset.

Experience-driven Multi-turn Reinforcement Learning for GUI Agents (2026.acl-long)

Copied to clipboard

Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang

Challenge:	GUI agents have demonstrated remarkable progress in automating complex user interface interactions . training such agents for long-horizon tasks remains challenging due to limited rewards and prohibitive costs.
Approach:	They propose a method that leverages expert trajectories as environment experiences for on-policy multi-turn training.
Outcome:	The proposed method achieves significant gains over the base model with 1K public trajectories as RL experiences . it achieves competitive performance against strong baselines such as UI-TARS-7B and GPT-4o .

SocialBench: Sociality Evaluation of Role-Playing Conversational Agents (2024.findings-acl)

Copied to clipboard

Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Gao Xing, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang

LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting (2022.coling-1)

Challenge:	Existing studies on role-playing agents have focused on enhancing their conversational capability, role-specific knowledge and style, but there has been a gap in assessing their social intelligence.
Approach:	They propose a benchmark to evaluate the sociality of role-playing agents using LLMs.
Outcome:	The proposed benchmark is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances.

Copied to clipboard

Xiang Chen, Lei Li, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen, Ningyu Zhang

Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation (2023.acl-long)

Challenge:	Existing approaches for Named Entity Recognition (NER) use extensive labeled data for model training, which struggles in low-resource scenarios.
Approach:	They propose a lightweight tuning paradigm for low-resource NER via pluggable prompting . they construct a learnable verbalizer of entity categories without any label-specific classifiers .
Outcome:	The proposed model outperforms baselines and class transfer models in low-resource scenarios.

Copied to clipboard

Chaoya Jiang, Wei Ye, Haiyang Xu, Songfang Huang, Fei Huang, Shikun Zhang

A Two-Agent Game for Zero-shot Relation Triplet Extraction (2024.findings-acl)

Challenge:	Large-scale pre-trained vision-language models have recently achieved tremendous success on a wide range of cross-modal tasks.
Approach:	They propose a new framework for a semantically-aware contrastive learning that minimizes the MI between false negative and positive samples .
Outcome:	The proposed framework minimizes the MI between false negative samples and positive samples even though they share similar semantics.

Copied to clipboard

Ting Xu, Haiqin Yang, Fei Zhao, Zhen Wu, Xinyu Dai

Extrapolating Multilingual Understanding Models as Multilingual Generators (2023.findings-emnlp)

Challenge:	Existing methods for relation triplet extraction rely on labeled data and are limited in their applicability.
Approach:	They propose a two-agent game approach to deliberate and debate unseen relations by two agents, a generator and an extractor.
Outcome:	The proposed method outperforms baseline methods by 6%-16% in F1 scores.

Copied to clipboard

Bohong Wu, Fei Yuan, Hai Zhao, Lei Li, Jingjing Xu

Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Challenge:	Existing multilingual understanding models are not capable of generating high-quality text compared with decoder-based causal language models.
Approach:	They propose a method to adapt a multilingual encoder to a language generator with a small number of additional parameters.
Outcome:	The proposed approach outperforms initialization-based methods with 9.4 BLEU on machine translation, 8.1 Rouge-L on question generation, and 5.5 METEOR on story generation.

Copied to clipboard

Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu

Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach:	They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome:	The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.

Copied to clipboard

Runxin Xu, Fuli Luo, Zhiyuan Zhang, Chuanqi Tan, Baobao Chang, Songfang Huang, Fei Huang

MRN: A Locally and Globally Mention-Based Reasoning Network for Document-Level Relation Extraction (2021.findings-acl)

Challenge:	Recent pretrained language models extend from millions to billions of parameters.
Approach:	They propose a technique which forwards on a whole network while backwarding on resetting the gradients of the non-child network during the backward process.
Outcome:	The proposed technique outperforms the vanilla fine-tuning technique on various downstream tasks and can achieve better generalization performance by large margins.

Copied to clipboard

Jingye Li, Kang Xu, Fei Li, Hao Fei, Yafeng Ren, Donghong Ji

Information Extraction & Text Mining

Challenge:	Existing studies on document-level relation extraction focus on sentencelevel RE, but recent studies reveal that a large number of relations can actually be expressed through multiple sentences, which necessitates document- level RE.
Approach:	They propose a document-level relation extraction model that captures local and global contextual information as well as close and distant mention interactions.
Outcome:	The proposed model outperforms state-of-the-art models on three widely used datasets, namely DocRED, CDR, and GDA.

CLEAR: A Framework Enabling Large Language Models to Discern Confusing Legal Paragraphs (2025.findings-emnlp)

Copied to clipboard

Qi Xu, Qian Liu, Hao Fei, Hang Yu, Shuhao Guan, Xiao Wei

Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking (2024.findings-naacl)

Challenge:	Existing work focuses on enabling LLMs to leverage legal rules to tackle complex legal reasoning tasks, but ignores their ability to understand legal rules.
Approach:	They propose a legal paragraph prediction task that aims to predict the legal paragraph given criminal facts and a framework CLEAR to enhance their legal reasoning ability.
Outcome:	The proposed model improves the ability of LLMs to analyze legal cases with the guidance of legal rule insights.

Copied to clipboard

Nan Xu, Fei Wang, Ben Zhou, Bangzheng Li, Chaowei Xiao, Muhao Chen

Robustness in NLP

Challenge:	Large language models (LLMs) have demonstrated increasing power, but they also have vulnerabilities.
Approach:	They propose a black-box attack that targets the cognitive structure and processes of large language models (LLMs) they propose defending cognitive overload attacks from three perspectives.
Outcome:	The proposed attack is a black-box attack with no need for knowledge of model architecture or access to model weights.

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning (2025.acl-long)

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang

PairCoder: Pair Programming-Inspired Two-Agent Collaboration for Code Generation (2026.findings-acl)

Challenge:	Existing approaches to learning from errors synthesize training data by extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases.
Approach:	They propose a framework that synthesizes more generalized training data from isolated bad cases by extrapolating from isolated cases.
Outcome:	The proposed framework synthesizes more generalized training data to address these model weaknesses.

Copied to clipboard

Junhao Chen, Xiang Li, Yibin Xu, Yuehan Cui, Fangsheng Weng, Hao Zhao, Fei Ma, Qi Tian

Programming Languages in NLP

Challenge:	Existing multi agent frameworks for large language models are brittle on code generation tasks.
Approach:	They propose a framework that brings pair programming to autonomous LLM collaboration.
Outcome:	Using PairCoder, large language models achieve better results on code generation tasks and reduce token usage by 40% to 70% on eight representative backbones.

Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning (2022.naacl-main)

Copied to clipboard

Fei Wang, Zhewei Xu, Pedro Szekely, Muhao Chen

Text Generation

Challenge:	Controlled table-to-text generation is a new approach to generate textual descriptions for highlighted subparts of a table.
Approach:	They propose an equivariance learning framework which encodes tables with a structure-aware self-attention mechanism and a positional encoding mechanism to preserve relative position of tokens in the same cell.
Outcome:	The proposed framework is free to be plugged into existing table-to-text generation models and has improved T5-based models to offer better performance on ToTTo and HiTab.

Knowledge Stimulated Contrastive Prompting for Low-Resource Stance Detection (2022.findings-emnlp)

Copied to clipboard

Kai Zheng, Qingfeng Sun, Yaming Yang, Fei Xu

Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy (2024.findings-emnlp)

Challenge:	Stance Detection Tasks require background knowledge especially when there is no explicit target mentioned in text.
Approach:	They propose a masked language prompt joint contrastive learning approach to stimulate the knowledge inherit from pre-trained models.
Outcome:	The proposed model is effective in stance detection on three benchmarks.

Copied to clipboard

Liyan Xu, Zhenlin Su, Mo Yu, Jin Xu, Jinho Choi, Jie Zhou, Fei Liu

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding (2024.findings-emnlp)

Challenge:	Existing studies have focused on specialized BERT-variants and recent LLMs to reason inconsistencies.
Approach:	They propose to incorporate task-specific taxonomy into inferences to facilitate both zero-shot and supervised paradigms.
Outcome:	The proposed model outperforms specialized non-LLM and recent LLM models in a number of domains.

Copied to clipboard

Anwen Hu, Haiyang Xu, Jiabo Ye, Ming Yan, Liang Zhang, Bo Zhang, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding (2025.acl-long)

Challenge:	Existing Multimodal Large Language Models lack general structure understanding abilities for text-rich document images.
Approach:	They propose to use unified structure learning to boost the performance of MLLMs by encoding structure information into text-rich images.
Outcome:	The proposed model achieves state-of-the-art on 10 visual document understanding benchmarks.

Copied to clipboard

Anwen Hu, Haiyang Xu, Liang Zhang, Jiabo Ye, Ming Yan, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou

Visual Data in NLP

Challenge:	Multimodal Large Language Models (MLLMs) have improved document understanding performance but generate thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times.
Approach:	They propose a high-resolution document compression module to generate 324 tokens for a single document image.
Outcome:	The proposed module reduces first token latency by more than 50% and improves document comprehension performance.

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models (2024.naacl-long)

Copied to clipboard

Jiashu Xu, Mingyu Ma, Fei Wang, Chaowei Xiao, Muhao Chen

S4-Tuning: A Simple Cross-lingual Sub-network Tuning Method (2022.acl-short)

Challenge:	et al., 2021) show that instruction models can be trained on crowdsourced datasets with task instructions to achieve superior performance.
Approach:	They examine security concerns of emergent instruction tuning paradigm that models are trained on crowdsourced datasets with task instructions to achieve superior performance.
Outcome:	The proposed model can achieve 90% success rate across four commonly used datasets.

Copied to clipboard

Runxin Xu, Fuli Luo, Baobao Chang, Songfang Huang, Fei Huang

Cross-Lingual Transfer

Challenge:	Existing multilingual pre-trained language models allow to adapt to target languages with only few labeled examples.
Approach:	They propose a simple cross-lingual sub-network tuning method that detects the most essential sub-netzwork for each target language and updates it during fine-tuning.
Outcome:	The proposed method improves on three multi-lingual tasks involving 37 different languages.

From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning (2025.naacl-long)

Copied to clipboard

Nan Xu, Fei Wang, Sheng Zhang, Hoifung Poon, Muhao Chen

E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning (2021.acl-long)

Challenge:	Motivated by in-context learning capabilities of Large Language Models (LLMs), multimodal LLMs with additional visual modality are also exhibited with similar ICL abilities when multiple image-text pairs are provided as demonstrations.
Approach:	They conduct systematic and principled evaluation of multimodal ICL for models of different scales on a broad spectrum of new yet critical tasks.
Outcome:	The proposed model performance improves on a broad spectrum of new yet critical tasks.

Copied to clipboard

Haiyang Xu, Ming Yan, Chenliang Li, Bin Bi, Songfang Huang, Wenming Xiao, Fei Huang

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning (2025.acl-long)

Challenge:	Existing vision-language pre-training methods use a two-step training procedure to learn visual features from image-text pairs.
Approach:	They propose a vision-language pre-trained model for V+L understanding and generation using a unified Transformer framework.
Outcome:	The proposed model can learn visual representation and semantic alignments between image and text on visual-text pairs and on visual processing tasks.

Copied to clipboard

Zhu Xu, Zhiqiang Zhao, Zihan Zhang, Yuchi Liu, Quanwei Shen, Fei Liu, Yu Kuang, Jian He, Conglin Liu

Challenge:	Large language models (LLMs) use tokenization methods but often obscure internal character structures within tokens.
Approach:	They propose a method that improves models’ ability to capture character positions within tokens by training them on reverse character prediction tasks using the tokenizer’s vocabulary.
Outcome:	Experiments show that the proposed method improves position prediction accuracy in large language models, enabling more precise identification of target characters in original text.

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection (2026.eacl-long)

Copied to clipboard

Yuhang Liu, Pengxiang Li, Zishu Wei, Congkai Xie, Xueyu Hu, Xinchen Xu, Shengyu Zhang, Xiaotian Han, Hongxia Yang, Fei Wu

Modularized Interaction Network for Named Entity Recognition (2021.acl-long)

Challenge:	Existing GUI Agents face challenges in multi-step reasoning and reliance on textual annotations, limiting their effectiveness.
Approach:	They propose an MLLM-based GUI Agent with a two-stage supervised fine-tuning pipeline that enhances GUI understanding and grounding.
Outcome:	InfiGUIAgent achieves competitive performance on several GUI benchmarks, highlighting the impact of native reasoning skills in enhancing GUI interaction for automation tasks.

Copied to clipboard

Fei Li, Zheng Wang, Siu Cheung Hui, Lejian Liao, Dandan Song, Jing Xu, Guoxiu He, Meihuizi Jia

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (NER) models focus on word-level information, while segment-based models focus only on word level information.
Approach:	They propose a Modularized Interaction Network (MIN) model which utilizes both word-level information and segment-level dependencies.
Outcome:	The proposed model outperforms the current state-of-the-art models on three NER benchmark datasets.

MetaScale: Test-Time Scaling with Evolving Meta-Thoughts (2026.findings-acl)

Copied to clipboard

Qin Liu, Wenxuan Zhou, Nan Xu, James Y. Huang, Fei Wang, Sheng Zhang, Hoifung Poon, Muhao Chen

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs (2023.findings-emnlp)

Challenge:	Existing approaches impose fixed cognitive structures that enhance performance in specific tasks but lack adaptability across diverse scenarios.
Approach:	They propose a test-time scaling framework based on meta-thoughts to improve performance . meta-thinkts are adaptive thinking strategies tailored to a given task .
Outcome:	Experimental results show that MetaScale outperforms standard inference approaches . it can scale more effectively with increasing sampling budgets and produces more structured responses .

Copied to clipboard

Hongru Wang, Rui Wang, Fei Mi, Yang Deng, Zezhong Wang, Bin Liang, Ruifeng Xu, Kam-Fai Wong

Natural Language Interfaces

Challenge:	Existing LLMs generate responses based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context.
Approach:	They propose a linguistic cue-based chain-of-thoughts method which enhances the LLMs inference with an intermediate reasoning step to find cues exhibited in the dialogue.
Outcome:	The proposed method outperforms standard prompting methods on in-depth dialogue questions and linguistic cues exhibited in the context.

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs (2025.findings-emnlp)

Copied to clipboard

Zige Wang, Qi Zhu, Fei Mi, Minghui Xu, Ruochun Jin, Wenjing Yang

Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval (2024.lrec-main)

Challenge:	Gradient-based data influence approximation is not feasible in practice.
Approach:	They propose a gradient-based data selection framework with clustering and a modified Upper Confidence Bound algorithm to solve this problem.
Outcome:	The proposed framework can achieve comparable results to the original gradient-based data selection methods while reducing computational consumption.

Copied to clipboard

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

Challenge:	Existing methods for video-text retrieval capture fine-grained semantic concepts . however, they lack the ability to capture finer-grain concepts such as objects and actions.
Approach:	They propose a dual-encoder architecture for fast video-text retrieval that learns lexicon representations to capture fine-grained semantics.
Outcome:	The proposed framework outperforms existing methods with 4.8% and 8.2% improvement on MSR-VTT and DiDeMo respectively.

Copied to clipboard

Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu

Over-Generation and Compaction: A Prompting Strategy for Procedural Text Adaptation with Large Language Models (2025.findings-emnlp)

Challenge:	In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach:	They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome:	The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.

Copied to clipboard

HyeongSik Kim, Xu Yanheng, Chaoqun Dong, Fei Du

UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)

Challenge:	Existing prompting strategies for large language models often yield superficial or erroneous adaptations due to alignmentinduced biases and the inherent complexity of procedural editing.
Approach:	They propose an overgenerationandcompaction prompting strategy that leverages the model’s latent knowledge and compacts them into concise, coherent adaptations.
Outcome:	The proposed approach improves adaptation consistency and feasibility compared to baseline prompting methods without additional fine-tuning or curated training resources.

Copied to clipboard

Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, Qin Jin, Liang He, Xin Lin, Fei Huang

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Challenge:	Existing studies for visually-situated language understanding have shown shallow zero-shot visual text recognition ability when fed a low-resolution image with salient text information.
Approach:	They propose a model for universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) their model is jointly finetuned on a wide range of visually situated language understanding tasks via a unified instruction format.
Outcome:	The proposed model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks across 5 domains: documents, tables, charts, natural images, and webpage screenshots.

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework (2025.acl-long)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Jundong Xu, Hao Fei, Meng Luo, Qian Liu, Liangming Pan, William Yang Wang, Preslav Nakov, Mong-Li Lee, Wynne Hsu

Adversarial Knowledge Stimulated Contrastive Prompting for Few-shot Language Learners (2023.findings-acl)

Challenge:	Existing systems fail to fully leverage the structure of logical tasks throughout the reasoning process, causing bottlenecks in efficiency and efficacy.
Approach:	They propose a logic-complete reasoning framework, Aristotle, which integrates symbolic expressions and logical rules into the entire reasoning process.
Outcome:	The proposed framework outperforms state-of-the-art reasoning frameworks in accuracy and efficiency.

Copied to clipboard

Kai Zheng, Qingfeng Sun, Yaming Yang, Tengchao Lv, Yeyong Pi, Changlin Zhao, Fei Xu, Qi Zhang

Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training (2024.lrec-main)

Challenge:	Prompt-based fine-tuning has boosted performance of Pre-trained language models on few-shot Natural Language Understanding (NLU) tasks by employing task-specific prompts.
Approach:	They propose a Cloze-driven prompt framework for prompt tuning that implicitly stimulates knowledge from pre-trained language models.
Outcome:	The proposed framework outperforms state-of-the-art for prompt-based fine-tuning on few-shot NLU tasks.

Copied to clipboard

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu

Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation (2023.findings-acl)

Challenge:	Existing methods for vision-language pre-training lack high-level semantics and text is not sufficiently involved in masked modeling.
Approach:	They propose a semantics-enhanced cross-modal MIM framework for vision-language representation learning that harvests high-level semantics from global image features via self-supervised agreement learning and transfers them to local patch encodings by sharing the encode space.
Outcome:	The proposed model achieves state-of-the-art or competitive performance on multiple vision-language tasks.

Copied to clipboard

Fei Yuan, Yinquan Lu, Wenhao Zhu, Lingpeng Kong, Lei Li, Yu Qiao, Jingjing Xu

Multilinguality

Challenge:	Existing monolithic models for multilingual neural machine translation encounter parameter interference and inefficient inference for large models.
Approach:	They propose a detachable multi-way model that assigns each language to an individual branch . they use data from OPUS to build a translation benchmark covering 433 languages .
Outcome:	The proposed model outperforms existing models in OPUS and is faster than existing models.

Multimodal Dialogue Response Generation (2022.acl-long)

Copied to clipboard

Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, Daxin Jiang

TinyChart: Efficient Chart Understanding with Program-of-Thoughts Learning and Visual Token Merging (2024.emnlp-main)

Challenge:	Existing studies focus on multimodal dialogue models but neglect generation methods.
Approach:	They propose a multimodal dialogue response generation task which requires multimodal dialogs containing both texts and images which are difficult to obtain.
Outcome:	Experiments show that the proposed model can generate informative text and high-resolution image responses.

Copied to clipboard

Liang Zhang, Anwen Hu, Haiyang Xu, Ming Yan, Yichen Xu, Qin Jin, Ji Zhang, Fei Huang

Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting (2024.naacl-long)

Challenge:	Recent studies have shown that multimodal large language models can be useful for chart understanding, but their size limits their use in resource-constrained environments.
Approach:	They propose an efficient multimodal large language model with only 3B parameters for chart understanding.
Outcome:	The proposed model outperforms several chart-understanding MLLMs with up to 13B parameters on ChartQA, Chart-to-Text, Chart to Table, OpenCQA, and ChartX.

Copied to clipboard

Rui Wang, Hongru Wang, Fei Mi, Boyang Xue, Yi Chen, Kam-Fai Wong, Ruifeng Xu

CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models (2025.coling-main)

Challenge:	Existing studies have focused on how LLMs handle inductive instructions, which may stem from users’ false beliefs or malicious intents.
Approach:	They propose a benchmark of Inductive Instructions where false knowledge is incorporated into instructions in multiple different styles.
Outcome:	The proposed model improves robustness against inductive instructions, despite different inductive styles and complexity.

Copied to clipboard

Zhongzhi Li, Ming-Liang Zhang, Pei-Jie Wang, Jian Xu, Rui-Song Zhang, Yin Fei, Zhi-Long Ji, Jin-Feng Bai, Zhen-Ru Pan, Jiaxin Zhang, Cheng-Lin Liu

Numerical Reasoning

Challenge:	Large language models excel in various language tasks, while large multimodal models effectively handle visual-language problems.
Approach:	They propose to use a multimodal multimodal model evaluation benchmark to evaluate model performance in Chinese K12 classrooms.
Outcome:	The proposed model evaluation tool is integrated with the CMMaTH dataset.

Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages (2022.acl-long)

Copied to clipboard

Xu Han, Yuqi Luo, Weize Chen, Zhiyuan Liu, Maosong Sun, Zhou Botong, Hao Fei, Suncong Zheng

DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling (2025.findings-acl)

Challenge:	Experimental results show that by applying our framework, we can easily learn effective FGET models for low-resource languages.
Approach:	They propose a cross-lingual contrastive learning framework to learn FGET models for low-resource languages.
Outcome:	The proposed framework can learn effective FGET models for low-resource languages even without human-labeled data.

Copied to clipboard

Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, Yongbin Li

Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering (2023.findings-acl)

Challenge:	Large language models (LLMs) enabled dialogue systems are one of the central modes in human-machine interaction.
Approach:	They propose a benchmark task for dialogue element MOdeling and Element Awareness and a new benchmark for dialogue agent interaction that allows the agent to model dialogue elements via imitation learning.
Outcome:	The proposed agent performs well in both dialogue element modeling and out-of-domain tasks.

Copied to clipboard

Qianglong Chen, Guohai Xu, Ming Yan, Ji Zhang, Fei Huang, Luo Si, Yin Zhang

mDPO: Conditional Preference Optimization for Multimodal Large Language Models (2024.emnlp-main)

Challenge:	Existing knowledge-enhanced methods have trouble obtaining knowledge from different knowledge bases . a concept-centric model can be used to generate a contrastive explanation for QA tasks .
Approach:	They propose a Concept-centric Prompt-bAsed Contrastive Explanation Generation model which converts obtained symbolic knowledge into the contrastive explanation for better distinguishing the differences among given candidates.
Outcome:	The proposed model achieves new SOTA on CSQA, QASC, and OBQA.

Copied to clipboard

Fei Wang, Wenxuan Zhou, James Y. Huang, Nan Xu, Sheng Zhang, Hoifung Poon, Muhao Chen

ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models (2023.emnlp-demo)

Challenge:	Recent studies have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement.
Approach:	They propose a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference.
Outcome:	The proposed method significantly improves performance on two multimodal LLMs of different sizes and three widely used benchmarks.

Copied to clipboard

Chenliang Li, He Chen, Ming Yan, Weizhou Shen, Haiyang Xu, Zhikai Wu, Zhicheng Zhang, Wenmeng Zhou, Yingda Chen, Chen Cheng, Hongzhu Shi, Ji Zhang, Fei Huang, Jingren Zhou

Monotonic Paraphrasing Improves Generalization of Language Model Prompting (2024.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior.
Approach:	They propose a framework that equips large language models with tool-use capabilities . they propose LLaMA and Chat-GLM as controllers, and a model-based agent framework .
Outcome:	The proposed framework equips open-source LLMs with tool-use capabilities . it provides a user-friendly system library with a customizable engine design .

Copied to clipboard

Qin Liu, Fei Wang, Nan Xu, Tianyi Yan, Tao Meng, Muhao Chen

Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet Extraction (2023.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated remarkable proficiency in zero-shot decision making and instruction following.
Approach:	They propose an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt rewriting, and a target LM that constrains the generation for lower perxity.
Outcome:	The proposed method can efficiently paraphrase the original prompt without altering its semantic meaning while decreasing the perplexity of each generation as calculated by the target LM.

Copied to clipboard

Ting Xu, Huiyun Yang, Zhen Wu, Jiaze Chen, Fei Zhao, Xinyu Dai

Sentiment Analysis

Challenge:	Existing ASTE datasets are limited in their ability to represent real-world scenarios, hindering progress in this area.
Approach:	They propose a new ASTE dataset that is manually annotated to better fit real-world scenarios by providing more diverse and realistic reviews.
Outcome:	The proposed dataset is manually annotated to better fit real-world scenarios.

End-to-end Deep Reinforcement Learning Based Coreference Resolution (P19-1)

Copied to clipboard

Hongliang Fei, Xu Li, Dingcheng Li, Ping Li

Information Extraction & Text Mining

Challenge:	Recent neural network models for coreference resolution are usually trained with heuristic loss functions that are computed over a sequence of local decisions.
Approach:	They propose an end-to-end reinforcement learning based coreference resolution model to directly optimize coreference evaluation metrics.
Outcome:	The proposed model achieves new state-of-the-art performance on the English OntoNotes v5.0 benchmark.

InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (2024.acl-long)

Copied to clipboard

Xintao Wang, Yunze Xiao, Jen-tse Huang, Siyu Yuan, Rui Xu, Haoran Guo, Quan Tu, Yaying Fei, Ziang Leng, Wei Wang, Jiangjie Chen, Cheng Li, Yanghua Xiao

Challenge:	Existing methods focus on knowledge and linguistic patterns of characters.
Approach:	They propose to evaluate character fidelity of role-playing agents with psychological scales . they propose to use psychological scale to measure personality traits of RPAs based on personality traits.
Outcome:	The proposed model reproduces character fidelity with psychological scales and shows that it is effective in measuring personality traits.

UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization (2026.acl-long)

Copied to clipboard

Zhengxi Lu, Fei Tang, Guangyi Liu, Jin Ma, Kaitao Song, Xu Tan, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

Information Retrieval

Challenge:	Experimental results show that UI-Copilot-7B achieves state-of-the-art performance on challenging MemGUI-Bench, outperforming strong 7B-scale GUI agents such as GUI-Owl-7B and UITARS-1.5-7B.
Approach:	They propose a collaborative framework where the GUI agent focuses on task execution while a lightweight copilot provides on-demand assistance for memory retrieval and numerical computation.
Outcome:	The proposed framework outperforms GUI-Owl-7B and UI-TARS-1.5-7B on MemGUI-Bench and delivers 17.1% improvement on AndroidWorld over the base Qwen model.

Transforming Visual Scene Graphs to Image Captions (2023.acl-long)

Copied to clipboard

Xu Yang, Jiawei Peng, Zihua Wang, Haiyang Xu, Qinghao Ye, Chenliang Li, Songfang Huang, Fei Huang, Zhangzikang Li, Yu Zhang

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models (2024.acl-long)

Challenge:	Existing approaches to generate captions using image captioning are based on multi-head attention (MHA)
Approach:	They propose to transform scene graphs into more descriptive captions by using multi-head attention to build a Graph Neural Network (GNN) . they construct a Mixture-of-Expert (MOE)-based decoder where each expert is built on MHA for discriminating the graph embeddings to generate different kinds of words.
Outcome:	The proposed framework can generate captions from multiple visual features and objects . it is based on a mixture-of-expert (MOE)-based decoder based upon MHA .

Copied to clipboard

Fangzhi Xu, Zhiyong Wu, Qiushi Sun, Siyu Ren, Fei Yuan, Shuai Yuan, Qika Lin, Yu Qiao, Jun Liu

Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter (D18-1)

Challenge:	Large Language Models (LLMs) have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language.
Approach:	They propose a model that integrates symbolic data into LLM training without loss of generality ability.
Outcome:	The proposed model performs better on symbol- and NL-centric tasks.

Copied to clipboard

Lijun Wu, Xu Tan, Di He, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu

Text Generation

Challenge:	Neural machine translation suffers from exposure bias and error propagation problem.
Approach:	They conduct a series of analyses to deeply understand the accuracy drop problem . they find that the left part of the translated sentence is often better than its right part .
Outcome:	The results show that the left part of the translated sentence is often better than its right part in left-to-right decoding models.

Divide and Conquer: Legal Concept-guided Criminal Court View Generation (2024.findings-emnlp)

Copied to clipboard

Qi Xu, Xiao Wei, Hang Yu, Qian Liu, Hao Fei

Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models (2025.findings-acl)

Challenge:	Existing methods for creating rationales for criminal cases do not pay enough attention to the important legal concepts.
Approach:	They propose a legal concept-guided court view generation framework that generates rationales based on predicted legal concepts . they first divide the court view into sub-views, then employ a solver and verifier to generate and select rationale.
Outcome:	The proposed model generates coherent and coherent court views on a real-world criminal case dataset.

Copied to clipboard

Haoyang Li, Xuejia Chen, Zhanchao Xu, Darian Li, Nicole Hu, Fei Teng, Yiming Li, Luyu Qiu, Chen Jason Zhang, Li Qing, Lei Chen

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA (2024.emnlp-main)

Challenge:	Existing benchmarks focus on linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical reasoning required in real-world scenarios.
Approach:	They propose a benchmark to evaluate numerical capabilities for large language models . they use a dataset to assess number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning.
Outcome:	The proposed benchmark evaluates six fundamental numerical capabilities: number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning.

Copied to clipboard

Minzheng Wang, Longze Chen, Fu Cheng, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li

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

Challenge:	Existing benchmarks for evaluating long-context language models employ irrelevant noise texts to artificially extend the length of test cases, diverging from the real-world scenarios of long-constituency applications.
Approach:	They propose a long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA) .
Outcome:	The proposed model can scale up the context window of large language models to perform in-depth analysis of multiple long documents.

Copied to clipboard

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

CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models (2025.acl-long)

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

Yongheng Zhang, Xu Liu, Ruoxi Zhou, Qiguang Chen, Hao Fei, Wenpeng Lu, Libo Qin

Rethinking Denoised Auto-Encoding in Language Pre-Training (2021.emnlp-main)

Challenge:	Existing studies on hallucinations in large language models are limited to a single scenario, either cross-lingual or cross-modal.
Approach:	They propose a joint Cross-lingual and Cross-modal hallucinations benchmark to fill this gap . they incorporate cross-lingual, cross-modal scenarios to assess hallucinic capabilities .
Outcome:	The proposed benchmark incorporates both cross-lingual and cross-modal hallucination scenarios to assess the cross-linguistic and crossmodal capabilities of LLMs.

Copied to clipboard

Fuli Luo, Pengcheng Yang, Shicheng Li, Xuancheng Ren, Xu Sun, Songfang Huang, Fei Huang

Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing (2022.emnlp-main)

Challenge:	Pre-trained models such as BERT have achieved success in learning sequence representations, but they tend to learn representations that are covariant with the noise of pre-training.
Approach:	They propose to train self-trained models to learn noise invariant sequence representations . they encourage consistency between original sequence and corrupted version via unsupervised instance-wise training signals.
Outcome:	The proposed model improves on 11 natural language understanding and cross-modal tasks and achieves 0.6% gain on GLUE benchmarks and 0.8% increment on NLVR2 .

Copied to clipboard

Nan Xu, Fei Wang, Bangzheng Li, Mingtao Dong, Muhao Chen

Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark (2025.coling-main)

Challenge:	Existing entity typing models are subject to spurious correlations due to shortcuts and biased training.
Approach:	They propose a method to augment existing model biases by combining spurious correlations with debiasedcounterparts to improve generalization.
Outcome:	The proposed method improves generalization of different entity typing models on the original and debiased test sets.

Copied to clipboard

Zhikun Xu, Yinghui Li, Ruixue Ding, Xinyu Wang, Boli Chen, Yong Jiang, Haitao Zheng, Wenlian Lu, Pengjun Xie, Fei Huang

Natural Language Interfaces

Challenge:	Recent work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer dynamic questions well.
Approach:	They propose a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest dynamic questions on the Chinese Internet.
Outcome:	The proposed benchmark will be one of the key data resources for improving LLMs’ Chinese question-answering ability in the future.

IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory (2025.acl-long)

Copied to clipboard

Wei Song, Zhenya Huang, Cheng Cheng, Weibo Gao, Bihan Xu, GuanHao Zhao, Fei Wang, Runze Wu

Linguistic Theories

Challenge:	Large language models have demonstrated exceptional performance across a wide range of tasks . however, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance and cost.
Approach:	They propose a multi-LLM routing framework that efficiently routes user queries to the most suitable LLM.
Outcome:	The proposed framework outperforms baseline methods in terms of effectiveness and interpretability.

Dense Retrieval as Indirect Supervision for Large-space Decision Making (2023.findings-emnlp)

Copied to clipboard

Nan Xu, Fei Wang, Mingtao Dong, Muhao Chen

Information Retrieval

Challenge:	Dense Decision Retrieval (DDR) is a learning-to-retrieve task for discriminative natural language understanding (NLU) tasks with large label spaces.
Approach:	They propose a novel approach to learning large-space discriminative NLU tasks as a learning-to-retrieve task by adopting a dual-encoder architecture that learns to predict by retrieving from a decision thesaurus.
Outcome:	The proposed approach outperforms baselines greatly on multi-label classification tasks, 1.17% in F1 score ultra-fine entity typing, and 1.26% in accuracy on three few-shot intent classification tasks on average.

Self-Improvement Programming for Temporal Knowledge Graph Question Answering (2024.lrec-main)

Copied to clipboard

Zhuo Chen, Zhao Zhang, Zixuan Li, Fei Wang, Yutao Zeng, Xiaolong Jin, Yongjun Xu

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)

Challenge:	Existing methods implicitly model time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively.
Approach:	They propose a temporal-based temporal programming method that leverages the in-context learning ability of Large Language Models to understand combinatory time constraints in questions.
Outcome:	The proposed method outperforms existing methods on multiTQ and CronQuestions datasets and is highly efficient on multi-level questions.

Copied to clipboard

Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng

AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)

Challenge:	Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome .
Approach:	They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens.
Outcome:	The proposed method reduces token usage by up to 44% while preserving accuracy.

Copied to clipboard

Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu

Instructional Fingerprinting of Large Language Models (2024.naacl-long)

Challenge:	Significant concerns emerge when addressing cultural sensitivity and local values.
Approach:	They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models.
Outcome:	The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks.

Copied to clipboard

Jiashu Xu, Fei Wang, Mingyu Ma, Pang Wei Koh, Chaowei Xiao, Muhao Chen

LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translation (2025.findings-acl)

Challenge:	Large language models (LLMs) require considerable cost to train from scratch . fingerprinting is essential to protect intellectual property and to ensure downstream users and developers adhere to their license terms.
Approach:	They propose a method for fingerprinting Large language models that implants a private key into the model to generate specific text when the key is present.
Outcome:	The proposed method prevents publisher overclaim and maintains robustness against fingerprint guessing and parameter-efficient training.

Copied to clipboard

Fei Yuan, Yinquan Lu, Lei Li, Jingjing Xu

Machine Translation

Challenge:	Existing methods to train a single model for massive languages have huge communication overheads and parameter interference.
Approach:	They propose an efficient training approach with an asymmetric multi-way model architecture for massive multilingual neural machine translation.
Outcome:	The proposed model is 16.2 faster than the distributed training method for M2M-100-12B while improving the translation performance by an average of 2.2 BLEU on Flores-101.

A Synthetic Data Generation Framework for Grounded Dialogues (2023.acl-long)

Copied to clipboard

Jianzhu Bao, Rui Wang, Yasheng Wang, Aixin Sun, Yitong Li, Fei Mi, Ruifeng Xu

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)

Challenge:	Existing approaches to train grounded dialogues require large amounts of data.
Approach:	They propose a synthetic data generation framework for grounded dialogues that takes knowledge data and heuristics to determine a dialogue flow and incrementally turn it into a dialog.
Outcome:	The proposed framework significantly boosts model performance in training data and low-resource scenarios.

Copied to clipboard

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

Visual Data in NLP

Challenge:	Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment.
Approach:	They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives.
Outcome:	The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering.

Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances (2024.acl-long)

Copied to clipboard

Hanlei Zhang, Hua Xu, Fei Long, Xin Wang, Kai Gao

Parallel Instance Query Network for Named Entity Recognition (2022.acl-long)

Challenge:	Existing methods for semantics discovery focus on text, video, and audio, failing to leverage the rich multimodal information in the real world.
Approach:	They propose a method to construct augmentation views for multimodal data and use them to perform pre-training to establish well-initialized representations for subsequent clustering.
Outcome:	The proposed method improves on benchmark multimodal intent and dialogue act datasets by 2-6% over state-of-the-art methods.

Copied to clipboard

Yongliang Shen, Xiaobin Wang, Zeqi Tan, Guangwei Xu, Pengjun Xie, Fei Huang, Weiming Lu, Yueting Zhuang

Knowledge Representation

Challenge:	Named entity recognition is a fundamental task in natural language processing.
Approach:	They propose a method that sets up global and learnable instance queries to extract entities from a sentence in a parallel manner.
Outcome:	The proposed method outperforms existing state-of-the-art models on nested and flat datasets.

Multi-modal Action Chain Abductive Reasoning (2023.acl-long)

Copied to clipboard

Mengze Li, Tianbao Wang, Jiahe Xu, Kairong Han, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Shiliang Pu, Fei Wu

Aspect Sentiment Classification with Aspect-Specific Opinion Spans (2020.emnlp-main)

Challenge:	Existing models for Abductive Reasoning are limited in their ability to infer the most plausible explanation of incomplete known phenomena.
Approach:	They propose a vision-language task that aims to imagine the most plausible event by spatio-temporal grounding in past video and infer the hypothesis of subsequent action chain layer by layer.
Outcome:	The proposed model outperforms existing video-language models in terms of effectiveness on the proposed dataset.

Copied to clipboard

Lu Xu, Lidong Bing, Wei Lu, Fei Huang

Sentiment Analysis

Challenge:	Existing attention-based models for sentiment analysis are not able to capture opinion spans as a whole or variable-length opinion span.
Approach:	They propose a model that extracts aspect-specific opinion spans and evaluates sentiment polarity by exploiting extracted opinion features.
Outcome:	The proposed model extracts aspect-specific opinion spans and evaluates sentiment polarity using extracted opinion features.

GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models (2025.emnlp-demos)

Copied to clipboard

Hengyu Luo, Zihao Li, Joseph Attieh, Sawal Devkota, Ona de Gibert, Xu Huang, Shaoxiong Ji, Peiqin Lin, Bhavani Sai Praneeth Varma Mantina, Ananda Sreenidhi, Raúl Vázquez, Mengjie Wang, Samea Yusofi, Fei Yuan, Jörg Tiedemann

Multilinguality

Challenge:	Existing evaluation frameworks focus on English and a handful of high-resource languages, thereby overlooking the realistic performance of large language models in multilingual and lower-resourced scenarios.
Approach:	They propose a unified and lightweight framework that integrates 27 benchmarks under a standard ISO 639-3 language identifier system to enable seamless incorporation of new benchmarks.
Outcome:	The proposed framework integrates 27 benchmarks under a standard ISO 639-3 language identifier system, allowing for seamless incorporation of new benchmarks.

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models (2023.acl-long)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Rui Wang, Jianzhu Bao, Fei Mi, Yi Chen, Hongru Wang, Yasheng Wang, Yitong Li, Lifeng Shang, Kam-Fai Wong, Ruifeng Xu

Natural Language Interfaces

Challenge:	Existing research on retrieval-augmented and retrieval free dialogue models focuses on retrieving knowledge from external sources and rely on finely annotated retrieval training data and knowledge-grounded responses.
Approach:	They propose a retrieval-free approach by turning knowledge documents into simulated multi-turn dialogues using a Multi-Document Traversal algorithm.
Outcome:	The proposed approach outperforms retrieval-augmented models while being cheaper and faster at domain transfer.

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Xu Huang, Wenhao Zhu, Hanxu Hu, Conghui He, Lei Li, Shujian Huang, Fei Yuan

Knowledge Mechanisms in Large Language Models: A Survey and Perspective (2024.findings-emnlp)

Challenge:	Existing multilingual benchmarks focus primarily on language understanding tasks.
Approach:	They develop a multi-way multilingual benchmark that measures critical capabilities of large language models across languages.
Outcome:	Extensive experiments on BenchMAX reveal uneven utilization of core capabilities across languages, emphasizing the performance gaps that scaling model size alone does not resolve.

Copied to clipboard

Mengru Wang, Yunzhi Yao, Ziwen Xu, Shuofei Qiao, Shumin Deng, Peng Wang, Xiang Chen, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Faithful Logical Reasoning via Symbolic Chain-of-Thought (2024.acl-long)

Challenge:	Using large language models, we can understand knowledge mechanisms in LLMs for learning, storage, utilization, and evolution.
Approach:	They propose to analyze knowledge mechanisms in Large Language Models (LLMs) they examine utilization, evolution, and the potential dark knowledge (hypothesis) they hope to help understand knowledge in LLMs and provide insights for future research .
Outcome:	The proposed model can be used to analyze the evolution of parametric knowledge in LLMs.

Copied to clipboard

Jundong Xu, Hao Fei, Liangming Pan, Qian Liu, Mong-Li Lee, Wynne Hsu

Machine Translation

Challenge:	SymbCoT is a framework that integrates symbolic expressions and logic rules with CoT prompting.
Approach:	They propose a Symbolic Chain-of-Thought framework that integrates symbolic expressions and logic rules with CoT prompting.
Outcome:	The proposed framework improves on 5 standard datasets with symbolic expressions and rules . it shows that it is more faithful, flexible, and explainable than the current method .

Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis (2024.findings-acl)

Copied to clipboard

Haining Wang, Kang He, Bobo Li, Lei Chen, Fei Li, Xu Han, Chong Teng, Donghong Ji

Sentiment Analysis

Challenge:	Aspect-based Sentiment Analysis (ABSA) data augmentation has attracted increasing attention in recent years due to data sparsity.
Approach:	They propose a framework to augment ABSA data using pseudo labels for target domain . they refine generated labeled data using a natural language inference filter .
Outcome:	The proposed framework outperforms 7 strong baselines on 4 kinds of ABSA tasks.

Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models (2024.findings-naacl)

Copied to clipboard

Rui Wang, Fei Mi, Yi Chen, Boyang Xue, Hongru Wang, Qi Zhu, Kam-Fai Wong, Ruifeng Xu

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Challenge:	Large Language Models (LLMs) suffer catastrophic forgetting when tailored to specific domains . authors present a novel approach to manage multi-domain LLM adaptation .
Approach:	They propose a strategy to manage multi-domain LLM adaptation using self-distillation and role integration.
Outcome:	The proposed model alleviates catastrophic forgetting and inter-domain confusion while maintaining robust general capabilities.

Copied to clipboard

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen

Challenge:	a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach:	They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome:	The proposed benchmarks show that the current models perform worse than the human ceiling.

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing (2024.acl-long)

Copied to clipboard

Ziwei Chai, Guoyin Wang, Jing Su, Tianjie Zhang, Xuanwen Huang, Xuwu Wang, Jingjing Xu, Jianbo Yuan, Hongxia Yang, Fei Wu, Yang Yang

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities across a wide spectrum of tasks, but performance and reliability in certain specialized domains still fall short of expectations.
Approach:	They propose a unified generalist framework that facilitates seamless integration of multiple expert LLMs.
Outcome:	The proposed framework outperforms existing multi-LLM collaboration paradigms across six diverse expert domains.

AEG: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning (2022.emnlp-main)

Copied to clipboard

Jianzhu Bao, Yasheng Wang, Yitong Li, Fei Mi, Ruifeng Xu