Papers by Chao Xu

Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning (2025.emnlp-main)

Challenge:	Recent studies have shown that large language models are useful, honest, harmless (HHH) however, RLHF requires high hardware resources and human efforts.
Approach:	They propose a framework that allows LLMs to align themselves with HHH . they use IF and reinforcement learning from human feedback to fine-tune their models .
Outcome:	The proposed framework achieves similar performance to RLHF and human-generated models with a minimal alignment tax.

Copied to clipboard

Haijiang Liu, Qiyuan Li, Chao Gao, Yong Cao, Xiangyu Xu, Xun Wu, Daniel Hershcovich, Jinguang Gu

Think Wider, Detect Sharper: Reinforced Reference Coverage for Document-Level Self-Contradiction Detection (2025.emnlp-main)

Challenge:	Introducing MARK, a framework for cultural value survey simulation . based on type dynamics theory, it improves accuracy and interpretation of models .
Approach:	They propose a framework that integrates psychological theory into cultural value survey simulations.
Outcome:	The proposed framework outperforms baseline models on the World Values Survey by 10% accuracy and reduces divergence between model predictions and human preferences.

Copied to clipboard

Yuhao Chen, Yuanjie Lyu, Shuochen Liu, Chao Zhang, Junhui Lv, Tong Xu

ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average (2024.emnlp-industry)

Challenge:	Recent approaches to document-level contradiction detection (DSCD) only gain marginal improvement and often introduce inconsistencies across repeated responses.
Approach:	They propose a method that combines supervised fine-tuning and reinforcement learning to enhance document-level contradiction detection (DSCD) they propose to use a task-specific reward function to expand the model’s reasoning scope, boosting both accuracy and consistency.
Outcome:	The proposed method significantly boosts Llama 3.1-8B-Instruct’s accuracy from 38.5% to 51.1%, and consistency from 59.6% to76.2%.

Copied to clipboard

Shaojie Shi, Xiaoyu Tan, Xihe Qiu, Chao Qu, Kexin Nie, Yuan Cheng, Wei Chu, Xu Yinghui, Yuan Qi

PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt Learning (2022.emnlp-industry)

Challenge:	Large language models (LLMs) have attracted significant interest from the research community due to their broad applicability in many language-oriented tasks.
Approach:	They propose a framework which uses pre-training datasets to rewrite instructions and generate negative responses to preserve the performance of the original LLM.
Outcome:	The proposed framework can erase the pre-training data while maintaining the performance of the original model.

Copied to clipboard

Zeyang Lei, Chao Zhang, Xinchao Xu, Wenquan Wu, Zheng-yu Niu, Hua Wu, Haifeng Wang, Yi Yang, Shuanglong Li

Rehearsal-free Continual Language Learning via Efficient Parameter Isolation (2023.acl-long)

Challenge:	Online advertisement text generation models have achieved remarkable success in generating high-quality text ads, but some challenges remain, such as low-resource scenarios and training efficiency for multiple ad tasks.
Approach:	They propose a unified text ad generation framework with multi-task prompt learning to tackle low-resource ade generation problem and a multi-step prompt learning mechanism to efficiently solve multiple aed generation tasks.
Outcome:	The proposed framework outperforms the state-of-the-art on offline and online metrics.

Copied to clipboard

Zhicheng Wang, Yufang Liu, Tao Ji, Xiaoling Wang, Yuanbin Wu, Congcong Jiang, Ye Chao, Zhencong Han, Ling Wang, Xu Shao, Wenqiu Zeng

Data Augmentation for Few-Shot Knowledge Graph Completion from Hierarchical Perspective (2022.coling-1)

Challenge:	Existing methods for learning continual tasks do not cache history data, which makes the problem more challenging.
Approach:	They propose a method that allocates a small portion of private parameters and learns them with a shared pre-trained model.
Outcome:	The proposed method is comparable to existing methods and comparable to those using historical data.

Copied to clipboard

Yuanzhou Yao, Zhao Zhang, Yongjun Xu, Chao Li

AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs (2025.acl-long)

Challenge:	Existing knowledge graph completion models require only a few associative triples to complete a relationship.
Approach:	They propose to perform data augmentation from two perspectives to solve the FKGC problem by inferring new triple facts from existing models.
Outcome:	The proposed framework can be applied to a number of existing models.

Copied to clipboard

Nicholas E. Corrado, Julian Katz-Samuels, Adithya M Devraj, Hyokun Yun, Chao Zhang, Yi Xu, Yi Pan, Bing Yin, Trishul Chilimbi

BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers (2024.emnlp-main)

Challenge:	Existing approaches to align large language models rely on large ablation studies, heuristics, or human intuition to produce models with strong performance across tasks.
Approach:	They propose an algorithm that mixes datasets during LLM training to balance performance across multiple tasks.
Outcome:	The proposed algorithm outperforms existing methods on multitask alignment setups and achieves convergence rate of O(1/T) in the convex case.

Copied to clipboard

Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Yanqiao Zhu, May Dongmei Wang, Joyce Ho, Chao Zhang, Carl Yang

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

Challenge:	Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedically tasks but still challenging due to the lack of sufficient publicly annotated biomedic data and computational resources.
Approach:	They propose a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedically corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs.
Outcome:	Experiments on 5 biomedical tasks across 11 datasets confirm the performance of the retrieval model on various biomedically demanding tasks.

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

Let’s Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model (2025.coling-main)

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.

Copied to clipboard

Haoyun Xu, Runzhe Zhan, Yingpeng Ma, Derek F. Wong, Lidia S. Chao

“I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) are composed of neurons that exhibit diverse behaviors and roles.
Approach:	They propose a novel approach that refines the granularity of parameter training down to the individual neuron, enabling a more parameter-efficient fine-tuning model.
Outcome:	The proposed approach exceeds the performance of full-parameter fine-tuning and PEFT and provides insights into the analysis of neurons.

Copied to clipboard

Jianshuo Dong, Yutong Zhang, Liu Yan, Zhenyu Zhong, Tao Wei, Ke Xu, Minlie Huang, Chao Zhang, Han Qiu

SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation (2026.findings-acl)

Challenge:	Large language models (LLMs) exhibit prompt leakage vulnerabilities, raising intellectual property and confidentiality concerns.
Approach:	They use probing techniques to capture LLMs’ intent-related internal representations and show that they internalize prompt leakage intents in their hidden states before generating tokens.
Outcome:	The proposed probes achieve 90%+ AUROC across all tested models, even when applied to new system prompts and attacks.

Copied to clipboard

Long Li, Zhijian Zhou, Jiangxuan Long, Peiyang Liu, Weidi Xu, Zhe Wang, Shirui Pan, Chao Qu

Programming Languages in NLP

Challenge:	Agentic SQL is a framework for multiturn agent learning, but it is limited to single-turn paradigms.
Approach:	They propose a framework that provides a universal two-tiered reward mechanism for credit assignment . they propose 'Aggregated Trajectory Reward' to resolve multi-turn credit assignment.
Outcome:	The proposed framework outperforms SOTA Arctic-Text2SQL-R1-7B on BIRD and Spider 2.0 using identical models.

ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry (2025.acl-industry)

Copied to clipboard

Junjie Jiang, Haodong Wu, Yongqi Zhang, Songyue Guo, Bingcen Liu, Caleb Chen Cao, Ruizhe Shao, Chao Guan, Peng Xu, Lei Chen

Improving Large-scale Paraphrase Acquisition and Generation (2022.emnlp-main)

Challenge:	drafting method statements is labor-intensive and time-consuming . traditional methods involve using static templates filled in manually by engineers .
Approach:	They propose a framework that automates method statement generation by using multi-agent collaboration.
Outcome:	The proposed framework achieves 4.38 ContentScore, excelling in specialization, completeness, organization, and clarity.

Copied to clipboard

Yao Dou, Chao Jiang, Wei Xu

Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking (2021.findings-acl)

Challenge:	Existing Twitter-based paraphrase datasets lack quality definitions for identification and generation tasks.
Approach:	They propose to use two separate definitions of paraphrase for identification and generation tasks in existing Twitter-based paraphrase datasets.
Outcome:	The proposed model achieves state-of-the-art performance of 84.2 F1 for automatic paraphrase identification compared to other models fine-tuned on other corpora such as Quora, MSCOCO, and ParaNMT.

Copied to clipboard

Heng-Da Xu, Zhongli Li, Qingyu Zhou, Chao Li, Zizhen Wang, Yunbo Cao, Heyan Huang, Xian-Ling Mao

Syntactic Text Processing

Challenge:	Chinese Spell Checking (CSC) aims to detect and correct erroneous characters for usergenerated text in Chinese.
Approach:	They propose a Chinese spell checker that leverages multimodal Chinese characters' information to predict the correct output.
Outcome:	The proposed model outperforms strong baselines on the SIGHAN benchmarks by a large margin.

Cold-Start Data Selection for Better Few-shot Language Model Fine-tuning: A Prompt-based Uncertainty Propagation Approach (2023.acl-long)

Copied to clipboard

Yue Yu, Rongzhi Zhang, Ran Xu, Jieyu Zhang, Jiaming Shen, Chao Zhang

Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks (2025.findings-acl)

Challenge:	Pre-trained language models (PLMs) have achieved competitive performance with limited labeled data for many NLP tasks.
Approach:	They propose a prompt-based data selection method for pre-trained language models fine-tuning under cold-start scenarios.
Outcome:	The proposed method outperforms the strongest cold-start data selection baselines on six text classification datasets with 128 labels.

Copied to clipboard

Yuanjie Lyu, Chao Zhang, Yuhao Chen, Yong Chen, Tong Xu

Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling (2020.coling-main)

Challenge:	Recent advances in "Chain of Models" approach increase resource demands as each model must be deployed separately.
Approach:	They propose a prompt-tuning method that enables models to share hidden states . they modify input and attention masks during training to eliminate redundant forward passes .
Outcome:	Empirical results show that FTHSS matches the performance of traditional model chains while improving inference efficiency.

Copied to clipboard

Xu Cao, Deyi Xiong, Chongyang Shi, Chao Wang, Yao Meng, Changjian Hu

Semantic Parsing

Challenge:	Existing joint models for intent detection and slot filling show insufficient robustness . however, some small changes of inputs can fool the models to produce wrong predictions .
Approach:	They propose a joint adversarial training model that generates adversarials to attack the joint model and trains the model to defend against the adversarial examples.
Outcome:	The proposed model achieves significantly higher scores and improves robustness on two datasets.

Multi-Stage LLM Fine-Tuning with a Continual Learning Setting (2025.findings-naacl)

Copied to clipboard

Changhao Guan, Chao Huang, Hongliang Li, You Li, Ning Cheng, Zihe Liu, Yufeng Chen, Jinan Xu, Jian Liu

Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents (2025.emnlp-main)

Challenge:	Large language models (LLMs) have made significant progress in knowledge-intensive applications, but they may face a multi-stage continuous learning scenario.
Approach:	They propose a multi-stage continuous learning paradigm that includes a preference-based learning bias to identify potential knowledge conflicts and a self-distillation-based data augmentation strategy to expand and enrich the training corpus.
Outcome:	The proposed learning paradigm achieves a significant improvement in accuracy after 7 stages of fine-tuning compared to previous methods while preserving general knowledge.

Copied to clipboard

Xueqiao Zhang, Chao Zhang, Jingtao Xu, Yifan Zhu, Xin Shi, Yi Yang, Yawei Luo

Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs (2026.acl-long)

Challenge:	Existing approaches to RPAs focus on static role profiles, overlooking dynamic perceptual abilities inherent to humans.
Approach:	They propose a framework that combines adaptive temporal sampling with dynamic and static role profiles.
Outcome:	The proposed framework combines adaptive temporal sampling with dynamic and static role profiles.

Copied to clipboard

Binxing Xu, Hao Gu, Lujun Li, Hao Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Xintong Yang, Chao Li, Sirui Han, Yike Guo

HyperIDP: Customizing Temporal Hypergraph Neural Networks for Multi-Scale Information Diffusion Prediction (2025.coling-main)

Challenge:	Existing approaches to training LLMs at ultra-low precisions suffer from convergence instability and substantial training costs.
Approach:	They propose a progressive QAT framework with outlier channel splitting to address these issues . they use nested structure of integer quantization grids to enable a "train once, deploy any precision" paradigm .
Outcome:	The proposed framework outperforms baselines on both Llama2/3 and W2A16, with an 11 speedup over BF16.

Copied to clipboard

Haowei Xu, Chao Gao, Xianghua Li, Zhen Wang

Enhancing Neural Topic Model with Multi-Level Supervisions from Seed Words (2023.findings-acl)

Challenge:	Existing studies on information diffusion prediction have focused on both macroscopic and microscopic scales.
Approach:	They propose a hypergraph-based model that manages both macroscopic and microscopic diffusion predictions.
Outcome:	The proposed model outperforms baseline models on both macroscopic and microscopic tasks.

Copied to clipboard

Yang Lin, Xin Gao, Xu Chu, Yasha Wang, Junfeng Zhao, Chao Chen

Information Extraction & Text Mining

Challenge:	Existing topic seed words are difficult to incorporate into topic models due to the semantic diversity of natural language.
Approach:	They propose a neural topic model enhanced with supervisions from seed words on word and document levels.
Outcome:	The proposed model outperforms the state-of-the-art seeded topic models in terms of topic quality and classification accuracy.

Neural CRF Model for Sentence Alignment in Text Simplification (2020.acl-main)

Copied to clipboard

Chao Jiang, Mounica Maddela, Wuwei Lan, Yang Zhong, Wei Xu

RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)

Challenge:	Text simplification systems are based on the quality and quantity of complex-simple sentence pairs extracted by aligning sentences between parallel articles.
Approach:	They propose a neural CRF alignment model which leverages the sequential nature of sentences in parallel documents and utilizes a sentence pair model to capture semantic similarity.
Outcome:	The proposed model outperforms previous work on monolingual sentence alignment task by more than 5 points in F1.

Copied to clipboard

Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, Haobo Wang

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following (2026.acl-long)

Challenge:	Existing benchmarks for large language models focus on simple, flat table structures.
Approach:	They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.
Outcome:	The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.

Copied to clipboard

Yuancheng Yang, Lin Yang, Xu Wang, Chao Tong, Haihua Yang

Neural semi-Markov CRF for Monolingual Word Alignment (2021.acl-long)

Challenge:	Experiments show that enhancing implicit reasoning capabilities can significantly improve complex instruction following in large language models.
Approach:	They propose a method to enhance LLMs’ understanding of implicit reasoning instructions by formalizing such instructions as verifiable reasoning graphs and fine-tuning with graph reasoning.
Outcome:	The proposed method outperforms existing models on five complex instruction following benchmarks and will be open-sourced in the near future.

Copied to clipboard

Wuwei Lan, Chao Jiang, Wei Xu

arXivEdits: Understanding the Human Revision Process in Scientific Writing (2022.emnlp-main)

Challenge:	Experimental results show that our proposed model outperforms all previous approaches for monolingual word alignment.
Approach:	They propose a neural semi-Markov CRF alignment model which unifies word and phrase alignments through variable-length spans.
Outcome:	The proposed model outperforms existing models on in-domain and out-of-domain evaluations and a QA-based benchmark with human annotations.

Copied to clipboard

Chao Jiang, Wei Xu, Samuel Stevens

Challenge:	a new computational framework is developed to study text revision in scientific writing . authors propose a method to extract revision at document-, sentence-, and word-levels .
Approach:	They propose a computational framework for studying text revision in scientific writing . arXivEdits is an annotated corpus of 751 full papers from arX . authors propose to use sentence alignment, fine-grained edits and intents to extract revision .
Outcome:	The proposed framework can be used to study revision in scientific writing.

BMInf: An Efficient Toolkit for Big Model Inference and Tuning (2022.acl-demo)

Copied to clipboard

Xu Han, Guoyang Zeng, Weilin Zhao, Zhiyuan Liu, Zhengyan Zhang, Jie Zhou, Jun Zhang, Jia Chao, Maosong Sun

A Speaker-Aware Co-Attention Framework for Medical Dialogue Information Extraction (2022.emnlp-main)

Challenge:	Recent years, pre-trained language models (PLMs) have achieved promising results on various NLP tasks.
Approach:	They propose an open-source toolkit for big model inference and tuning which can support big model tuning at extremely low computation cost.
Outcome:	The proposed toolkit can support big model inference and tuning at extremely low computation cost.

Copied to clipboard

Yuan Xia, Zhenhui Shi, Jingbo Zhou, Jiayu Xu, Chao Lu, Yehui Yang, Lei Wang, Haifeng Huang, Xia Zhang, Junwei Liu

Natural Language Interfaces

Challenge:	With the development of medical digitization, the extraction and structuring of electronic medical records (EMRs) have become challenging but fundamental tasks.
Approach:	They propose a speaker-aware dialogue encoder with multi-task learning which takes the speaker's identity into account and a co-attention fusion network to aggregate the utterance information.
Outcome:	The proposed framework outperforms the state-of-the-art methods on the public medical dialogue extraction datasets to demonstrate its superiority.

DoSEA: A Domain-specific Entity-aware Framework for Cross-Domain Named Entity Recogition (2022.coling-1)

Copied to clipboard

Minghao Tang, Peng Zhang, Yongquan He, Yongxiu Xu, Chengpeng Chao, Hongbo Xu

Challenge:	Existing approaches to named entity recognition ignore domain-specific information and suffer from subtype conflicts.
Approach:	They propose a machine reading comprehension framework which can identify domain-specific semantic differences and mitigate the subtype conflicts between domains.
Outcome:	The proposed framework can identify domain-specific semantic differences and mitigate the subtype conflicts between domains.

WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning (2025.emnlp-main)

Copied to clipboard

Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, Lihong Li

Challenge:	Existing work on reinforcement learning has focused on single-turn tasks such as solving math problems.
Approach:	They propose a framework that learns directly from online interactions by asynchronously generating diverse trajectories, guided by binary rewards depending on task success.
Outcome:	Experiments on the WebArena-Lite benchmark show that the framework outperforms state-of-the-art methods and strong proprietary models.

PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching (2023.emnlp-industry)

Copied to clipboard

Zhenting Qi, Xiaoyu Tan, Shaojie Shi, Chao Qu, Yinghui Xu, Yuan Qi

GuoFeng: A Benchmark for Zero Pronoun Recovery and Translation (2022.emnlp-main)

Challenge:	Low-Rank Adaptation (LoRA) has been used to adapt Large Language Models to a variety of tasks, but it requires substantial computational resources to perform.
Approach:	They propose a low-rank adaptive learning approach that leverages LoRA's in-context learning capability through prompt matching via reinforcement learning in resource-constrained environments.
Outcome:	The proposed model improves LoRA performance on evaluation metrics and utilises consumer-grade GPU resources.

Copied to clipboard

Mingzhou Xu, Longyue Wang, Derek F. Wong, Hongye Liu, Linfeng Song, Lidia S. Chao, Shuming Shi, Zhaopeng Tu

Multilinguality

Challenge:	ZPs are often omitted when they can be pragmatically or grammatically inferred from intraand inter-sentential contexts.
Approach:	They propose a benchmark testset for target evaluation on Chinese-English ZP translation.
Outcome:	The proposed testset covers five genres and identifies current challenges for evaluation.

DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models (2023.emnlp-main)

Copied to clipboard

Xinwei Wu, Junzhuo Li, Minghui Xu, Weilong Dong, Shuangzhi Wu, Chao Bian, Deyi Xiong

Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding (2026.eacl-long)

Challenge:	Existing studies have demonstrated that pretrained language models memorize and regurgitate a significant portion of training data, including atypical data points that appear only once in the training data.
Approach:	They propose a method to locate and erase risky neurons in order to eliminate the impact of privacy data in the model in batches.
Outcome:	The proposed method eliminates the impact of privacy data in the model in batches without affecting the model's performance.

Copied to clipboard

Juncheng Wang, Zhe Hu, Chao Xu, Siyue Ren, Yuxiang Feng, Yang Liu, Baigui Sun, Shujun Wang

End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning (2026.acl-long)

Challenge:	Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts.
Approach:	They propose a lightweight auxiliary model trained with a GAE-inspired objective to predict final instruction-following quality from partial generations.
Outcome:	The proposed model achieves 10 points improvement in CLAP score over baseline AR models while maintaining computational parity with best-of-N decoding.

Copied to clipboard

Guanzhong Chen, Shaoxiong Yang, Chao Li, Wei Liu, Jian Luan, Zenglin Xu

PSC: Extending Context Window of Large Language Models via Phase Shift Calibration (2024.emnlp-main)

Challenge:	Existing multi-agent reinforcement learning methods depend on large critic networks to evaluate joint actions, leading to instability and high memory costs.
Approach:	They propose a method to optimize large language models for agent-specific roles . they propose combining agent-based frameworks with retrieval-augmented generation .
Outcome:	Experiments show that multi-agent group policy optimization outperforms baselines in task performance and computational efficiency.

Copied to clipboard

Wenqiao Zhu, Chao Xu, Lulu Wang, Jun Wu

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation (2024.emnlp-main)

Challenge:	Large-scale language models (LLMs) have shown impressive results across a variety of tasks.
Approach:	They propose a module for calibrating the frequencies predefined by existing methods . they conducted extensive experiments across multiple models and tasks .
Outcome:	The proposed method reduces perplexity as the context window size is varied from 16k to 32k and up to 64k.

Copied to clipboard

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen

Information Retrieval

Challenge:	Large language models (LLMs) often produce factual errors due to limited internal knowledge.
Approach:	They propose a retrieval-augmented generation framework that generates plan tokens to guide subsequent generation.
Outcome:	The proposed framework improves the accuracy of large language models with external knowledge sources.

Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers (2025.emnlp-main)

Copied to clipboard

Juncheng Wang, Chao Xu, Cheng Yu, Zhe Hu, Haoyu Xie, Guoqi Yu, Lei Shang, Shujun Wang

Boosting Data Utilization for Multilingual Dense Retrieval (2025.emnlp-main)

Challenge:	Autoregressive language models excel in text-to-audio generation, but lag behind diffusion models by a non-trivial margin.
Approach:	They propose a framework that integrates multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning.
Outcome:	The proposed framework outperforms existing LM-based and diffusion-based systems in audio synthesis.

Copied to clipboard

Chao Huang, Fengran Mo, Yufeng Chen, Changhao Guan, Zhenrui Yue, Xinyu Wang, Jinan Xu, Kaiyu Huang

Information Retrieval

Challenge:	Existing studies focus on fine-tuning multilingual dense retrieval models, but data scarcity for low-resource languages makes it difficult to align representations in a shared vector space.
Approach:	They propose to obtain high-quality hard negative samples and effective mini-batch data to boost data utilization for multilingual dense retrieval by obtaining high-quality negative samples.
Outcome:	The proposed method outperforms existing baselines on a multilingual retrieval benchmark, MIRACL, with 16 languages.

MedReadMe: A Systematic Study for Fine-grained Sentence Readability in Medical Domain (2024.emnlp-main)

Copied to clipboard

Chao Jiang, Wei Xu

Challenge:	Using fine-grained readability measures is the first step towards making medical texts more accessible.
Approach:	They propose a dataset MedReadMe which measures sentences and complex spans with an annotation tool.
Outcome:	The proposed dataset covers 650 linguistic features and additional complex span features, and is compared against state-of-the-art methods using large language models.

To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization (2025.findings-acl)

Copied to clipboard

Haozhe Wang, Long Li, Chao Qu, Weidi Xu, Fengming Zhu, Wei Chu, Fangzhen Lin

Document Graph for Neural Machine Translation (2021.emnlp-main)

Challenge:	Existing tools that integrate chain-of-thought reasoning and code execution lack metacognitive awareness to integrate tools.
Approach:	They propose a framework that synergizes structured exploration with off-policy RL optimization to create a cycle between metacognitive tool-use decisions and evolving capabilities.
Outcome:	The proposed framework improves over 11% on MATH500 and 9.4% on AIME without o1-like CoT.

Copied to clipboard

Mingzhou Xu, Liangyou Li, Derek F. Wong, Qun Liu, Lidia S. Chao

Multilinguality

Challenge:	Existing document-level NMT methods fail to leverage contexts beyond a few set of previous sentences.
Approach:	They propose to represent a document as a graph that connects relevant contexts regardless of distances.
Outcome:	Experiments on IWSLT English–French, Chinese-English, WMT English–German and Opensubtitle English–Russian show that using document graphs can significantly improve translation quality.

DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning (2026.findings-acl)

Copied to clipboard

Chao Huang, Zeliang Zhang, Jiang Liu, Ximeng Sun, Jialian Wu, Xiaodong Yu, Ze Wang, Chenliang Xu, Emad Barsoum, Zicheng Liu

SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy Labels (2023.acl-industry)

Challenge:	Multimodal large language models (MLLMs) have made rapid progress in perception and alignment, but their reasoning ability often lags behind strong text-only LLMs.
Approach:	They propose a method that transfers reasoning knowledge in the gradient space while preserving multimodal alignment.
Outcome:	Experiments on multimodal reasoning benchmarks show that DRIFT outperforms naive merging and standard SFT.

Copied to clipboard

Zhenting Qi, Xiaoyu Tan, Chao Qu, Yinghui Xu, Yuan Qi

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning (2024.findings-acl)

Challenge:	Existing noise-handling methods could not improve performance of BERT on noisy datasets . existing methods could only improve performance on noisy data, authors say .
Approach:	They propose a fine-tuning framework for BERT-based text classifiers that combats label noises without access to clean data for training or validation.
Outcome:	The proposed framework achieves superior performance on multiple text classification benchmarks.

Copied to clipboard

Zhiyang Xu, Chao Feng, Rulin Shao, Trevor Ashby, Ying Shen, Di Jin, Yu Cheng, Qifan Wang, Lifu Huang

Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units (2025.emnlp-main)

Challenge:	Recent vision-language models (VLMs) have shown impressive capabilities as general visual assistants, but there are two challenges to their performance: (1) lacking task diversity in pretraining and visual instruction tuning; (2) annotation error and bias in GPT-4 synthesized instruction tuning data.
Approach:	They propose a two-stage instruction tuning framework that fine tunes VLMs firstly and further tuned on GPT-4 synthesized data.
Outcome:	The proposed framework outperforms the traditional single-stage visual instruction tuning framework and achieves state-of-the-art performance across a wide range of multi-modal evaluation benchmarks.

Copied to clipboard

Chao Hao, Zezheng Wang, Yanhua Huang, Ruiwen Xu, Wenzhe Niu, Xin Liu, Zitong Yu

FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Models (2024.findings-acl)

Challenge:	Existing methods to enhance reasoning capabilities of language models are expensive and often lack the ability to perform complex reasoning tasks.
Approach:	They propose a token-level multi-model collaboration strategy to enhance reasoning capabilities in language models by selecting the optimal tokens from the next token distributions.
Outcome:	The proposed method is superior to existing methods and will be released soon.

Copied to clipboard

Kaixin Lan, Tao Fang, Derek Wong, Yabo Xu, Lidia Chao, Cecilia Zhao

Improving BERT with Syntax-aware Local Attention (2021.findings-acl)

Challenge:	Existing methods to generate original text using pre-trained language models are problematic as they are trained on corpora constructed by human authors.
Approach:	They propose a unique “self-plagiarism” contrastive decoding strategy that modifies prompts in LLMs to develop an amateur model and a professional model.
Outcome:	The proposed method enables the development of an amateur model and a professional model while maintaining its standard language model status.

Copied to clipboard

Zhongli Li, Qingyu Zhou, Chao Li, Ke Xu, Yunbo Cao

LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating (2025.acl-long)

Challenge:	Recent studies show that attention-based models benefit from more focused attention over local regions.
Approach:	They propose a syntax-aware local attention which restrains attention over syntactically relevant words.
Outcome:	The proposed model performs better on all benchmark datasets, including sentence classification and sequence labeling tasks.

Copied to clipboard

Chao Deng, Jiale Yuan, Pi Bu, Peijie Wang, Zhong-Zhi Li, Jian Xu, Xiao-Hui Li, Yuan Gao, Jun Song, Bo Zheng, Cheng-Lin Liu

Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models (2025.findings-acl)

Challenge:	Existing document understanding benchmarks only handle a small number of pages . existing models are limited to handling only a limited number of documents .
Approach:	They propose a long document understanding benchmark that integrates three primary tasks and 20 sub-tasks based on different primary tasks.
Outcome:	The proposed model outperforms existing benchmarks on open-source and closed-source models . the model outpersforms other models on more than 33,000 pages of documents .

Copied to clipboard

You Li, Heyu Huang, Chi Chen, Kaiyu Huang, Chao Huang, Zonghao Guo, Zhiyuan Liu, Jinan Xu, Yuhua Li, Ruixuan Li, Maosong Sun

Frustratingly Easy Label Projection for Cross-lingual Transfer (2023.findings-acl)

Challenge:	Existing MLLMs still struggle to achieve precise grounding in multi-image scenarios.
Approach:	They propose a Chain-of-Thought framework that integrates single-image grounding with multi-image comprehension to address this challenge.
Outcome:	The proposed model outperforms existing models in multi-image grounding tasks by 24.94% and surpasses larger 70B models.

Copied to clipboard

Yang Chen, Chao Jiang, Alan Ritter, Wei Xu

Multilinguality

Challenge:	Existing approaches to improve cross-lingual transfer performance are based on word alignment, but no empirical studies have evaluated their effectiveness or limitations.
Approach:	They propose a mark-then-translate method that integrates translation and projection by inserting special markers around the labeled spans in the original sentence.
Outcome:	The proposed method outperforms word alignment-based methods in 57 languages and three tasks.

MoEC: A Memory-Routed Mixture-of-Experts Controller for Adaptive Minecraft Control (2026.acl-long)

Copied to clipboard

Hui Wu, Chao Xu, Jianghui Wang, Ziqiong Liu, Dong Li, Yiwei Dai, Emad Barsoum

LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)

Challenge:	Existing systems rely on a monolithic policy to execute subgoals across varying contexts, causing inconsistent outcomes and scaling only partially mitigates.
Approach:	They propose a memory-routed mixtureof-experts controller for Adaptive Minecraft Control that routes via a subgoal-indexed expert memory and regulates capacity through failure-triggered expert growth and redundancy-aware consolidation.
Outcome:	The proposed controller shows significant gains in adaptability, robustness, and execution consistency over strong baselines.

Copied to clipboard

Zihan Zhou, Chong Li, Xinyi Chen, Shuo Wang, Yu Chao, Zhili Li, Haoyu Wang, Qi Shi, Zhixing Tan, Xu Han, Xiaodong Shi, Zhiyuan Liu, Maosong Sun