Papers by Jiajun Wang

From Outcome to Process: Optimizing MoE Load Balancing with MCTS (2026.findings-acl)

Challenge:	Current multimodal large language models (MLLMs) show limited understanding of dental images.
Approach:	They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning.
Outcome:	The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks.

Copied to clipboard

Wenjun Ke, Hengyuan Xu, Ziyu Shang, Yao He, Jiahao Wang, Zijie Xu, Peng Wang, Yuhang Lou, Jiajun Liu

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Existing balancing strategies focus on constraining the final distribution of expert usage, but overlook the routing decisions made at each layer.
Approach:	They propose a three-stage framework that leverages process-level rewards to guide balanced expert routing.
Outcome:	Extensive experiments show that LayerMoE improves the performance of state-of-the-art LoRA-MoA baselines, yielding an average accuracy gain of 1.39%.

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults (2026.acl-long)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Zhenhao Zhou, Zhuochen Huang, Yike He, Chong Wang, Jiajun Wang, Yijian Wu, Xin Peng, Yiling Lou

Challenge:	Existing LLM agents struggle with identifying bugs in the Linux kernel . bugs can affect billions of users, affecting the Linux Foundation's research on the topic .
Approach:	They propose a LinuxFLBench benchmark to measure the accuracy of LLM agents on the Linux kernel.
Outcome:	The proposed framework improves FL accuracy with minimal costs.

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

Copied to clipboard

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

On the Consistency of Commonsense in Large Language Models (2025.findings-acl)

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

Copied to clipboard

Guozheng Li, Peng Wang, Wenjun Ke, Zijie Xu, Jiajun Liu, Ziyu Shang

Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning (2025.acl-long)

Challenge:	Existing evaluations of commonsense for large language models focus on downstream knowledge tasks, failing to probe whether LLMs truly understand and utilize knowledge or merely memorize it.
Approach:	They propose to automatically construct a large benchmark named CoCo which measures LLMs’ knowledge memorization, comprehension, and application and examines the consistency between these tasks.
Outcome:	The proposed benchmark systematically assesses LLMs’ knowledge memorization, comprehension, and application and examines the consistency between these tasks.

Copied to clipboard

Shaobo Wang, Xiangqi Jin, Ziming Wang, Jize Wang, Jiajun Zhang, Kaixin Li, Zichen Wen, Zhong Li, Conghui He, Xuming Hu, Linfeng Zhang

Acquisition and Application of Novel Knowledge in Large Language Models (2025.acl-long)

Challenge:	Using fine-tuning on task-specific data is essential for large language models to be effective in specialized tasks.
Approach:	They propose a method that leverages few-shot in-context learning with the model to be fine-tuned.
Outcome:	The proposed method outperforms existing methods with a 3.1-point improvement and a 7.4 speedup on the Llama-3-8B-Instruct model using just 10% of the dataset.

Copied to clipboard

Ziyu Shang, Jianghan Liu, Zhizhao Luo, Peng Wang, Wenjun Ke, Jiajun Liu, Zijie Xu, Guozheng Li

X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions (2024.findings-acl)

Challenge:	Existing methods for constructing new datasets rely on timestamps or simple templates that do not accurately reflect the real world.
Approach:	They propose a knowledge dataset construction approach that simulates biological evolution using knowledge graphs to generate synthetic entities with diverse attributes.
Outcome:	The proposed framework outperforms knowledge augmentation methods by 3.3%-38%.

Copied to clipboard

Chong Li, Wen Yang, Jiajun Zhang, Jinliang Lu, Shaonan Wang, Chengqing Zong

Addressing Asymmetry in Multilingual Neural Machine Translation with Fuzzy Task Clustering (2022.coling-1)

Challenge:	Large language models respond well in high-resource languages but struggle in low-resourced languages.
Approach:	They propose a method to construct cross-lingual instruction following samples with instruction in English and response in low-resource languages.
Outcome:	The proposed method builds a large-scale cross-lingual instruction tuning dataset on 10 languages.

Copied to clipboard

Qian Wang, Jiajun Zhang

Cross-Modal Cloze Task: A New Task to Brain-to-Word Decoding (2022.findings-acl)

Challenge:	Existing clustering methods cannot handle asymmetric problem in multilingual NMT . existing models cannot handle the asymmetry problem since there are thousands of languages involved .
Approach:	They propose a fuzzy task clustering method to address the asymmetric problem in multilingual NMT by using task affinity as the clustering criterion.
Outcome:	The proposed method outperforms baselines for a multilingual model and the existing models.

Copied to clipboard

Shuxian Zou, Shaonan Wang, Jiajun Zhang, Chengqing Zong

Text Classification

Challenge:	Existing work on decoding language from non-invasive brain activity is limited due to noisy nature of brain recordings.
Approach:	They propose a cross-modal cloze task to predict a word from a neural image . they use a pre-trained language model to leverage the pre-training language model .
Outcome:	The proposed method outperforms baselines on 20 participants from two brain imaging datasets.

A Compact and Language-Sensitive Multilingual Translation Method (P19-1)

Copied to clipboard

Yining Wang, Long Zhou, Jiajun Zhang, Feifei Zhai, Jingfang Xu, Chengqing Zong

RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)

Challenge:	Existing paradigms for multilingual neural machine translation do not make full use of language commonality and parameter sharing.
Approach:	They propose a multilingual neural machine translation paradigm with one encoder-decoder model that makes full use of language commonality and parameter sharing.
Outcome:	The proposed method outperforms strong standard multilingual translation systems on WMT and IWSLT datasets.

Copied to clipboard

Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)

Challenge:	Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains, but their ability to replicate complex, multi-panel visualizations remains largely unassessed.
Approach:	They propose a large-scale benchmark to evaluate chart generation from large- scale raw data and assess iterative code refinement in a multi-turn conversational setting.
Outcome:	The new benchmark evaluates 14 leading VLMs on real-world data and shows they struggle with complex plot structures and authentic data.

Copied to clipboard

Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang

EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary (2025.acl-industry)

Challenge:	Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand.
Approach:	They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages.
Outcome:	Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages.

Copied to clipboard

Yaozhen Liang, Xiao Liu, Jiajun Yu, Zhouhua Fang, Qunsheng Zou, Linghan Zheng, Yong Li, Zhiwei Liu, Haishuai Wang

Explainability & Interpretability in NLP

Challenge:	Existing document question answering methods reduce inference costs and input tokens.
Approach:	They propose a retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents.
Outcome:	The proposed method surpasses baseline retrieval-augmented generation (RAG) and long-context question answering (LC) methods achieve higher accuracy by processing entire documents, but at the cost of increased computational Corresponding authors.

Towards Database-Free Text-to-SQL Evaluation: A Graph-Based Metric for Functional Correctness (2025.coling-main)

Copied to clipboard

Yi Zhan, Longjie Cui, Han Weng, Guifeng Wang, Yu Tian, Boyi Liu, Yingxiang Yang, Xiaoming Yin, Jiajun Xie, Yang Sun

Are You for Real? Detecting Identity Fraud via Dialogue Interactions (D19-1)

Challenge:	Existing metrics for evaluating functional correctness of SQL queries are prone to false positives due to inadequately prepared test databases.
Approach:	They propose a graph-based metric that uses a relational operator tree to extract rich semantic information from the logical execution plan of SQL queries and embed it into a diagram.
Outcome:	The proposed method eliminates the need for extensive test database preparation and performs graph matching on unseen SQL queries.

Copied to clipboard

Weikang Wang, Jiajun Zhang, Qian Li, Chengqing Zong, Zhifei Li

Incremental Learning from Scratch for Task-Oriented Dialogue Systems (P19-1)

Challenge:	Existing methods to detect identity fraud are prone to errors and are not based on real data.
Approach:	They propose to use a KG constructor and structured dialogue management to detect identity fraud in loan applications to generate questions based on personal information.
Outcome:	The proposed system can detect fraudsters and achieve higher recognition accuracy compared with rule-based systems.

Copied to clipboard

Weikang Wang, Jiajun Zhang, Qian Li, Mei-Yuh Hwang, Chengqing Zong, Zhifei Li

Structure-Unified M-Tree Coding Solver for Math Word Problem (2022.emnlp-main)

Challenge:	Existing task-oriented dialogue systems cannot guarantee that all user needs are taken into account in the design phase.
Approach:	They propose a new incremental learning framework to design task-oriented dialogue systems without pre-defining user needs.
Outcome:	The proposed framework is robust to unconsidered user actions and can update itself online with less annotation cost.

Copied to clipboard

Bin Wang, Jiangzhou Ju, Yang Fan, Xinyu Dai, Shujian Huang, Jiajun Chen

Numerical Reasoning

Challenge:	Existing models that take into account the binary tree structure of mathematical expressions have achieved better performance, but the output space is non-deterministic.
Approach:	They propose a Structure-Unified M-Tree Coding Solver which applies a tree with any M branches to unify the output structures.
Outcome:	The proposed model outperforms several state-of-the-art models under similar experimental conditions and performs much better under low-resource conditions.

DeepWell-Adol: A Scalable Expert-Based Dialogue Corpus for Adolescent Positive Mental Health and Wellbeing Promotion (2025.emnlp-main)

Copied to clipboard

Wenyu Qiu, Yuxiong Wang, Jiajun Tan, Hanchao Hou, Qinda Liu, Wei Yao, Shiguang Ni

Dialogue Systems & Conversational Agents

Challenge:	Promoting positive mental health and well-being is a critical yet underexplored area in natural language processing.
Approach:	They propose a Chinese dialogue corpus grounded in positive psychology and coaching that integrates human expert-written seed data with automated data augmentation to ensure high quality and scalability.
Outcome:	The proposed corpus meets general standards for psychological dialogue and emotional support while also showing superior performance across multiple models in promoting positive psychological processes, character strengths, interpersonal relationships, and healthy behaviors.

Touch Editing: A Flexible One-Time Interaction Approach for Translation (2020.aacl-main)

Copied to clipboard

Qian Wang, Jiajun Zhang, Lemao Liu, Guoping Huang, Chengqing Zong

Machine Translation

Challenge:	Existing methods for machine translation require intensive keyboard interaction, which is inconvenient on mobile devices.
Approach:	They propose a touch-based editing method that is more flexible than keyboard-mouse-based translation postediting.
Outcome:	The proposed method significantly outperforms existing interactive translation methods on translation datasets and on post-editing datasets.

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

Copied to clipboard

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

Rethinking Document-level Neural Machine Translation (2022.findings-acl)

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

Copied to clipboard

Zewei Sun, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Shujian Huang, Jiajun Chen, Lei Li

FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation (2022.lrec-1)

Challenge:	Neural machine translation models are weak enough for document-level translation . current models only translate sentences individually, resulting in poor document coherence .
Approach:	They propose to use the original Transformer model to test document-level neural machine translation . they find that the original transformer models can achieve strong results for document translation if trained properly .
Outcome:	The proposed model outperforms sentence-level models on nine datasets and two sentence- level datasets across six languages.

Copied to clipboard

Wenhao Zhu, Shujian Huang, Tong Pu, Pingxuan Huang, Xu Zhang, Jian Yu, Wei Chen, Yanfeng Wang, Jiajun Chen

OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model (2025.emnlp-demos)

Challenge:	Recent research on domain adaptation neglects diversity in translation within a domain . current research on NMT models considers very broad target domains .
Approach:	They propose a fine-grained domain adaptation task for autonomous vehicles, AI education, real-time networks, and smart phone.
Outcome:	The proposed task is compared with a dataset of Chinese-English translation tasks for four sub-domains of information technology: autonomous vehicles, AI education, real-time networks, and smart phone.

Copied to clipboard

Chen Wang, Tianyu Peng, Wen Yang, YiNan Bai, Guangfu Wang, Jun Lin, Lanpeng Jia, Lingxiang Wu, Jinqiao Wang, Chengqing Zong, Jiajun Zhang

Distill and Replay for Continual Language Learning (2020.coling-main)

Challenge:	Empathetic speech models are increasingly closed off, leaving details about the architecture, data and development opaque to researchers.
Approach:	They propose an open-source empathetic speech-to-text model with a streaming interleaved decoding architecture and a data pipeline to enable end-to end training.
Outcome:	The proposed model is open-source and transparent, with no data or data required to build it.

Copied to clipboard

Jingyuan Sun, Shaonan Wang, Jiajun Zhang, Chengqing Zong

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Existing models fail to isolate acquired knowledge and forget previously learned tasks when learning in a stream where data distribution may shift.
Approach:	They propose a framework that distills knowledge and replays experience from previous tasks when fitting on a new task.
Outcome:	The proposed framework outperforms state-of-the-art models in continuously learning tasks of the same type but from different domains, as well as tasks of different types.

Copied to clipboard

Peiru Yang, Haoran Zheng, Tong Ju, Shiting Wang, Wanchun Ni, Jiajun Liu, Shangguang Wang, Yongfeng Huang, Tao Qi

MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Challenge:	Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability .
Approach:	They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval .
Outcome:	The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets.

Copied to clipboard

Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement (2025.findings-acl)

Challenge:	Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach:	They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome:	The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.

Copied to clipboard

Peng Ding, Jun Kuang, ZongYu Wang, Xuezhi Cao, Xunliang Cai, Jiajun Chen, Shujian Huang

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across various tasks but are vulnerable to meticulously crafted jailbreak attacks.
Approach:	They propose a training-free defense strategy to align LLMs’ strong safety discrimination performance with their relatively weaker safety generation ability.
Outcome:	The proposed strategy achieves an average 99% success rate against numerous complex and covert jailbreak methods while maintaining helpfulness on general benchmarks.

UIOrchestra: Generating High-Fidelity Code from UI Designs with a Multi-agent System (2025.findings-emnlp)

Copied to clipboard

Chuhuai Yue, Jiajun Chai, Yufei Zhang, Zixiang Ding, Xihao Liang, Peixin Wang, Shihai Chen, Wang Yixuan, null Wangyanping, Guojun Yin, Wei Lin

Matching Varying-Length Texts via Topic-Informed and Decoupled Sentence Embeddings (2024.findings-naacl)

Challenge:	Recent advances in large language models have significantly improved automated code generation . however, the translation of complex mobile UI designs into high-fidelity front-end code remains a challenge .
Approach:	They propose a collaborative multi-agent system to reconstruct static single-page apps from mockups.
Outcome:	The proposed system outperforms existing methods in reconstructing complex app pages . the code and data will be released upon paper acceptance .

Copied to clipboard

Xixi Zhou, Chunbin Gu, Xin Jie, Jiajun Bu, Haishuai Wang

Representation Learning

Challenge:	Existing approaches to matching text with non-comparable lengths are limited due to truncation issues.
Approach:	They propose a model that decouples sentences and embeds them into natural sentences for matching texts of significantly different lengths.
Outcome:	The proposed model matches texts of significantly different lengths across three well-studied datasets.

Capability Decomposition for Unified Information Extraction via Hierarchical Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Jing Zhou, Peng Wang, Wenjun Ke, Jiajun Liu, Yao He

A Teacher-Student Framework for Maintainable Dialog Manager (D18-1)

Challenge:	Existing methods for IE tasks suffer from inconsistent schema representation and implicitly intermediate reasoning . UC-UIE adopts a low-rank adapted hierarchical Mixture-of-Experts adapter for UIE tasks .
Approach:	They propose a framework that decomposes IE reasoning into three universal capabilities . UC-UIE adopts a low-rank Adaptation adapter to fine-tune LLMs for IE tasks .
Outcome:	The proposed framework outperforms full-parameter tuning methods with 1.24% trainable parameters and outperformed existing methods in generalization and interpretability.

Copied to clipboard

Weikang Wang, Jiajun Zhang, Han Zhang, Mei-Yuh Hwang, Chengqing Zong, Zhifei Li

AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning (2026.findings-acl)

Challenge:	Reinforcement learning (RL) is an attractive solution for task-oriented dialog systems . but extending RL-based systems to handle new intents and slots requires a system redesign .
Approach:	They propose a teacher-student framework to extend RL-based dialog systems . they propose to specify constraints held in the new dialog manager .
Outcome:	The proposed framework makes no assumption about unsupported intents and slots, making it possible to improve RL-based systems incrementally.

Copied to clipboard

Jingbo Sun, Wenyue Chong, Songjun Tu, Qichao Zhang, Yaocheng Zhang, Jiajun Chai, Xiaohan Wang, Wei Lin, Guojun Yin, Dongbin Zhao

Language-Mediated, Object-Centric Representation Learning (2021.findings-acl)

Challenge:	Prior work limits search depth to reduce cost, but this often leads to underexploration of complex questions.
Approach:	They propose a reinforcement learning framework that evaluates each search step via self-generated intermediate answers.
Outcome:	Extensive experiments on multiple benchmarks show that AutoSearch achieves a superior accuracy-efficiency trade-off, alleviating over-searching while preserving search quality.

Copied to clipboard

Ruocheng Wang, Jiayuan Mao, Samuel Gershman, Jiajun Wu

Representation Learning

Challenge:	Recent work has studied the problem of unsupervised object representation learning, though without language.
Approach:	They propose language-mediated, Objectcentric Representation Learning (LORL) a paradigm for learning disentangled, objectcentric scene representations from vision and language.
Outcome:	The proposed paradigm improves performance of unsupervised object discovery algorithms on two datasets using language.

Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation (2022.emnlp-main)

Copied to clipboard

Chen Wang, Yuchen Liu, Boxing Chen, Jiajun Zhang, Wei Luo, Zhongqiang Huang, Chengqing Zong

VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction (2025.findings-emnlp)

Challenge:	Existing zero-shot methods fail to align speech and text into a shared semantic space . Existing methods require expensive and expensive parallel ST data .
Approach:	They propose a method that uses a shared discrete vocabulary space to align speech and text into a common space.
Outcome:	The proposed method significantly improves the SOTA and even performs on par with the strong supervised ST baselines.

Copied to clipboard

Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, Xipeng Qiu

Challenge:	Traditional Function Calling (FC) approaches operate statelessly, requiring multiple exploratory calls to build environmental awareness before execution, leading to inefficiency and limited error recovery.
Approach:	They propose a state-based function call approach that maintains explicit system state awareness and implements direct state transitions to achieve target conditions.
Outcome:	The proposed approach outperforms traditional function calling approaches, achieving superior execution accuracy and reduced latency.

BLSP-Emo: Towards Empathetic Large Speech-Language Models (2024.emnlp-main)

Copied to clipboard

Chen Wang, Minpeng Liao, Zhongqiang Huang, Junhong Wu, Chengqing Zong, Jiajun Zhang

Long-form Hallucination Detection with Self-elicitation (2025.findings-acl)

Challenge:	BLSP-Emo model understands both semantics and emotions in speech and generates empathetic responses.
Approach:	They propose a language-speech pretraining with emotion support that utilizes existing speech and emotion recognition datasets to create an end-to-end speech-language model.
Outcome:	The proposed model can understand both semantics and emotions in speech and generate empathetic responses.

Copied to clipboard

Zihang Liu, Jiawei Guo, Hao Zhang, Hongyang Chen, Jiajun Bu, Haishuai Wang

Reasoning

Challenge:	Existing methods for hallucination detection tend to decompose text into isolated statements, unable to understand contextual semantics.
Approach:	They propose a framework to leverage self-generated thoughts derived from prior statements as catalysts to elicit the expression of intrinsic knowledge and understand contextual semantics.
Outcome:	The proposed framework enables self-elicitation to elicit expressions of knowledge and understand semantics.

Non-Autoregressive Translation by Learning Target Categorical Codes (2021.naacl-main)

Copied to clipboard

Yu Bao, Shujian Huang, Tong Xiao, Dongqi Wang, Xinyu Dai, Jiajun Chen

Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning (2023.emnlp-main)

Challenge:	Existing non-autoregressive text generation models still fall behind in translation quality . authors propose a model that learns implicitly categorical codes as latent variables .
Approach:	They propose a non-autoregressive Transformer model that implicitly categorizes latent variables into decoding . they find it improves translation quality by introducing more informative decoder inputs .
Outcome:	The proposed model achieves comparable or better performance in machine translation tasks than strong baselines.

Copied to clipboard

Chong Li, Shaonan Wang, Yunhao Zhang, Jiajun Zhang, Chengqing Zong

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models (2025.emnlp-main)

Challenge:	Experimental results show that multi-head attention module evolves functional specialization after multi-task training.
Approach:	They propose a method to quantify the degree of functional specialization in multi-head attention . they propose 'multi-task training' method to increase functional specialisation and mitigate negative information transfer .
Outcome:	The proposed method increases functional specialization and mitigates negative information transfer in multi-task learning without adding any parameters.

Copied to clipboard

Peng Ding, Wen Sun, Dailin Li, Wei Zou, Jiaming Wang, Jiajun Chen, Shujian Huang

Online Distilling from Checkpoints for Neural Machine Translation (N19-1)

Challenge:	Large Language Models (LLMs) excel at various tasks but are vulnerable to jailbreak attacks that induce harmful content generation.
Approach:	They propose a reinforcement learning framework that leverages the model’s own discrimination capabilities as a reward signal to enhance generation safety through iterative self-improvement.
Outcome:	The proposed framework improves model safety by iterative self-improvement without additional annotated data or external models during training phase.

Copied to clipboard

Hao-Ran Wei, Shujian Huang, Ran Wang, Xin-yu Dai, Jiajun Chen

LLM-Guided Semantic-Aware Clustering for Topic Modeling (2025.acl-long)

Challenge:	Existing neural machine translation models have a deep structure with large amounts of parameters, making them hard to train.
Approach:	They propose an online method to generate a teacher model from checkpoints . they show steady improvement over a strong self-attention-based baseline system .
Outcome:	The proposed method improves on-the-fly on several datasets and language pairs.

Copied to clipboard

Jianghan Liu, Ziyu Shang, Wenjun Ke, Peng Wang, Zhizhao Luo, Jiajun Liu, Guozheng Li, Yining Li

Information Extraction & Text Mining

Challenge:	Experimental results show that topic modeling is competitive compared to closed-source methods.
Approach:	They propose a semi-supervised topic modeling method that combines LLMs with clustering to improve topic generation and distribution.
Outcome:	The proposed method outperforms state-of-the-art methods that utilize GPT-4 on topic alignment and exhibits competitive performance compared to Neural Topic Models on topic quality.

Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment (2024.naacl-long)

Copied to clipboard

Chong Li, Shaonan Wang, Jiajun Zhang, Chengqing Zong

Synchronously Generating Two Languages with Interactive Decoding (D19-1)

Challenge:	Existing studies show that multilingual generative models exhibit a strong language bias toward high-resource languages.
Approach:	They propose a cross-lingual alignment framework exploiting pairs of translation sentences to improve cross-linguistic abilities.
Outcome:	The proposed framework improves cross-lingual abilities and mitigates performance gap.

Copied to clipboard

Yining Wang, Jiajun Zhang, Long Zhou, Yuchen Liu, Chengqing Zong

Boosting Textural NER with Synthetic Image and Instructive Alignment (2024.findings-acl)

Challenge:	Experimental results show that multilingual NMT models handle multiple language pairs in one model.
Approach:	They propose an interactive approach to translate a source language into two different languages simultaneously and interactively.
Outcome:	The proposed approach improves on IWSLT and WMT datasets.

Copied to clipboard

Jiahao Wang, Wenjun Ke, Peng Wang, Hang Zhang, Dong Nie, Jiajun Liu, Guozheng Li, Ziyu Shang

AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment (2026.acl-long)

Challenge:	Named entity recognition (NER) is a key task reliant on textual data.
Approach:	They propose a method to transform NER into a multimodal task by using images from the internet as auxiliaries.
Outcome:	The proposed method surpasses all text-only baselines and improves F1 score by 1.4% to 2.3% on prominent MNER datasets.

Copied to clipboard

Yixuan Wang, Yue Huang, Hong Qian, Yunzhao Wei, Yifei Ding, Wenkai Wang, Zhi Liu, Zhongjing Huang, Aimin Zhou, Jiajun Guo

Challenge:	Existing LLM-based tools struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking.
Approach:	They propose an evolutionary tree-based psychometric context generator that integrates rule-guided outline planning, sentence-level MCTS generation, MAP-Elites quality-diversity optimization and assessment-guide refiner simulation.
Outcome:	The proposed tool outperforms strong LLMs and structured frameworks on 7 evaluation dimensions and shows higher alignment with expert-designed contexts.

Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification (2021.emnlp-main)

Copied to clipboard

Ran Wang, Xi’ao Su, Siyu Long, Xinyu Dai, Shujian Huang, Jiajun Chen

NCLS: Neural Cross-Lingual Summarization (D19-1)

Challenge:	Large-scale multi-label text classification tasks often face long-tailed label distributions, where many labels have few or even no training instances.
Approach:	They propose a meta-learning approach that incorporates the objective of adapting to new low-resource tasks into the meta-Learning phase.
Outcome:	The proposed approach achieves state-of-the-art against strong baselines and can still enhance powerful BERTlike models.

Copied to clipboard

Junnan Zhu, Qian Wang, Yining Wang, Yu Zhou, Jiajun Zhang, Shaonan Wang, Chengqing Zong

Robust Membership Inference for Large Language Models under Adversarial Generative Corruption (2026.acl-long)

Challenge:	Existing approaches to cross-lingual summarization divide the task into two steps: summarizing and translation.
Approach:	They propose to integrate two related tasks into the training process of CLS under multi-task learning to improve cross-lingual summarization.
Outcome:	The proposed framework improves on English-to-Chinese and Chinese-to English CLS human-corrected test sets.

Copied to clipboard

Yuanhong Huang, Huili Wang, Xueying Bai, Jinrui Wang, Jiajun Liu, Ziqin Wang, Wanchun Ni, Shangguang Wang, Tao Qi

On the Role of Discriminative Models in Generative Relation Extraction (2026.acl-long)

Challenge:	Membership inference attacks are a promising tool for auditing training data of LLMs . existing methods rely on the assumption that LLM's assign higher confidence scores to training samples than to non-training ones.
Approach:	They propose a membership inference framework that can be robust against adversarial MIAs.
Outcome:	The proposed framework can be robust against adversarial MIA methods and AIGT detectors while maintaining the performance of baselines.

Copied to clipboard

Guozheng Li, Peng Wang, Zijie Xu, Jing Zhou, Jiajun Liu, Ziyu Shang

Information Extraction & Text Mining

Challenge:	Existing methods for relation extraction (RE) are discriminative and generative . previous studies show that discriminative models can support generative RE .
Approach:	They propose a framework that leverages discriminative models to produce a top-k set of candidate relations and integrates this knowledge into generative models via in-context or prompt learning.
Outcome:	The proposed framework achieves state-of-the-art on five widely used RE benchmarks.

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training (2025.emnlp-main)

Copied to clipboard

Haotian Dong, Jingyan Jiang, Rongwei Lu, Jiajun Luo, Jiajun Song, Bowen Li, Ying Shen, Zhi Wang

Text Clustering

Challenge:	Decentralized LLM training leverages dispersed resources at varying scales.
Approach:	They propose a resource-driven paradigm that leverages dispersed resources across clusters, datacenters and even regions.
Outcome:	The proposed model scales are 175 billion to 660 billion parameters, and the exponential growth in computational requirements poses significant challenges.

Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment (2025.findings-acl)

Copied to clipboard

Wen Yang, Junhong Wu, Chen Wang, Chengqing Zong, Jiajun Zhang

latent-GLAT: Glancing at Latent Variables for Parallel Text Generation (2022.acl-long)

Challenge:	Existing approaches to align English LLMs with human preferences rely on expensive human annotations or advanced multilingual preference alignment models.
Approach:	They propose a method that captures learned preferences from English models by implicit rewards . they annotate preference relations in cross-lingual instruction-following pairs using English .
Outcome:	The proposed approach captures learned preferences from well-aligned English models by implicit rewards and transfers them to other languages through iterative training.

Copied to clipboard

Yu Bao, Hao Zhou, Shujian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei Li

Beyond the Individual: Virtualizing Multi-Disciplinary Reasoning for Clinical Intake via Collaborative Agents (2026.findings-acl)

Challenge:	Recent advances in text generation have limited applications due to multimodality problem.
Approach:	They propose a method which uses latent variables to capture word categorical information and invoke an advanced curriculum learning technique to overcome multi-modality problem.
Outcome:	The proposed method outperforms strong baselines without an autoregressive model, which further broadens the application scenarios of the parallel decoding paradigm.

Copied to clipboard

Huangwei Chen, Wu Li, Junhao Jia, Yining Chen, Xiaotao Pang, Ya-Long Chen, Li Gonghui, Haishuai Wang, Jiajun Bu, Lei Wu

Reasoning

Challenge:	Initial outpatient consultations are costly and difficult to scale to real-time intake.
Approach:	They propose a synchronous virtual MDT framework that formalizes the consultation state using a structured SOAP representation, separating evidence collection from diagnostic reasoning to improve traceability and bias control.
Outcome:	The proposed framework outperforms state-of-the-art models on ClinicalBench and a real-world RAPID-IPN dataset in documentation quality and consultation capability.

Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction (2024.lrec-main)

Copied to clipboard

Guozheng Li, Wenjun Ke, Peng Wang, Zijie Xu, Ke Ji, Jiajun Liu, Ziyu Shang, Qiqing Luo

Low-Resource NLP

Challenge:	Existing methods for relational triple extraction (RTE) are unnatural and recast RTE tasks to text-to-text prompting formats.
Approach:	They propose a tabular prompting for RTE which frames RTE task into a table generation task and propose an instructive in-context learning which only selects and annotates samples considering triple semantics in massive unlabeled samples.
Outcome:	The proposed prompting for RTE with TableIE achieves state-of-the-art performance compared to other methods . the proposed prompts are based on off-the shelf LLMs and are scalable to multiple scenarios .

Exploring Layer Activation Dynamic of CoT via Knowledge Probe (2026.acl-long)

Copied to clipboard

Chuanxin Zhang, Jiajun Liu, Yao He, Wenjun Ke, Peng Wang, Yankun Le, Sirui Liu, Zhaoyu Yang

Information Extraction & Text Mining

Challenge:	Chain-of-thought reasoning has emerged as a crucial paradigm for multi-step reasoning tasks.
Approach:	They propose a multi-stage probing framework that enforces structured reasoning with three explicit stages: keyword extraction, theorem generation, and computation execution.
Outcome:	The proposed framework enforces structured reasoning with three explicit stages: keyword extraction, theorem generation, and computation execution.

Towards Scalable Lightweight GUI Agents via Multi-role Orchestration (2026.findings-acl)

Copied to clipboard

Ziwei Wang, Junjie Zheng, Leyang Yang, Sheng Zhou, Xiaoxuan Tang, Fang Zhouhua, Zhiwei Liu, Dajun Chen, Yong Li, Jiajun Bu

Challenge:	Advanced GUI agents suffer from prohibitive deployment costs on resource-constrained devices.
Approach:	They propose a lightweight GUI agent with GUI-specific knowledge and task scalability . LAMO-3B supports monolithic execution and MAS-style orchestration .
Outcome:	The proposed GUI agent LAMO-3B supports monolithic execution and MAS-style orchestration.

Exploring the Factual Consistency in Dialogue Comprehension of Large Language Models (2024.naacl-long)

Copied to clipboard

Shuaijie She, Shujian Huang, Xingyun Wang, Yanke Zhou, Jiajun Chen

Three Strategies to Improve One-to-Many Multilingual Translation (D18-1)

Challenge:	LLMs generate responses following user's instructions, which requires high dialogue comprehension ability.
Approach:	They propose to evaluate LLMs' dialogue comprehension ability using a dialogue summarization task to derive factual questions from the generated summaries and use them as a more flexible measurement of dialogue comprehension.
Outcome:	The proposed model reduces the error rate by 11% on the dialogue summarization task.

Copied to clipboard

Yining Wang, Jiajun Zhang, Feifei Zhai, Jingfang Xu, Chengqing Zong

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning (2026.acl-long)

Challenge:	Existing studies show that one-to-many multilingual translation cannot perform on par with the individually trained models.
Approach:	They propose to exploit unique initial states for target languages and language-dependent positional embeddings to create hidden cells of the encoder to achieve comparable or even better performance than individually trained models.
Outcome:	The proposed methods achieve comparable or even better performance than the individually trained models.

Copied to clipboard

Jiajun Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang, Yuheng Jing, Zeyao Ma, Tianyi Bai, Zilei Wang, Qiang Liu, Liang Wang, Binyuan Hui, Junyang Lin

Programming Languages in NLP

Challenge:	Fill-in-the-Middle (FIM) models suffer from performance degradation and prohibitive latency.
Approach:	They propose a search-and-replace infilling framework that integrates agentic verification and editing into a single-pass inference process.
Outcome:	The proposed framework harmonizes completion tasks with the instruction-following priors of Chat LLMs, extending the paradigm from static infilling to dynamic context-aware editing.

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

Copied to clipboard

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

From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling (2026.findings-acl)

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

Copied to clipboard

Yifei Cao, Changhao Jiang, Jiabao Zhuang, Jiajun Sun, Ming Zhang, Zhiheng Xi, Hui Li, Shihan Dou, Yuran Wang, Yunke Zhang, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)

Challenge:	Experimental results show that the MOS-aware GRM significantly improves fine-grained speech quality discrimination.
Approach:	They propose a MOS-aware reward model that incorporates MOS gap into reward function during reinforcement learning.
Outcome:	The proposed model significantly improves fine-grained speech quality discrimination.

Copied to clipboard

Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li

BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training (2023.acl-long)

Challenge:	Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training.
Approach:	They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks.

Copied to clipboard

Yiming Yan, Tao Wang, Chengqi Zhao, Shujian Huang, Jiajun Chen, Mingxuan Wang

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)

Challenge:	Automated metrics are used for machine translation, but they are often considered to be black boxes with potential biases that are difficult to detect.
Approach:	They analyze automatic metrics from the perspective of their guidance for machine translation training.
Outcome:	The proposed measures improve the performance of machine translation models.

Copied to clipboard

Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li, Yueting Zhuang

Reasoning

Challenge:	Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored.
Approach:	They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes.
Outcome:	The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks.

CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs (2026.findings-acl)

Copied to clipboard

Siyi Li, Jiajun Shi, Shiwen Ni, Ge Zhang, Shuaimin Li, Shijian Wang, Zhoufutu Wen, Yizhi LI, Hamid Alinejad-Rokny, Jiaheng Liu, Min Yang, Wenhao Huang

Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models (2025.findings-emnlp)

Challenge:	Existing evaluations emphasize final accuracy or coarse token counts, and lack automated tools to separate essential logic from structural redundancy.
Approach:	They propose a graph-driven framework that quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path needed to reach a correct solution.
Outcome:	Evaluating 21 LRMs, the proposed framework quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path (SEP) needed to reach a correct solution.

Copied to clipboard

Xiaojun Wu, Junxi Liu, Huan-Yi Su, Zhouchi Lin, Yiyan Qi, Chengjin Xu, Jiajun Su, Jiajie Zhong, Fuwei Wang, Saizhuo Wang, Fengrui Hua, Jia Li, Jian Guo

SCOUT: Selective Coupling via Optimal Unbalanced Transport for Interpretable Text Classification (2026.acl-long)

Challenge:	Existing financial benchmarks suffer from limited language and task coverage, low-quality datasets, and inadequate adaptability for LLM evaluation.
Approach:	They propose a bilingual benchmark for financial LLMs that assesses models’ language understanding and generation capabilities.
Outcome:	The proposed bilingual benchmark assesses models’ language understanding and generation capabilities.

Copied to clipboard

Junhao Jia, Hanwen Zheng, Yueyi Wu, Huangwei Chen, Haishuai Wang, Jiajun Bu, Lei Wu

Explainability & Interpretability in NLP

Challenge:	Standard interpretable models often rely on scalar similarities that obscure the true evidentiary basis of a prediction.
Approach:	They propose a new paradigm that grounds prototype reasoning in the selective correspondence of discriminative fragments.
Outcome:	The proposed model outperforms rationale extraction and post-hoc attribution methods on seven benchmarks.

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models (2025.emnlp-main)

Copied to clipboard

Pu Jian, Junhong Wu, Wei Sun, Chen Wang, Shuo Ren, Jiajun Zhang