Papers by Yan Xiao

Transductive Learning for Unsupervised Text Style Transfer (2021.emnlp-main)

Challenge:	Temporal knowledge graphs (TKGs) require predicting future facts by modeling structural dependencies within each snapshot and temporal evolution across snapshots.
Approach:	They propose an encoder-agnostic framework that provides persistent entity states . EST maintains a global state buffer and aligns structural evidence with sequential signals .
Outcome:	Experiments show that EST improves diverse backbones and achieves state-of-the-art performance.

Copied to clipboard

Fei Xiao, Liang Pang, Yanyan Lan, Yan Wang, Huawei Shen, Xueqi Cheng

Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations (2025.findings-naacl)

Challenge:	Existing methods for style transfer are based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases.
Approach:	They propose a retrieval-based context-aware style representation that involves top-K relevant sentences in the target style in the transfer process.
Outcome:	The proposed method outperforms several strong baselines and is general and effective to the task of unsupervised style transfer.

Copied to clipboard

Wenjie Jacky Mo, Jiashu Xu, Qin Liu, Jiongxiao Wang, Jun Yan, Hadi Askari, Chaowei Xiao, Muhao Chen

Federated Document-Level Biomedical Relation Extraction with Localized Context Contrast (2024.lrec-main)

Challenge:	Existing studies on backdoor defense have focused on training phase, overlooking critical aspect of testing time defense.
Approach:	They propose to use demonstrations as a defense mechanism against backdoor attacks in black-box LLMs.
Outcome:	The proposed method outperforms existing defense baselines across most evaluation scenarios.

Copied to clipboard

Yan Xiao, Yaochu Jin, Kuangrong Hao

Information Extraction & Text Mining

Challenge:	Existing studies on relation extraction focus on document-level training without sharing raw medical texts.
Approach:	They propose a federated framework for relation extraction that enables collaborative training without sharing raw medical texts.
Outcome:	The proposed framework extends document-level relation extraction to a federated environment.

WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types (2022.acl-long)

Copied to clipboard

Xuwu Wang, Junfeng Tian, Min Gui, Zhixu Li, Rui Wang, Ming Yan, Lihan Chen, Yanghua Xiao

Knowledge Representation

Challenge:	Multimodal Entity Linking (MEL) is an essential task for many multimodal applications.
Approach:	They propose to use a human-annotated Wikipedia-based multimodal entity linking dataset to improve the quality of existing MEL models.
Outcome:	The proposed model uses the visual information of images more effectively than existing models.

Cross-Lingual Phrase Retrieval (2022.acl-long)

Copied to clipboard

Heqi Zheng, Xiao Zhang, Zewen Chi, Heyan Huang, Yan Tan, Tian Lan, Wei Wei, Xian-Ling Mao

Cross-Lingual Transfer

Challenge:	Existing approaches to cross-lingual phrase retrieval learn word or sentence representations in word or sentences.
Approach:	They propose a cross-lingual phrase retrieval model that extracts phrase representations from unlabeled example sentences.
Outcome:	The proposed model outperforms state-of-the-art methods on a large-scale cross-lingual phrase retrieval dataset, showing it can perform in an unseen language pair during training.

TrInk: Ink Generation with Transformer Network (2025.emnlp-main)

Copied to clipboard

Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Chong-Xin Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie Liu

LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Challenge:	Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples.
Approach:	They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies.
Outcome:	The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models.

Copied to clipboard

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

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

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

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 .

Distract Large Language Models for Automatic Jailbreak Attack (2024.emnlp-main)

Copied to clipboard

Zeguan Xiao, Yan Yang, Guanhua Chen, Yun Chen

On the Robustness of Reading Comprehension Models to Entity Renaming (2022.naacl-main)

Challenge:	Commercial large language models (LLMs) have made great progress in various NLP tasks.
Approach:	They propose a black-box jailbreak framework for automated red teaming of Large language models using an iterative optimization algorithm to conceal malicious content and memory reframing.
Outcome:	The proposed framework outperforms existing jailbreak defense methods and highlights the need to develop more effective and practical defense strategies.

Copied to clipboard

Jun Yan, Yang Xiao, Sagnik Mukherjee, Bill Yuchen Lin, Robin Jia, Xiang Ren

Incomplete In-context Learning (2026.acl-long)

Challenge:	SpanBERT model is more robust than RoBERTa, despite having similar accuracy on unperturbed test data.
Approach:	They propose a pipeline to replace entity names with names from a variety of sources.
Outcome:	The proposed model performs worse when entities are renamed, the authors show . SpanBERT, which is pretrained with span-level masking, is more robust than RoBERTa .

Copied to clipboard

Wenqiang Wang, Wen Yujia, Yan Xiao, Zhifeng Chen, Yangshijie Zhang, Peng Chen, Mingbo Yang, Xiaochun Cao

Low-Resource NLP

Challenge:	Existing in-context learning assumes the retrieval dataset contains demonstrations for all output label spaces.
Approach:	They propose a framework with train-free and train-based variants to address IICL . they propose to integrate a dataset with labeled demonstrations for each output space .
Outcome:	The proposed framework outperforms existing methods under incomplete retrieval datasets and even outperformed ICL with complete labels.

Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Copied to clipboard

Yiwen Qiu, Linjuan Wu, Yizhou Liu, Yuchen Yan, Jin Ma, Xu Tan, Yao Hu, Daoxin Zhang, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment (2026.findings-acl)

Challenge:	Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach:	They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome:	The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .

Copied to clipboard

Chang Hong, Minghao Wu, Qingying Xiao, Yuchi Wang, Xiang Wan, Guangjun Yu, Benyou Wang, Yan Hu

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding (2025.acl-short)

Challenge:	Existing benchmarks lack systematic approaches to integrate philosophical frameworks and expert validation for ethical reasoning assessment.
Approach:	They propose a philosophy-grounded approach to assess medical ethics alignment . PrinciplismQA comprises 3,648 expert-validated questions spanning knowledge assessment and clinical reasoning .
Outcome:	PrinciplismQA provides a philosophy-grounded approach to assessing medical ethics alignment.

Copied to clipboard

Zikai Xiao, Ziyang Wang, Wen Ma, Yan Zhang, Wei Shen, WangYan WangYan, Luqi Gong, Zuozhu Liu

Challenge:	Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored.
Approach:	They propose a positional contrast decoding technique that contrasts long-aware attention with designed local-awn attention.
Outcome:	The proposed model achieves state-of-the-art performance on long-context benchmarks.

Revealing the Attention Floating Mechanism in Masked Diffusion Models (2026.findings-acl)

Copied to clipboard

Xin Dai, Pengcheng Huang, Zhenghao Liu, Shuo Wang, Yukun Yan, Chaojun Xiao, Yu Gu, Ge Yu, Maosong Sun

CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging (2026.findings-acl)

Challenge:	Masked diffusion models (MDMs) leverage bidirectional attention and a denoising process.
Approach:	They investigate the attention behaviors of Masked diffusion models by revealing the phenomenon of Attention Floating.
Outcome:	The proposed model doubles the performance of autoregressive models in knowledge-intensive tasks.

Copied to clipboard

Jie Cao, Zhenxuan Fan, Zhuonan Wang, Tianwei Lin, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Feifei Shao, Hongwei Wang, Jun Xiao, Siliang Tang

Green & Sustainable NLP

Challenge:	Existing PEFT methods suffer from limited parameter efficiency and coarse-grained adaptation due to proliferation of LoRA experts and instance-level routing.
Approach:	They propose a new MoE-LoRA framework that incorporates expert diversity, parameter efficiency, and fine-grained adaptation.
Outcome:	The proposed framework outperforms existing methods on multiple tasks while maintaining parameter efficiency.

LiGen: Active Lipid Generation via a Molecular Language Model (2026.acl-long)

Copied to clipboard

Ying Zhan, Xiuqi Tang, Yan Zhang, Xiao Tan, Dian Shen, Zhou Yu, Beilun Wang

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

Challenge:	Lipid nanoparticles (LNPs) can deliver cargos to tumor and immune cells . traditional approaches rely on experimental screening and expert judgment .
Approach:	They propose a method to generate lipid molecules efficiently and actively using deep learning.
Outcome:	The proposed method outperforms baseline methods on multiple cell lines and achieves a 30% improvement over the current methods.

Copied to clipboard

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

EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models (2024.findings-acl)

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

Yuyan Chen, Songzhou Yan, Sijia Liu, Yueze Li, Yanghua Xiao

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Challenge:	Existing evaluations of emotional intelligence in large language models (LLMs) focus on basic sentiment analysis tasks, such as emotion recognition, which is not enough to evaluate LLMs’ overall emotional intelligence.
Approach:	They propose a framework for evaluating the emotional intelligence of large language models (LLMs) that includes four distinct tasks: Key Event Recognition, Mixed Event Recognition and Implicit Emotional Recognition.
Outcome:	The proposed framework includes four distinct tasks: Key Event Recognition, Mixed Event Recognition and Implicit Emotional Recognition.

Copied to clipboard

Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

Reasoning

Challenge:	Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach:	They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome:	Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .

Harnessing Consistency for Robust Test-Time LLM Ensemble (2026.findings-eacl)

Copied to clipboard

Zhichen Zeng, Qi Yu, Xiao Lin, Ruizhong Qiu, Xuying Ning, Tianxin Wei, Yuchen Yan, Jingrui He, Hanghang Tong

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Challenge:	Existing efforts to improve LLM ensemble quality have focused on model consistency, but failures are often due to heterogeneous tokenization schemes and varying model expertise.
Approach:	They propose a plug-and-play technique that harnesses model consistency for robust LLM ensemble.
Outcome:	The proposed technique improves ensemble performance and robustness against erroneous signals.

Copied to clipboard

Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong

Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models (2025.acl-long)

Challenge:	Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach:	They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome:	The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.

Copied to clipboard

Huanhuan Wei, Xiao Luo, Hongyi Yu, Jinping Liang, Luning Yang, Lixing Lin, Alexandra Popa, Xiting Yan

DeltaNet: Conditional Medical Report Generation for COVID-19 Diagnosis (2022.coling-1)

Challenge:	Spatial transcriptomic technologies allow measuring gene expression profile and spatial information of cells in tissues simultaneously.
Approach:	They propose a spatial transcriptomic approach to identify spatial niches using a zero-shot large language models by transforming spatial transcriptomics data into spatial context prompts.
Outcome:	The proposed model improves performance by leveraging gene expression of neighboring cells/spots, cell type composition, tissue information, and external knowledge.

Copied to clipboard

Xian Wu, Shuxin Yang, Zhaopeng Qiu, Shen Ge, Yangtian Yan, Xingwang Wu, Yefeng Zheng, S. Kevin Zhou, Li Xiao

DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? (2024.findings-emnlp)

Challenge:	X-ray and CT are the gold standard for COVID-19 diagnosis and treatment . however, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists.
Approach:	They propose to use X-ray and CT to generate medical reports automatically . they evaluate DeltaNet on a COVID-19 dataset, where it outperforms state-of-the-art approaches .
Outcome:	The proposed system outperforms state-of-the-art methods on a COVID-19 dataset.

Copied to clipboard

Zhouhong Gu, Lin Zhang, Xiaoxuan Zhu, Jiangjie Chen, Wenhao Huang, Yikai Zhang, Shusen Wang, Zheyu Ye, Yan Gao, Hongwei Feng, Yanghua Xiao

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries (2025.acl-long)

Challenge:	Existing LLMs' abilities to detect evidence in long contexts are far inferior to humans.
Approach:	They propose a benchmark to assess LLMs' abilities in evidence and multi-step commonsense reasoning within a long context.
Outcome:	The proposed method improves the performance of LLMs in evidence detection and commonsense reasoning.

Copied to clipboard

Wenqiang Wang, Yan Xiao, Hao Lin, Yangshijie Zhang, Xiaochun Cao

ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling (2026.findings-eacl)

Challenge:	Existing adversarial text attacks rely on abundant access to shared internal features and numerous queries, limited to a single task type.
Approach:	They propose a black-box attack that exploits the transferability of adversarial texts . they use a deep-level substitute model trained in a plug-and-play manner for text classification .
Outcome:	The proposed attack can target multiple tasks with minimal perturbations . it can target commercial APIs, large language models, and image-generation models .

Copied to clipboard

Zhipeng Xu, Zhenghao Liu, Yukun Yan, Shuo Wang, Shi Yu, Zheni Zeng, Chaojun Xiao, Zhiyuan Liu, Ge Yu, Chenyan Xiong

HOTVCOM: Generating Buzzworthy Comments for Videos (2024.findings-acl)

Challenge:	Large Language Models (LLMs) exhibit suboptimal behaviors and inconsistencies when exposed to unfamiliar external information, underscoring their limitations in effectively leveraging such knowledge.
Approach:	They propose a framework that enhances the external knowledge utilization of Large Language Models through a two-stage constructivist cognitive modeling process.
Outcome:	The proposed framework achieves a 10% improvement over baseline methods on various question-answering benchmarks.

Copied to clipboard

Yuyan Chen, Songzhou Yan, Qingpei Guo, Jiyuan Jia, Zhixu Li, Yanghua Xiao

Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models (2024.acl-long)

Challenge:	Existing research focuses on generating descriptive comments in English . hot-comments are important for video marketing and branding, authors say .
Approach:	They propose a framework to generate hot-comments on a Chinese video dataset . they use a combination of visual, auditory, and textual data to generate them .
Outcome:	The proposed framework shows that it generates hot-comments on both the new and existing datasets.

Copied to clipboard

Yuyan Chen, Songzhou Yan, Panjun Liu, Yanghua Xiao

CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parsers (2022.findings-emnlp)

Challenge:	Recognizing LLMs’ capability to generate educational content can lead to advances in automated and personalized learning.
Approach:	They propose to evaluate the questioning capability in education as a teacher of large language models by evaluating their generated educational questions.
Outcome:	The proposed model can generate educational content that aligns with human perspectives and is more apt as an interdisciplinary teacher.

Copied to clipboard

Dongling Xiao, LinZheng Chai, Qian-Wen Zhang, Zhao Yan, Zhoujun Li, Yunbo Cao

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)

Challenge:	Existing text-to-SQL methods focus on making full use of history context, but neglect to explicitly comprehend the schema and conversational dependency.
Approach:	They propose a CQR-SQL that explicitly exploits schema and conversational dependency for multi-turn SQL parsing.
Outcome:	The proposed method exploits schema and contextual dependency for multi-turn SQL parsing.

Copied to clipboard

Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen

Wenqiang Wang, Peng Chen, Yan Xiao, Yangshijie Zhang, Xiaoyue Lu, Jianjie Huang, Xiaochun Cao

Challenge:	Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks.
Approach:	They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically.
Outcome:	The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios.

Copied to clipboard

Information Retrieval

Challenge:	Standard in-context learning assumes identical output spaces between test and retrieval datasets . however, in practice, these datasets can be fully aligned, partially alignes, or fully disjoint in label space .
Approach:	They propose a framework for in-context learning under output-space mismatch . they identify demonstrations relevant to the test label space via a Bayesian probabilistic criterion .
Outcome:	The proposed framework achieves state-of-the-art results across three LLMs, three task types, and four datasets.

UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)

Copied to clipboard

Yuzhe Yang, Yifei Zhang, Yan Hu, Yilin Guo, Ruoli Gan, Yueru He, Mingcong Lei, Xiao Zhang, Haining Wang, Qianqian Xie, Jimin Huang, Honghai Yu, Benyou Wang

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have expanded their potential applications in finance.
Approach:	They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions.
Outcome:	The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios.

Copied to clipboard

Zijie Dai, Shiyuan Deng, Sheng Guan, Yizhou Tian, Xin Yao, Xiao Yan, James Cheng

Green & Sustainable NLP

Challenge:	Existing memory systems invoke LLMs to extract episodic and semantic memory, and this leads to substantial token consumption.
Approach:	They propose a method that stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval.
Outcome:	Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.

MDC-Bench: A Multidisciplinary Causal Benchmark Based on Causal Structures for Evaluating Large Language Models (2026.findings-acl)

Copied to clipboard

Peng Wang, Yuxiong Yan, Xiao Ding, Kai Xiong, Bibo Cai, Chao Peng, Yutai Hou, Dandan Tu, Bing Qin, Ting Liu

HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)

Challenge:	Existing causal datasets focus on the commonsense domain, but LLMs perform poorly when answering complex questions.
Approach:	They propose a multidisciplinary causal evaluation benchmark to assess LLMs' knowledge and skills.
Outcome:	The proposed model improves in domain specialization, structural diversity, and task complexity.

Copied to clipboard

Yan Liu, Minghui Zhang, Bojian Xiong, Yifan Xiao, Yinong Sun, Yating Mei, Longyu Zeng, Jingchao Yang, Yang Wang, Deyi Xiong

Reasoning

Challenge:	a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models .
Approach:	They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams .
Outcome:	The proposed model is based on o1-like models and a high-level model.

ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)

Copied to clipboard

Haiquan Zhao, Lingyu Li, Shisong Chen, Shuqi Kong, Jiaan Wang, Kexin Huang, Tianle Gu, Yixu Wang, Jian Wang, Liang Dandan, Zhixu Li, Yan Teng, Yanghua Xiao, Yingchun Wang

Dialogue Systems & Conversational Agents

Challenge:	Emotion Support Conversation (ESC) is a crucial application for reducing stress and providing emotional guidance.
Approach:	They re-organize 2,801 role-playing cards to define roles of role-players . they train a specific role- playing model called ESC-Role which behaves more like a confused person than GPT-4 .
Outcome:	The proposed model behaves more like a confused person than GPT-4, and the model performs better than GPLs.

Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios? (2024.findings-acl)

Copied to clipboard

Yuyan Chen, Yueze Li, Songzhou Yan, Sijia Liu, Jiaqing Liang, Yanghua Xiao

MIND: Towards Immersive Psychological Healing with Multi-Agent Inner Dialogue (2025.findings-emnlp)

Challenge:	Existing games such as "Who is undercover" are subjective and difficult to evaluate .
Approach:	They propose a game called BrainKing that evaluates LLMs' problem-solving capability under incomplete information scenarios.
Outcome:	The proposed game requires LLMs to identify target entities with limited yes-or-no questions and potential misleading answers.

Copied to clipboard

Yujia Chen, Changsong Li, Yiming Wang, Tianjie Ju, Qingqing Xiao, Nan Zhang, Zifan Kong, Peng Wang, Binyu Yan

Dialogue Systems & Conversational Agents

Challenge:	Mental health issues are worsening in today’s competitive society, such as depression and anxiety.
Approach:	They propose a multi-agent inner dialogue paradigm that provides more immersive psychological healing environments.
Outcome:	The proposed paradigm provides more immersive psychological healing environments.

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)

Copied to clipboard

Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo

Empirical Analysis of Decoding Biases in Masked Diffusion Models (2026.acl-long)

Challenge:	Existing research on reinforcement learning for LLMs under data scarcity has not been unified.
Approach:	They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric.
Outcome:	The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area.

Copied to clipboard

Pengcheng Huang, Tianming Liu, Zhenghao Liu, Yukun Yan, Shuo Wang, Tong Xiao, Zulong Chen, Maosong Sun

Analyzing Large Language Models’ Capability in Location Prediction (2024.lrec-main)

Challenge:	Existing MDMs employ uncertainty-based decoding strategies that limit their reasoning ability and ultimately degrade generation quality.
Approach:	They propose a framework that regularizes uncertainty-based decoding by incorporating two complementary priors to shape global decoding trajectories and promote content informativeness.
Outcome:	The proposed framework outperforms existing decoding strategies by more than 7% while achieving comparable performance to autoregressive models of similar parameter scales.

Copied to clipboard

Zhaomin Xiao, Eduardo Blanco, Yan Huang

COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval (2026.acl-long)

Challenge:	Large language models (LLMs) are underutilized in the field of location prediction due to the sparsity of geotagged tweets.
Approach:	They present experimental results with four large language models in various instruction finetuning and exemplar settings and analyze whether taking into account the context is beneficial.
Outcome:	The proposed model is able to predict location in a variety of settings, including fine tuning and exemplar settings, and it is compared with the best model in the literature.

Copied to clipboard

Boci Peng, Xiao Liu, Boren Hu, Yun Zhu, Xuanbo Fan, Yanwei Yue, Chunyu Yang, Yan Zhang

Com2 : A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models (2025.acl-long)

Challenge:	Existing paradigms treat facts independently or employ myopic search, failing to optimize collective subgraph utility.
Approach:	They propose a framework that formalizes evidence retrieval as a constrained submodular maximization problem.
Outcome:	The proposed framework captures the trade-off between information relevance and structural complexity.

Copied to clipboard

Kai Xiong, Xiao Ding, Yixin Cao, Yuxiong Yan, Li Du, Yufei Zhang, Jinglong Gao, Jiaqian Liu, Bing Qin, Ting Liu

Reasoning

Challenge:	Existing works focus on complex tasks like math and code, while complex commonsense reasoning remains underexplored due to its uncertainty and lack of structure.
Approach:	They propose to build a benchmark for large language models based on complex commonsense reasoning based upon causal event graphs and causal theory.
Outcome:	The proposed benchmark combines a complex commonsense reasoning benchmark with a detective story to achieve a more challenging subset.

X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation (2026.findings-acl)

Copied to clipboard

Kun Zhao, Chenghao Xiao, Sixing Yan, Haoteng Tang, William K. Cheung, Noura Al Moubayed, Liang Zhan, Chenghua Lin

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Challenge:	Technical language and templated nature of professional reports hinder patient comprehension and allow models to artificially boost lexical metrics such as BLEU by reproducing common report patterns.
Approach:	They propose a layman's RRG framework that leverages layperson-friendly language to enhance patient accessibility and promote robust evaluation and report generation by encouraging models to focus on semantic accuracy over rigid templates.
Outcome:	The proposed framework improves model performance with more layman-style data, compared to templated professional language and inflated lexical scores.

Copied to clipboard

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

SEMIROUTER: Sparse-Data Enhanced Routing for Adaptive Multi-LLM System (2026.eacl-long)

Challenge:	Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach:	They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome:	The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.

Copied to clipboard

Zijie Wang, Xinyu Yan, Che Wang, Zeng Zihao, Lei Xiao, Wei Yang Bryan Lim

Green & Sustainable NLP

Challenge:	Existing routing methods suffer from poor scalability and dependence on datasets for training . energy footprint is also considered in the decision to implement our new LLM routing framework .
Approach:	They propose a new LLM routing framework that dynamically allocates queries to the most appropriate LLM.
Outcome:	The proposed method improves data efficiency, adaptability, and routing accuracy compared to existing methods.

DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models (2024.emnlp-main)

Copied to clipboard

Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, Kang Liu

Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages (2025.findings-emnlp)

Challenge:	DA-Code is a code generation benchmark designed to assess LLMs on agent-based data science tasks.
Approach:	They propose a code generation benchmark specifically designed for LLMs on agent-based data science tasks.
Outcome:	The benchmark performs better than existing frameworks, but lacks accuracy . it is based on real-world data, and includes examples that cover a wide range of tasks .

Copied to clipboard

Yongdong Chi, Hanqing Wang, Yun Chen, Yan Yang, Jian Yang, Zonghan Yang, Xiao Yan, Guanhua Chen

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language (2025.findings-acl)

Challenge:	Existing prompt-based methods craft meticulous text guidelines and examples to facilitate SQL generation, but their accuracy is hindered by the large semantic gap between the texts and the low-resource SQL programs.
Approach:	They propose to use Python as a pivot to bridge between natural language query and SQL program.
Outcome:	The proposed method improves the execution accuracy of the best-performing baseline by up to 3.20.

Copied to clipboard

Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao, Ruoyu Li, Yong Jiang

Concise and Organized Perception Facilitates Reasoning in Large Language Models (2025.findings-naacl)

Challenge:	Existing methods to bypass security defenses of large language models (LLMs) are not effective, but QueryAttack can be jailbroken.
Approach:	They propose a framework to examine generalizability of safety alignment by translating malicious queries into structured non-natural query languages.
Outcome:	The proposed framework can achieve high attack success rates and jailbreak various defense methods on mainstream LLMs.

Copied to clipboard

Junjie Liu, Shaotian Yan, Chen Shen, Zhengdong Xiao, Liang Xie, Wenxiao Wang, Jieping Ye

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications (2026.acl-long)

Challenge:	Extensive experimental results on several popular logical benchmarks (ProofWriter, PrOntoQA, PrONtoQA-OOD, and FOLIO) and mathematical benchmark (DI-GSM) show that COP significantly outperforms previous state-of-the-art methods.
Approach:	They propose a reasoning approach called Concise and Organized Perception (COP) that carefully analyzes the given statements to identify the most pertinent information while eliminating redundancy efficiently.
Outcome:	The proposed approach outperforms state-of-the-art methods on several popular logical benchmarks and mathematical benchmarks.

Copied to clipboard

Xiaoyue Lu, Xianglin Yang, Haijun Liu, Jiahao Liu, Kuntai Cai, Yan Xiao, Jin Song Dong

Structured Data in NLP

Challenge:	Existing safety evaluation paradigms rely on constructed benchmarks or dynamic red-teaming to probe potential vulnerabilities.
Approach:	They propose a framework that integrates specification-based software testing with AI safety.
Outcome:	The proposed framework achieves higher coverage and attack success counts compared to baselines.

Allies: Prompting Large Language Model with Beam Search (2023.findings-emnlp)

Copied to clipboard

Hao Sun, Xiao Liu, Yeyun Gong, Yan Zhang, Daxin Jiang, Linjun Yang, Nan Duan

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

Challenge:	Existing methods to build LLMs with stacking are limited by their information coverage and low fault tolerance.
Approach:	They propose a method that leverages large language models to iteratively generate new queries from an input query.
Outcome:	The proposed method outperforms baselines on open-domain question answering benchmarks.

Copied to clipboard

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

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization (2023.acl-long)

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

Copied to clipboard

SongYang Gao, Shihan Dou, Yan Liu, Xiao Wang, Qi Zhang, Zhongyu Wei, Jin Ma, Ying Shan

Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (P19-1)

Challenge:	Existing adversarial training methods require multi-step gradient ascents or word substitutions to obtain adversarials, which impairs the effectiveness of adversariarial training.
Approach:	They propose a procedure for instead adversarial training with only clean data that estimates the adversarials loss by perturbing the input data’s probability distribution rather than their embeddings.
Outcome:	The proposed procedure reduces time consumption by up to 70% compared to current best-performing adversarial training methods.

Copied to clipboard

Jiaqi Guo, Zecheng Zhan, Yan Gao, Yan Xiao, Jian-Guang Lou, Ting Liu, Dongmei Zhang