Papers by Li Cui

Composable Text Controls in Latent Space with ODEs (2023.emnlp-main)

Challenge:	Pretrained Language Models excel in various Natural Language Processing tasks, but performance on social media applications like rumor detection remains suboptimal.
Approach:	They propose a pretraining strategy to infuse information from propagation structures into pretrained language models to capture interactions of stance and sentiment crucial for rumor detection.
Outcome:	The proposed model outperforms existing methods on social media applications and significantly improves rumor detection performance.

Copied to clipboard

Guangyi Liu, Zeyu Feng, Yuan Gao, Zichao Yang, Xiaodan Liang, Junwei Bao, Xiaodong He, Shuguang Cui, Zhen Li, Zhiting Hu

Green & Sustainable NLP

Challenge:	Existing approaches to composable text operations often require plug-and-play . a single LM can perform arbitrary text operation composition in the latent space .
Approach:	They propose an efficient approach for composable text operations in the latent space of text . they connect pretrained LMs to the laten space and adapt them to the space .
Outcome:	The proposed approach improves on existing methods in the latent space of text.

TWAG: A Topic-Guided Wikipedia Abstract Generator (2021.acl-long)

Copied to clipboard

Fangwei Zhu, Shangqing Tu, Jiaxin Shi, Juanzi Li, Lei Hou, Tong Cui

FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs’ Responsiveness to Human Feedback (2025.emnlp-main)

Challenge:	Existing models view Wikipedia abstract as plain text, ignoring that it is a description of a certain entity and can be decomposed into different topics.
Approach:	They propose a model that guides Wikipedia abstract generation with topical information.
Outcome:	The proposed model outperforms baselines and is capable of generating comprehensive abstracts.

Copied to clipboard

Youquan Li, Miao Zheng, Fan Yang, Guosheng Dong, Bin Cui, Weipeng Chen, Zenan Zhou, Wentao Zhang

Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot (2021.emnlp-demo)

Challenge:	Existing research focuses on benchmarking LLMs in single-turn dialogues, neglecting the nuanced nature of human feedback within real-world usage scenarios.
Approach:	They propose a fine-grained, multi-task benchmark designed to evaluate LLMs’ responsiveness to human feedback under real-world usage scenarios in Chinese.
Outcome:	The proposed benchmarks show that human feedback can significantly impact LLMs’ responsiveness in real-world usage scenarios.

Copied to clipboard

Juraj Juraska, Kevin Bowden, Lena Reed, Vrindavan Harrison, Wen Cui, Omkar Patil, Rishi Rajasekaran, Angela Ramirez, Cecilia Li, Eduardo Zamora, Phillip Lee, Jeshwanth Bheemanpally, Rohan Pandey, Adwait Ratnaparkhi, Marilyn Walker

Natural Language Interfaces

Challenge:	Athena 2.0 is a socialbot that has been a finalist in the last two Alexa Prize Grand Challenges.
Approach:	They describe Athena 2.0's dialogue management strategy and its performance in the Alexa Prize 20/21 competition.
Outcome:	The system is a finalist in the Alexa Prize 20/21 competition and will be shown on a live demo and recorded video recordings.

CodeArena: Evaluating and Aligning CodeLLMs on Human Preference (2025.emnlp-main)

Copied to clipboard

Jian Yang, Jiaxi Yang, Wei Zhang, Jin Ke, Yibo Miao, Lei Zhang, Liqun Yang, Zeyu Cui, Yichang Zhang, Zhoujun Li, Binyuan Hui, Junyang Lin

Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generation (2025.findings-emnlp)

Challenge:	Code large language models (codeLLMs) focus on synthesizing the correct code snippet, ignoring the alignment with human preferences.
Approach:	They propose a benchmark code-based on 40 categories and 44 programming languages to emulate real-world coding tasks.
Outcome:	The proposed benchmarks show that open-source code LLMs perform better than open-sourced ones.

Copied to clipboard

Xiaohu Zhu, Qian Li, Lizhen Cui, Yuntao Du

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)

Challenge:	Existing models struggle with complex queries, especially multi-table joins and reasoning.
Approach:	They propose to build a model with synthetic training samples and a structure-aware curriculum learning framework for enhancing SQL generation.
Outcome:	The proposed model improves on the existing model on the Spider and Bird benchmarks.

Copied to clipboard

Zheng Liu, Honglin Lin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Conghui He, Bin Cui, Wentao Zhang, Lijun Wu

Selective Differential Privacy for Language Modeling (2022.naacl-main)

Challenge:	Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations .
Approach:	They propose a framework to synthesize complex charts and reliable reasoning data from scratch.
Outcome:	Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models .

Copied to clipboard

Weiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia, Zhou Yu

Ethical NLP

Challenge:	Existing methods to protect sensitive data from leaking are over-pessimistic and undifferentiated.
Approach:	They propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data to improve model utility.
Outcome:	The proposed privacy-preserving mechanism achieves better utility while remaining safe under various privacy attacks compared to baselines.

From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models (2026.findings-acl)

Copied to clipboard

Jiaxin Zhang, Wendi Cui, Zhuohang Li, Lifu Huang, Bradley A. Malin, Caiming Xiong, Chien-Sheng Wu

Multi-Granularity Optimization for Non-Autoregressive Translation (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have remarkable capabilities, but unreliability remains a barrier to deployment in high-stakes domains.
Approach:	They propose to transform uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.
Outcome:	The proposed model evolution from passive diagnostic metric to active control signal is critical for high-stakes applications.

Copied to clipboard

Yafu Li, Leyang Cui, Yongjing Yin, Yue Zhang

Machine Translation

Challenge:	Non-autoregressive machine translation suffers severe performance deterioration due to the naive independence assumption.
Approach:	They propose a method which collects model behaviours on translation segments of various granularities and integrates feedback for backpropagation to reduce latency.
Outcome:	Experiments on four benchmark datasets show that the proposed method outperforms baseline models trained with cross-entropy loss and achieves the best performance on WMT’16 EnRo and highly competitive results on WTM’14 EnDe.

Turning the Tide: Repository-based Code Reflection (2025.findings-emnlp)

Copied to clipboard

Wei Zhang, Jian Yang, Jiaxi Yang, Ya Wang, Zhoujun Li, Zeyu Cui, Binyuan Hui, Junyang Lin

Better Explain Transformers by Illuminating Important Information (2024.findings-eacl)

Challenge:	Code large language models (LLMs) enhance programming by understanding and generating code across languages.
Approach:	a new benchmark evaluates code understanding and generation in repositories using code large language models.
Outcome:	The proposed model improves code understanding and generation in repositories by evaluating 1,888 test cases across 6 programming languages.

Copied to clipboard

Linxin Song, Yan Cui, Ao Luo, Freddy Lecue, Irene Li

Explainability & Interpretability in NLP

Challenge:	Existing explanations focus on the input and output of the Transformers, resulting in confusing results.
Approach:	They propose to highlight important information and eliminate irrelevant information by a refined information flow on top of the layer-wise relevance propagation method.
Outcome:	The proposed method outperforms baseline models on classification and question-answering datasets with over 3% to 33% improvement on explanation metrics.

Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality (2023.eacl-main)

Copied to clipboard

Xinnian Liang, Shuangzhi Wu, Chenhao Cui, Jiaqi Bai, Chao Bian, Zhoujun Li

CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval (2026.acl-long)

Challenge:	Experimental results show that our model outperforms strong baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.
Approach:	They propose a topic-aware global-local centrality model to help select the salient context from all sub-topics.
Outcome:	The proposed model outperforms baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.

Copied to clipboard

Jiahui Geng, Fengyu Cai, Shaobo Cui, Qing Li, Liangwei Chen, Chenyang Lyu, Haonan Li, Derui Zhu, Alexander Pretschner, Heinz Koeppl, Fakhri Karray

Information Retrieval

Challenge:	Existing benchmarks focus on functional relevance while neglecting code quality.
Approach:	They propose a multilingual benchmark to evaluate quality-aware code retrieval . they include fine-grained quality annotations over 42,725 queries and 134,907 code snippets .
Outcome:	The proposed benchmarks show that state-of-the-art models fail to separate buggy or insecure code from robust counterparts.

ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions (2024.findings-acl)

Copied to clipboard

Honglin Lin, Siyu Li, Guoshun Nan, Chaoyue Tang, Xueting Wang, Jingxin Xu, Rong Yankai, Zhouzhili Zhouzhili, Yutong Gao, Qimei Cui, Xiaofeng Tao

Visual Data in NLP

Challenge:	Existing approaches to image retrieval from contextual descriptions (IRCD) lag behind human performance in IRCD.
Approach:	They propose a method that relies on a doubly contextual alignment scheme for challenging IRCD.
Outcome:	The proposed method can yield comparable results with GPT-4V, despite fewer parameters.

Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration (2026.findings-acl)

Copied to clipboard

Linzhuang Sun, Tianyu Guo, Hao Liang, Ruitong Liu, Yuying Li, Qifeng Cai, Jingxuan Wei, Yuchen Wu, Bihui Yu, Xiangxiang Zhang, Wentao Zhang, Bin Cui

TableBank: Table Benchmark for Image-based Table Detection and Recognition (2020.lrec-1)

Challenge:	Structured Query Language (SQL) is the cornerstone for data-driven decision-making.
Approach:	They propose a benchmark to rigorously evaluate Large Language Models within a dynamic interaction framework.
Outcome:	The proposed benchmark aims to rigorously evaluate LLMs within a dynamic interaction framework.

Copied to clipboard

Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou, Zhoujun Li

Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists (2025.findings-acl)

Challenge:	Existing techniques for table detection and recognition are limited to document types and layouts.
Approach:	They propose to build a table detection and recognition dataset with weak supervision from Word and Latex documents on the internet.
Outcome:	The proposed dataset contains 417K high quality labeled tables and is publicly available.

Copied to clipboard

Yue Cui, Liuyi Yao, Shuchang Tao, Weijie Shi, Yaliang Li, Bolin Ding, Xiaofang Zhou

MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation (2022.acl-long)

Challenge:	Large language models (LLMs) have advanced natural language processing, but their effectiveness is often hampered by parameter mis-filling during tool calling.
Approach:	They propose a hierarchical tool error checklist framework to diagnose and mitigate tool-calling errors without relying on extensive real-world interactions.
Outcome:	The proposed framework improves parameter-filling accuracy and tool-calling success rates compared to baseline methods.

Copied to clipboard

Quan Tu, Yanran Li, Jianwei Cui, Bin Wang, Ji-Rong Wen, Rui Yan

ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants (2026.acl-long)

Challenge:	Existing methods for emotional support conversation are too coarse-grained to capture user’s instant mental state and focus on expressing empathy in the response rather than gradually reducing user’ s distress.
Approach:	They propose a model which firstly infers the user’s fine-grained emotional status and then responds skillfully using a mixture of strategy.
Outcome:	The proposed model infers the user’s fine-grained emotional status and responds skillfully using mixed-up strategy modeling.

Copied to clipboard

ZhongDong Li, Weijie Shi, Yue Cui, Haolun MA, Yuanjun Liu, Jiawei Li, An Liu, Jia Zhu, Jiajie Xu

Robustness in NLP

Challenge:	Learning transfer theory emphasizes that applying acquired knowledge to novel manifestations is a key signal of deep understanding
Approach:	They propose a benchmark that probes transfer robustness along two rewrite levels: Near Transfer and Far Transfer.
Outcome:	The proposed benchmark demonstrates that large language models are robust when faced with novel manifestations of the same problem.

PV2TEA: Patching Visual Modality to Textual-Established Information Extraction (2023.findings-acl)

Copied to clipboard

Hejie Cui, Rongmei Lin, Nasser Zalmout, Chenwei Zhang, Jingbo Shang, Carl Yang, Xian Li

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

Challenge:	Empirical results show up to 11.74% absolute (20.97% relative) increase over unimodal baselines.
Approach:	They propose to patch the visual modality to the textual-established attribute in- formation extractor.
Outcome:	Empirical results show up to 11.74% absolute (29.9% relative) increase over unimodal baselines.

Copied to clipboard

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

FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models (2026.findings-acl)

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

Copied to clipboard

Junzhe Jiang, Chang Yang, Aixin Cui, Sihan Jin, Yujing Zhang, Yilin Xiao, Ruiyu Wang, Bo Li, Xiao Huang, Danny Dongning Sun, Xinrun Wang

ChatEdit: Towards Multi-turn Interactive Facial Image Editing via Dialogue (2023.emnlp-main)

Challenge:	Existing benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow- level evaluation.
Approach:	a new benchmark evaluates large language models on financial management workflows . the global financial services market is projected to grow to $37 trillion by 2027 .
Outcome:	a new benchmark for large language models on financial management workflows reveals critical capability gaps . accuracy drops from 90% on basic tasks to 40% on complex scenarios requiring multi-step reasoning . the global financial services market reached $25.8 trillion in 2022 and is projected to grow to $37 trillion by 2027 .

Copied to clipboard

Xing Cui, Zekun Li, Pei Li, Yibo Hu, Hailin Shi, Chunshui Cao, Zhaofeng He

Visual Data in NLP

Challenge:	Existing approaches to interactive facial image editing treat multi-turn editing as a sequence of successive single-turn edits, leading to attribute forgetting and error accumulation.
Approach:	They propose a framework for interactive facial image editing through dialogues based on the CelebA-HQ dataset and a benchmark dataset to evaluate this.
Outcome:	The proposed framework outperforms existing methods and improves existing ones.

OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety (2024.acl-demos)

Copied to clipboard

Chuang Liu, Linhao Yu, Jiaxuan Li, Renren Jin, Yufei Huang, Ling Shi, Junhui Zhang, Xinmeng Ji, Tingting Cui, Liutao Liutao, Jinwang Song, Hongying Zan, Sun Li, Deyi Xiong

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination (2026.acl-long)

Challenge:	a rapid development of Chinese large language models poses big challenges for efficient LLM evaluation.
Approach:	They propose an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety.
Outcome:	The evaluation platform OpenEval benchmarks Chinese LLMs across capability, alignment and safety.

Copied to clipboard

Chenlong Yin, Zeyang Sha, Shiwen Cui, Changhua Meng, Zechao Li

Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis (2024.findings-emnlp)

Challenge:	Recent studies suggest that strengthening reasoning often coincides with increased hallucination . however, no prior work has examined whether reasoning enhancement itself causes tool hallucinism .
Approach:	They propose a diagnostic benchmark measuring tool hallucination in two failure modes . they demonstrate a causal relationship between enhancing reasoning and tool hallubulation .
Outcome:	The proposed benchmark measures tool hallucination in two failure modes: no tool available, and (ii) only distractor tools available.

Copied to clipboard

Jianxiang Yu, Zichen Ding, Jiaqi Tan, Kangyang Luo, Zhenmin Weng, Chenghua Gong, Long Zeng, RenJing Cui, Chengcheng Han, Qiushi Sun, Zhiyong Wu, Yunshi Lan, Xiang Li

ConMA : Confidence-Guided Kernel Sampling with Multi-Stage Aggregation for LLM Reasoning (2026.findings-acl)

Challenge:	Existing approaches to review scientific papers are limited by their content or quality . SEA is a framework for automated scientific review, but its contents are generic or partial.
Approach:	They propose a framework for automated scientific review using large language models . they propose to use a standardized review dataset to fine-tune an LLM to generate high-quality reviews.
Outcome:	The proposed framework can generate high-quality reviews from standardized datasets and improves on the existing feedback mechanisms.

Copied to clipboard

Yinuo Wang, Qingjie Li, Wenyao Cui, Qiuchi Li, Zhang Huaping

Hyperbolic Graph Neural Network for Temporal Knowledge Graph Completion (2024.lrec-main)

Challenge:	Existing approaches to test-time scaling rely on external verifiers and one-shot independent sampling.
Approach:	They propose a test-time scaling framework that reallocates a fixed inference budget into iterative sample–filter–diversify–select cycles.
Outcome:	ConMA outperforms baselines on multiple benchmarks while converging early with only 18 samples on average, substantially reducing inference cost.

Copied to clipboard

Yancong Li, Xiaoming Zhang, Ying Cui, Shuai Ma

BERT-enhanced Relational Sentence Ordering Network (2020.emnlp-main)

Challenge:	Existing knowledge graph models are inefficient at capturing complex temporal dynamics and hierarchical relations within TKGs.
Approach:	They propose to use hyperbolic geometry to effectively model temporal knowledge graphs . they use the hyperbolical gated Graph Neural Network and the hyperbipolar convolutional neural network .
Outcome:	The proposed model achieves state-of-the-art performance on four benchmark datasets . it is compared with previous models and is expected to be useful in real-world applications .

Copied to clipboard

Baiyun Cui, Yingming Li, Zhongfei Zhang

Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation (2025.findings-naacl)

Challenge:	Existing approaches to improve coherence modeling for paragraphs have been developed.
Approach:	They propose a BERT-enhanced Relational Sentence Ordering Network to capture better dependency relationship among sentences and exploit it with a deep relational module.
Outcome:	The proposed model shows significant improvement over the state-of-the-art on six datasets.

Copied to clipboard

Yu Wang, Jiaxin Zhang, Xiang Gao, Wendi Cui, Peng Li, Kamalika Das

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)

Challenge:	Large Language Models (LLMs) often experience “contextual hallucination” where they prioritize self-generated content over input context, leading to a disregard for pertinent details.
Approach:	They propose a method that dynamically adjusts attention maps to enhance contextual relevance by using a trained classifier to identify attention maps likely to induce hallucinations.
Outcome:	The proposed approach reduces hallucinations across open-source models on summarization and open-book QA tasks.

Copied to clipboard

Hongze Mi, Yibo Feng, WenJie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Jun Fang, Hua Chai, Naiqiang Tan, Gang Pan

Challenge:	Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction.
Approach:	They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process.
Outcome:	The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process .

Beyond Human Labels: A Multi-Linguistic Auto-Generated Benchmark for Evaluating Large Language Models on Resume Parsing (2025.emnlp-main)

Copied to clipboard

Zijian Ling, Han Zhang, Jiahao Cui, Zhequn Wu, Xu Sun, Guohao Li, Xiangjian He

A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning (2026.acl-industry)

Challenge:	Efficient resume parsing is critical for global hiring, yet the lack of dedicated benchmarks for evaluating large language models (LLMs) on multilingual, structure-rich resumes hinders progress.
Approach:	They propose to use a human-in-the-loop pipeline to generate 2,500 synthetic resumes spanning 50 templates, 30 career fields, and 5 languages to evaluate large language models.
Outcome:	The proposed benchmarks show that the models perform poorly on multilingual resumes and lack of standardized templates.

Copied to clipboard

Guoliang Zhao, Zixin Cui, Chao Ye, Dengwu He, Fei Huang, Yubo Liu, Shuanglong Li, Tzungren Kuo, Bin Ding, Shuang Zhang, null KunhongZhu, Zhi Guo, Liu Lin

Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension (D19-58)

Challenge:	Existing approaches to matching use Large Language Models as feature extractors, underutilizing their full modeling capabilities.
Approach:	They propose a matching paradigm that integrates two-tower, single-towing, and generative tasks within a unified LLM framework via attention-mask partitioning.
Outcome:	The proposed model achieves superior performance and strong practical value in an industrial search engine.

Copied to clipboard

Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Lei Cui, Songhao Piao, Ming Zhou

CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models (2025.findings-emnlp)

Challenge:	Experimental results show that unified model outperforms other models that treat encoding and matching separately.
Approach:	They evaluate a unified model with Transformer layers for machine reading comprehension . they find that the model learns different modeling strategies compared with previous models .
Outcome:	The unified model outperforms models with Transformer layers on the machine reading comprehension task.

Copied to clipboard

Feiyang Li, Peng Fang, Zhan Shi, Arijit Khan, Fang Wang, Weihao Wang, null Zhangxin-hw, Cui Yongjian

Lost in Literalism: How Supervised Training Shapes Translationese in LLMs (2025.acl-long)

Challenge:	Chain-of-thought reasoning has two key limitations: lack of reliability when solely relying on LLM-generated reasoning chains and interference from natural language reasoning steps with the models’ inference logic.
Approach:	They propose a chain-of-thought reasoning framework with three key designs to address these issues.
Outcome:	The proposed framework improves the performance of large language models on complex tasks by incorporating knowledge graphs and learnable knowledge case-aware RAG.

Copied to clipboard

Yafu Li, Ronghao Zhang, Zhilin Wang, Huajian Zhang, Leyang Cui, Yongjing Yin, Tong Xiao, Yue Zhang

Machine Translation

Challenge:	Large language models exhibit translationese errors and generate unexpected unnatural translations . Neural machine translation (NMT) has become the dominant method in machine translation research .
Approach:	They evaluate the prevalence of translationese in LLM-generated translations and investigate its roots during supervised fine-tuning.
Outcome:	The proposed methods reduce translationese while improving translation naturalness . the proposed methods are validated by human evaluations and automatic metrics .

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models (2026.acl-long)

Copied to clipboard

Zirui Song, Qian Jiang, Mingxuan Cui, Mingzhe Li, Lang Gao, Zeyu Zhang, Zixiang Xu, Yanbo Wang, Guangxian Ouyang, Zhenhao Chen, Xiuying Chen

Focus-Constrained Attention Mechanism for CVAE-based Response Generation (2020.findings-emnlp)

Challenge:	a recent study evaluated large audio-language models against jailbreak attacks . a new benchmark is being developed to evaluate LAM safety against jailbreaking attacks based on temporal and semantic nature of speech .
Approach:	They propose a benchmark to evaluate LAM jailbreak vulnerabilities in adversarial audio prompts . they use a dataset of 1,495 adversarials to evaluate their performance .
Outcome:	The proposed benchmark evaluates state-of-the-art LAMs against jailbreak attacks . it demonstrates that even small, semantically preserved perturbations can reduce safety .

Copied to clipboard

Zhi Cui, Yanran Li, Jiayi Zhang, Jianwei Cui, Chen Wei, Bin Wang

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection (2024.emnlp-main)

Challenge:	Existing models generate high-frequency but trivial responses such as "I don't know" or "I'm ok" due to the discrepancy in discourse-level information, standard models generate one-to-many relationships.
Approach:	They propose to transform coarse-grained discourse-level information into fine-grounded word-level knowledge by introducing a fine-grain focus signal and a focus-constrained attention mechanism to take full advantage of focus.
Outcome:	The proposed model can generate more diverse and informative responses compared with state-of-the-art models.

Copied to clipboard

Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, Li Yuan

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)

Challenge:	Existing approaches to visual-language understanding lack unified tokenization for images and videos . lack of unified visual representations makes it difficult to learn multi-modal interactions from poor projection layers.
Approach:	They propose to unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM.
Outcome:	The proposed model outperforms Video-ChatGPT on image benchmarks and on 9 image benchmark benchmarks.

Copied to clipboard

Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He

GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models (2025.findings-emnlp)

Challenge:	Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps.
Approach:	They propose a method to identify critical reasoning steps using perplexity as a measure of their importance.
Outcome:	The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT.

Copied to clipboard

Jialin Chen, Houyu Zhang, Seongjun Yun, Alejandro Mottini, Rex Ying, Xiang Song, Vassilis N. Ioannidis, Zheng Li, Qingjun Cui

Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue (2023.findings-emnlp)

Challenge:	Existing graph RAGs decouple retrieval and reasoning processes, preventing adaptability . existing graph Raggings depend heavily on ground-truth entities, which are often unavailable in open-domain settings.
Approach:	They propose a graph retriever that is trained end-to-end with large-scale graphs . structure and semantic features are encoded via soft tokens and the verbalized graph .
Outcome:	The proposed approach improves the performance of large-scale graph retrieval models by grounding it with external knowledge.

Copied to clipboard

Yuanxing Liu, Weinan Zhang, Yifan Chen, Yuchi Zhang, Haopeng Bai, Fan Feng, Hengbin Cui, Yongbin Li, Wanxiang Che

PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling (2022.coling-1)

Challenge:	E-commerce pre-sales dialogues elicit user needs and preferences for items . large language models lack domain-specific knowledge for accurate recommendations .
Approach:	They propose two collaboration strategies to integrate CRS and large language models in pre-sales dialogues.
Outcome:	The proposed methods can be very effective in some cases, the authors say .

Copied to clipboard

Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao, Hao Lei, Xinyue Cui, Yi Huang, Junlan Feng, Weiran Xu

Robustness in NLP

Challenge:	Existing slot filling models memorize inherent patterns of entities and contexts from training data.
Approach:	They propose a perturbed semantic structure awareness transferring method for slot filling models . they use two MLM-based training strategies to learn contextual semantic structure and word distribution .
Outcome:	The proposed method outperforms existing methods and gains strong generalization while preventing model from memorizing inherent patterns of entities and contexts.

Event Causality Extraction with Event Argument Correlations (2022.coling-1)

Copied to clipboard

Shiyao Cui, Jiawei Sheng, Xin Cong, Quangang Li, Tingwen Liu, Jinqiao Shi

Syntactic Text Processing

Challenge:	Event Causality Identification (ECI) ignores crucial event structure and cause-effect component information, making it struggle for downstream applications.
Approach:	They propose a task to extract event causality pairs with their structured event information from plain text.
Outcome:	The proposed method captures the intra- and inter-event argument correlations for ECE and provides several future directions.

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction (2023.findings-acl)

Copied to clipboard

Qian Li, Shu Guo, Cheng Ji, Xutan Peng, Shiyao Cui, Jianxin Li, Lihong Wang

LLMSurgeon: Diagnosing Data Mixture of Large Language Models (2026.acl-long)

Challenge:	Existing methods for multi-modal relation extraction lack useful visual information.
Approach:	They propose a novel multi-modal relation extraction framework to capture deeper correlations of text, entity pair, and image/objects.
Outcome:	The proposed framework captures the deeper correlations of text, entity pair, and image/objects, and extracts useful information.

Copied to clipboard

Yaxin Luo, Jiacheng Cui, Xiaohan Zhao, Xinyi Shang, Jiacheng Liu, Xinyue Bi, Zhaoyi Li, Zhiqiang Shen

Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks (2025.coling-main)

Challenge:	a lack of transparency in large language models makes auditing their "digital DNA" difficult.
Approach:	They propose a framework that casts DMS as an inverse problem under label-shift assumption . they propose LLMScan, a recipe-verifiable evaluation suite built from open-source LLMs .
Outcome:	The proposed framework casts DMS as an inverse problem under label-shift assumption . compared with existing frameworks, it recovers domain mixtures with high fidelity .

Copied to clipboard

Qintong Li, Leyang Cui, Lingpeng Kong, Wei Bi

Decoder Tuning: Efficient Language Understanding as Decoding (2023.acl-long)

Challenge:	Existing work uses large language models (LLMs) to evaluate natural language process tasks, but there are shortcomings in current LLMs.
Approach:	They examine the alignment between LLM evaluators and human annotators by comparing conventional and alignment tasks with different evaluation criteria.
Outcome:	The proposed models excel in general criteria, such as fluency, but face challenges with complex criteria, including numerical reasoning.

Copied to clipboard

Ganqu Cui, Wentao Li, Ning Ding, Longtao Huang, Zhiyuan Liu, Maosong Sun

Spotting AI’s Touch: Identifying LLM-Paraphrased Spans in Text (2024.findings-acl)

Challenge:	Existing approaches to adapt pre-trained models with parameters frozen are based on input-side adaptation, which requires thousands of API queries.
Approach:	They propose to train a model-as-a-service (MaaS) setting to provide only the inference APIs for users . they argue that input-side adaptation could be arduous due to the lack of gradient signals .
Outcome:	The proposed model outperforms state-of-the-art algorithms with a 200x speed-up.

Copied to clipboard

Yafu Li, Zhilin Wang, Leyang Cui, Wei Bi, Shuming Shi, Yue Zhang

History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System (2022.findings-emnlp)

Challenge:	Existing work focuses on detecting (partially) AI-generated texts, but paraphrasing is commonly employed in various application scenarios for text refinement and diversity.
Approach:	They propose a framework for paraphrased text span detection that takes in the full text and assigns each sentence with a score indicating the paraphrasing degree.
Outcome:	The proposed framework can detect paraphrased text spans within a text . it takes in the full text and assigns each sentence with a score indicating the paraphrasing degree.

Copied to clipboard

Tong Zhang, Yong Liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui

C3KG: A Chinese Commonsense Conversation Knowledge Graph (2022.findings-acl)

Challenge:	Existing open-domain dialogue systems conduct one-session conversations, but multi-session MSCs are under-investigated.
Approach:	They propose a History-Aware Hierarchical Transformer for multi-session open-domain dialogue . they propose to encode history conversations into a history memory and leverage historical information to generate well-informed responses.
Outcome:	The proposed model outperforms baseline models on a large-scale MSC dataset.

Copied to clipboard

Dawei Li, Yanran Li, Jiayi Zhang, Ke Li, Chen Wei, Jianwei Cui, Bin Wang

Natural Language Interfaces

Challenge:	Existing commonsense knowledge bases organize tuples in an isolated manner, causing problems for chatbots .
Approach:	They create a Chinese commonsense conversation knowledge graph which integrates social commonsensm and dialog flow information.
Outcome:	The proposed graph incorporates social commonsense knowledge and dialog flow information.

UniGeM: Unifying Data Selection and Mixing via Geometric Exploration and Mining (2026.findings-acl)

Copied to clipboard

Changhao Wang, null Yunfeiyu, Xinhao Yao, Jiaolong Yang, Lu Yu, Junpeng Fang, Chaobo Li, Riccardo Cantoro, Qing Cui, Jun Zhou

Challenge:	Large Language Models (LLMs) scaling is limited by data quality and domain mixing and instance selection are two separate problems.
Approach:	They propose a framework that unifies mixing and selection without training proxy models or relying on external reference datasets.
Outcome:	The proposed framework achieves 2.0 data efficiency over a random baseline and further improves overall performance compared to SOTA methods in reasoning-heavy evaluations and multilingual generalization.

Aspect-Category Enhanced Learning with a Neural Coherence Model for Implicit Sentiment Analysis (2023.findings-emnlp)

Copied to clipboard

Jin Cui, Fumiyo Fukumoto, Xinfeng Wang, Yoshimi Suzuki, Jiyi Li, Wanzeng Kong

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) is a major research topic in NLP since social networking services have increased . but the recognition of implicit sentiments that do not contain obvious opinion words remains unexplored . elcom captures document-level coherence by using contrastive learning and sentence-level by a hypergraph .
Approach:	They propose aspect-category enhanced learning with a neural coherence model . it captures document-level coherency by contrastive learning and sentence-level by a hypergraph .
Outcome:	The proposed model captures document-level coherence by using contrastive learning and sentence-level by a hypergraph to mine opinions from explicit sentences to aid implicit sentiment classification.

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers (2024.acl-long)

Copied to clipboard

Qintong Li, Leyang Cui, Xueliang Zhao, Lingpeng Kong, Wei Bi

GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated impressive performance across various mathematical reasoning benchmarks.
Approach:	They introduce an adversarial grade school math dataset and explore whether LLMs can be more robust when questions are slightly changed.
Outcome:	The proposed method generates and verifies each intermediate thought based on its reasoning goal and calculation result.

Copied to clipboard

Shaoting Tan, Ning Liu, Yuntao Du, Shuyue Wei, Wu Shuai, Qian Li, Yanyu Xu, Wei Zhang, Lizhen Cui, Haitao Yuan

How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective (2024.emnlp-main)

Challenge:	Existing Large Language Models struggle to reason systematically under cost constraints . Existing approaches lack the knowledge-reasoning capability to reason under cost .
Approach:	They propose a knowledge-enhanced framework that leverages large language models to construct MDKGs . they propose three collaborative agents that handle language understanding and generation .
Outcome:	GraphDx improves diagnostic success rates from 50–68% to 79–93% while reducing test costs by 20–54%.

Copied to clipboard

Teng Xiao, Mingxiao Li, Yige Yuan, Huaisheng Zhu, Chao Cui, Vasant Honavar

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Challenge:	Existing methods for fine-tuning large language models are not suitable for task-dependent tasks.
Approach:	They propose a generalized self-imitation learning framework which aligns large language models with offline demonstration data.
Outcome:	The proposed framework outperforms baselines in many challenging benchmarks . it is available on github.com/tengxiao1/GSIL .

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

Sinkhorn Distance Minimization for Knowledge Distillation (2024.lrec-main)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan Xu, Tong Wu, Ke Li, Xing Sun, Wengang Zhou, Houqiang Li

DocBank: A Benchmark Dataset for Document Layout Analysis (2020.coling-main)

Challenge:	Existing knowledge distillation methods investigate divergence measures but fail to deliver effective supervision when few distribution overlap exists between teacher and student.
Approach:	They propose a knowledge distillation method that exploits the Sinkhorn distance to ensure a nuanced assessment of the disparity between teacher and student distributions.
Outcome:	The proposed method outperforms state-of-the-art methods on all kinds of LLMs with encoder-only, encoder decoder, and decoded architectures.

Copied to clipboard

Minghao Li, Yiheng Xu, Lei Cui, Shaohan Huang, Furu Wei, Zhoujun Li, Ming Zhou

Challenge:	Existing approaches for document layout analysis are based on rule-based or machine learning methods that ignore textual information.
Approach:	They present a benchmark document layout analysis dataset using a computer vision model . they build strong baselines and manually split train/dev/test sets for evaluation .
Outcome:	The proposed model trains on DocBank accurately recognize layout information for a variety of documents.

CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code Representation (2025.findings-acl)

Copied to clipboard

Jiayuan Li, Lei Cui, Sen Zhao, Yun Yang, Lun Li, Hongsong Zhu

Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction (2021.acl-long)

Challenge:	Existing methods for detecting code capture the overall semantics of the code rather than its intrinsic vulnerability-specific semantics.
Approach:	They propose an approach that leverages contrastive learning to generate precise vulnerability code representations under the supervision of vulnerability descriptions.
Outcome:	The proposed approach outperforms state-of-the-art methods in vulnerability detection tasks by 11.85% and 13.61%.

Copied to clipboard

Li Cui, Deqing Yang, Jiaxin Yu, Chengwei Hu, Jiayang Cheng, Jingjie Yi, Yanghua Xiao

Information Extraction & Text Mining

Challenge:	Existing methods to extract relationships from texts depend on memory size and replay these memorized samples in subsequent tasks.
Approach:	They propose to use a model to extract relations between entities from texts where the samples of different relations are delivered into the model continuously.
Outcome:	The proposed model outperforms the state-of-the-art models and avoids catastrophic forgetting.

A Span-Extraction Dataset for Chinese Machine Reading Comprehension (D19-1)

Copied to clipboard

Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu

Machine Reading Comprehension

Challenge:	Existing reading comprehension datasets are mostly in English . MRC is a new field of research that aims to comprehend the context of articles and answer the questions based on them.
Approach:	They propose a Span-Extraction dataset for Chinese machine reading comprehension to add language diversities to existing reading comprehension datasets.
Outcome:	The proposed dataset is composed of 20,000 real questions annotated on Wikipedia paragraphs by human experts.

Deep Attentive Sentence Ordering Network (D18-1)

Copied to clipboard

Baiyun Cui, Yingming Li, Ming Chen, Zhongfei Zhang

Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation (2022.naacl-main)

Challenge:	Existing methods for sentence ordering tasks rely on linguistic knowledge and are domain specific.
Approach:	They propose a deep attentive sentence ordering network which integrates self-attention mechanism with LSTMs in the encoding of input sentences.
Outcome:	The proposed model outperforms the state-of-the-art models on Sentence Ordering and Order Discrimination tasks and is shown to be highly efficient.

Copied to clipboard

Guangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang, Junwei Bao, Zhen Li, Xiaodong He, Shuguang Cui, Zhiting Hu

Context-Sensitive Generation of Open-Domain Conversational Responses (C18-1)

Challenge:	Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss.
Approach:	They propose an Edit-Invariant Sequence Loss method which computes the matching loss of a target sequence with all n-grams in the generated sequence.
Outcome:	The proposed method outperforms the common CE loss and strong baselines on a wide range of tasks.

Copied to clipboard

Weinan Zhang, Yiming Cui, Yifa Wang, Qingfu Zhu, Lingzhi Li, Lianqiang Zhou, Ting Liu

MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark (2025.acl-long)

Challenge:	Existing studies on single-turn conversation generation focus on coherence and context-sensitive generation of open-domain conversational responses.
Approach:	They propose static and dynamic attention based approaches for context-sensitive generation of open-domain conversational responses.
Outcome:	The proposed model outperforms all baselines on automatic and human evaluation on two public datasets.

Copied to clipboard

Qihao Zhao, Yangyu Huang, Tengchao Lv, Lei Cui, Qinzheng Sun, Shaoguang Mao, Xin Zhang, Ying Xin, Qiufeng Yin, Scarlett Li, Furu Wei

LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation (2022.emnlp-main)

Challenge:	Multiple-choice question datasets like Massive Multitask Language Understanding (MMLU) have inevitably led to benchmark contamination, resulting in unreliable evaluation.
Approach:	They propose a contamination-free MCQ benchmark called MMLU-CF which reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination.
Outcome:	The proposed MMLU-CF reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination.

Copied to clipboard

Hongcheng Guo, Jiaheng Liu, Haoyang Huang, Jian Yang, Zhoujun Li, Dongdong Zhang, Zheng Cui

Multilinguality

Challenge:	Recent advances struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases in the real world.
Approach:	They propose to train different MMT models to support translations between different languages.
Outcome:	The proposed model is able to handle the above issues by providing a shared semantic space for multiple languages.

MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models (2026.findings-acl)

Copied to clipboard

Zhang He, Wenqian Cui, Haoning Xu, Xiao-Hui Li, Lei Zhu, Haoli Bai, Ma Shaohua, Irwin King

Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory (2026.acl-long)

Challenge:	Existing benchmarks focus on evaluating single-round interactions, neglecting other critical aspects.
Approach:	They propose a benchmark to evaluate full-duplex speech language models in multi-round settings . they segment continuous full-dual dialogues into discrete turns for evaluation .
Outcome:	The proposed benchmark compared full-duplex speech language models with full-dual speech models . the results show that the models perform better in multi-round settings than standard models compared to benchmarks .

Copied to clipboard

Shiqi He, Yue Cui, Xinyu Ma, Yaliang Li, Bolin Ding, Mosharaf Chowdhury

MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking (2023.findings-acl)

Challenge:	Existing methods for embodied reasoning are coarse-grained and expensive . branch-and-browse framework enables fine-grounded, memory-guided, and efficient multi-branch reasoning.
Approach:	They propose a framework that unifies structured reasoning-acting, contextual memory, and efficient execution.
Outcome:	The proposed framework achieves task success rate of 35.8% and reduces execution time by up to 40.4% relative to state-of-the-art methods.

Copied to clipboard

Haoning Zhang, Junwei Bao, Haipeng Sun, Youzheng Wu, Wenye Li, Shuguang Cui, Xiaodong He

FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting (2026.findings-acl)

Challenge:	Experimental results show that MoNET outperforms previous DST methods in alleviating state momentum issues and improving the anti-noise ability.
Approach:	They propose to use previous state of each turn in training data as input to learn to predict current state.
Outcome:	The proposed model outperforms existing methods on multiWOZ datasets and shows that it can update and correct slot values and improve anti-noise ability.

Copied to clipboard

Fengxian Ji, Jingpu Yang, Zirui Song, Yuanxi Wang, Zhexuan Cui, Yuke Li, Qian Jiang, Xiuying Chen

UltraIF: Advancing Instruction Following from the Wild (2025.emnlp-main)

Challenge:	FineState-Bench evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state.
Approach:	They propose a benchmark that evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state.
Outcome:	The proposed benchmark evaluates whether an agent can ground an instruction to the intended UI control and reach the exact target state.

Copied to clipboard

Kaikai An, Li Sheng, Ganqu Cui, Shuzheng Si, Ning Ding, Yu Cheng, Baobao Chang

Heuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A Survey (2025.findings-acl)

Challenge:	a lack of transparency has resulted in a gap between research community and leading companies . large language models have demonstrated remarkable capabilities in following complex instructions .
Approach:	They propose a method to build large language models that can follow complex instructions with open-source data.
Outcome:	The proposed approach can synergize complex instructions and filter responses with evaluation questions.

Copied to clipboard

Wendi Cui, Jiaxin Zhang, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika Das, Bradley A. Malin, Sricharan Kumar

Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data (2025.findings-naacl)

Challenge:	Recent advances in Large Language Models (LLMs) have led to remarkable achievements across a variety of NLP tasks.
Approach:	They propose a taxonomy of automatic prompt optimization methods that explore and improve prompts with minimal human oversight.
Outcome:	The proposed methods can explore and improve prompts with minimal human oversight.

Copied to clipboard

Juanhui Li, Sreyashi Nag, Hui Liu, Xianfeng Tang, Sheikh Muhammad Sarwar, Limeng Cui, Hansu Gu, Suhang Wang, Qi He, Jiliang Tang

UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces (2025.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated superior language understanding abilities in many real-world NLP applications.
Approach:	They propose a learning-based sample selection method that incorporates signals from both teacher and student to enhance model performance.
Outcome:	The proposed method improves model performance across datasets with higher data efficiency.

Copied to clipboard

Baining Zhao, Jianjie Fang, Zichao Dai, Ziyou Wang, Jirong Zha, Weichen Zhang, Chen Gao, Yue Wang, Jinqiang Cui, Xinlei Chen, Yong Li

Effidit: An Assistant for Improving Writing Efficiency (2023.acl-demo)

Challenge:	Large multimodal models exhibit remarkable intelligence, yet their embodied cognitive abilities during motion in open-ended urban aerial spaces remain to be explored.
Approach:	They propose a benchmark to evaluate whether large multimodal models can process continuous first-person visual observations like humans.
Outcome:	The proposed model can process first-person visual observations like humans, enabling recall, perception, reasoning, and navigation.

Copied to clipboard

Shuming Shi, Enbo Zhao, Wei Bi, Deng Cai, Leyang Cui, Xinting Huang, Haiyun Jiang, Duyu Tang, Kaiqiang Song, Longyue Wang, Chenyan Huang, Guoping Huang, Yan Wang, Piji Li

Green & Sustainable NLP

Challenge:	Effidit is a digital writing assistant that provides three modules to help users write faster and more efficiently.
Approach:	They present Effidit, a digital writing assistant that provides three modules to help users write higher-quality text more efficiently.
Outcome:	Effidit expands the capabilities of a typical writing assistant by providing three modules . Effit can help users create their own text faster and more efficiently .

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)

Copied to clipboard

Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song

Retrieval Heads are Dynamic (2026.acl-long)

Challenge:	Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges .
Approach:	They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions.
Outcome:	The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset .

Copied to clipboard

Yuping Lin, Zitao Li, Yue Xing, Pengfei He, Yingqian Cui, Yaliang Li, Bolin Ding, Jingren Zhou, Jiliang Tang

Information Retrieval

Challenge:	Recent studies have identified "retrieval heads" in Large Language Models responsible for extracting information from input contexts.
Approach:	They propose to examine retrieval heads from a dynamic perspective . they establish that retrieval head activation is highly dynamic and functionally irreplaceable .
Outcome:	The proposed model's hidden state encodes a predictive signal for future retrieval head patterns, indicating an internal planning mechanism.

Multilingual Collaborative Defense for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Hongliang Li, Jinan Xu, Gengping Cui, Changhao Guan, Fengran Mo, Kaiyu Huang

Boosting LLM’s Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning (2025.acl-long)

Challenge:	Existing safeguards for Large Language Models are vulnerable to "jailbreaking" harmful queries.
Approach:	They propose a learning method that optimizes a continuous soft safety prompt automatically to facilitate multilingual safeguarding of LLMs.
Outcome:	The proposed method outperforms previous approaches in multilingual jailbreak defense while exhibiting strong cross-lingual generalization.

Copied to clipboard

Xiang Zhuang, Bin Wu, Jiyu Cui, Kehua Feng, Xiaotong Li, Huabin Xing, Keyan Ding, Qiang Zhang, Huajun Chen

FoldMoE: Efficient Long Sequence MoE Training via Attention-MoE Pipelining (2025.acl-long)

Challenge:	Molecular structure elucidation involves deducing a molecule’s structure from various types of spectral data, which is crucial in chemical experimental analysis.
Approach:	They propose a Knowledge-enhanced reasoning framework for Molecular Structure Elucidation that leverages Monte Carlo Tree Search for test-time scaling as a plugin to extend the LLMs’ coverage of the chemical structure space.
Outcome:	The proposed framework significantly improves on both GPT-4o-mini and GPT4o, and a specialized molecule-spectrum scorer improves performance.

Copied to clipboard

Guichao Zhu, Lintian Lei, Yuhao Qing, Yichao Fu, Fanxin Li, Dong Huang, Zekai Sun, Heming Cui

Green & Sustainable NLP

Challenge:	Existing approaches to training LLMs with Mixture-of-Experts (MoE) architecture on long sequences are limited by the insufficient computation.
Approach:	They propose a MoE training system that enables token-level overlapping across entire Transformer blocks through novel attention-MoE pipelining.
Outcome:	The proposed system achieves 1.49x and 2.72x speedup over state-of-the-art token-level overlapping and non-overlapping baselines on GPT-MoE models with sequences up to 32K tokens.

Explicit Syntactic Guidance for Neural Text Generation (2023.acl-long)

Copied to clipboard

Yafu Li, Leyang Cui, Jianhao Yan, Yongjing Yin, Wei Bi, Shuming Shi, Yue Zhang

Syntactic Text Processing

Challenge:	Existing text generation models follow the sequence-to-sequence paradigm . generative grammar suggests humans generate language by learning language grammar .
Approach:	They propose a syntax-guided generation schema that searches the syntax tree in a top-down direction.
Outcome:	The proposed method outperforms autoregressive baselines on paraphrase generation and machine translation.

MAGE: Machine-generated Text Detection in the Wild (2024.acl-long)

Copied to clipboard

Yafu Li, Qintong Li, Leyang Cui, Wei Bi, Zhilin Wang, Longyue Wang, Linyi Yang, Shuming Shi, Yue Zhang

Fast and Accurate Neural Machine Translation with Translation Memory (2021.acl-long)

Challenge:	Existing research has focused on evaluating detection methods for specific domains or language models.
Approach:	They build a testbed to detect texts from diverse human writings and LLMs using different detection methods.
Outcome:	Empirical results show that the top performing detector can identify 84.12% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.

Copied to clipboard

Qiuxiang He, Guoping Huang, Qu Cui, Li Li, Lemao Liu

Machine Translation

Challenge:	Existing knowledge demonstrates the superiority of TM-based neural machine translation only on TM specialized tasks .
Approach:	They propose a translation memory-based approach to machine translation using a single bilingual sentence as its TM.
Outcome:	The proposed approach surpasses baselines on two general tasks and improves on the TM-specialized translation tasks.

Explanation Graph Generation via Generative Pre-training over Synthetic Graphs (2023.findings-acl)

Copied to clipboard

Han Cui, Shangzhan Li, Yu Zhang, Qi Shi

Cross-lingual Contextualized Phrase Retrieval (2024.findings-emnlp)

Challenge:	Existing frameworks for explanation graph generation are limited due to the large number of datasets available.
Approach:	They propose a text-to-graph generative task to pre-train a model to bridge the text-graph gap.
Outcome:	The proposed framework surpasses all baseline systems with remarkable margins on ExplaGraphs and CommonsenseQA.

Copied to clipboard

Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe

Multilinguality

Challenge:	Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks.
Approach:	They propose a task formulation of dense retrieval, cross-lingual contextualized phrase retrieval . they extract pairs of cross-linguistic phrases using word alignment information .
Outcome:	The proposed task formulation surpasses baselines on the phrase retrieval task and a downstream task, i.e., machine translation, and achieves top-1 accuracy 13 points higher.

CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory (2025.acl-long)

Copied to clipboard

Weichen Zhang, Chen Gao, Shiquan Yu, Ruiying Peng, Baining Zhao, Qian Zhang, Jinqiang Cui, Xinlei Chen, Yong Li

Towards Statistical Factuality Guarantee for Large Vision-Language Models (2025.emnlp-main)

Challenge:	Existing ground VLN agents struggle in aerial VLLN due to the lack of predefined navigation graphs and the exponentially expanding action space in long-horizon exploration.
Approach:	They propose a large language model-empowered aerial VLN agent that decomposes the long-horizon task into sub-goals with different semantic levels.
Outcome:	The proposed method achieves state-of-the-art performance with significant improvement in continuous city environments.

Copied to clipboard

Zhuohang Li, Chao Yan, Nicholas J Jackson, Wendi Cui, Bo Li, Jiaxin Zhang, Bradley A. Malin

Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs (2025.emnlp-main)

Challenge:	Advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive performance in image-conditioned text generation, but hallucinated outputs pose a major barrier to their use in safety-critical applications.
Approach:	They propose a conformal-prediction-based framework that achieves finite-sample distribution-free statistical guarantees to the factuality of LVLM output.
Outcome:	The proposed framework reduces the error rate of LLaVa-1.5 claims from 87.8% to 10.0% while ensuring that the output is accurate.

Copied to clipboard

Dingdong Wang, Junan Li, Mingyu Cui, Dongchao Yang, Xueyuan Chen, Helen M. Meng

SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization (2025.acl-long)

Challenge:	Speech Large Language Models (SpeechLLMs) have emerged as dominant speech processing approaches.
Approach:	They compare self-supervised learning-based discrete and continuous features . they compare performance across six spoken language understanding-related tasks .
Outcome:	The proposed models outperform discrete tokens and continuous features in six spoken language understanding-related tasks.

Copied to clipboard

Wendi Cui, Jiaxin Zhang, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika Das, Bradley A. Malin, Sricharan Kumar

MarkupLM: Pre-training of Text and Markup Language for Visually Rich Document Understanding (2022.acl-long)

Challenge:	Existing approaches separate the optimization of prompt instructions and in-context learning examples, leading to incohesive, suboptimal results.
Approach:	They propose a framework that refines both prompt instructions and in-context learning examples.
Outcome:	The proposed framework outperforms state-of-the-art prompt optimization methods on 35 benchmark tasks.

Copied to clipboard

Junlong Li, Yiheng Xu, Lei Cui, Furu Wei

Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysis (2024.lrec-main)

Challenge:	Existing layout-based pre-training approaches are not easy to apply to VRDU tasks.
Approach:	They propose to use markup languages as the backbone for document understanding tasks where text and markup information are jointly pre-trained.
Outcome:	The proposed model outperforms existing models on document understanding tasks.

Copied to clipboard

Jin Cui, Fumiyo Fukumoto, Xinfeng Wang, Yoshimi Suzuki, Jiyi Li, Noriko Tomuro, Wanzeng Kong

Sentiment Analysis

Challenge:	Aspect-category-based sentiment analysis (ACSA) is a popular approach for identifying aspect categories and predicting their sentiments.
Approach:	They propose an enhanced coherence-aware network with hierarchical disentanglement (ECAN) to capture contexts across the whole review and to help the implicit aspect and sentiment identification.
Outcome:	The proposed network decouples multiple aspects and sentiment features and achieves state-of-the-art (SOTA) performance.

Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs (2025.findings-naacl)

Copied to clipboard

Sen Yang, Xin Li, Leyang Cui, Lidong Bing, Wai Lam

Explainability & Interpretability in NLP

Challenge:	a new framework for complex reasoning with LLMs is developed to improve reasoning proof accuracy and interpretability.
Approach:	They propose to use LLMs to generate search logs that can be interpreted into human-readable reasoning proofs.
Outcome:	The proposed framework improves reasoning accuracy but lacks interpretability due to black-box nature of the solvers.

EviReport: From Reasoned Outlines to Evidence Tracked Long-Form Reports (2026.findings-acl)

Copied to clipboard

Zihan Liu, Jianhui li, Zexin Wang, Fei Sun, Jingjing LI, Zheyuan Li, Ke Xiang, Hang Cui, Houhua Gong, Changhua Pei, Gaogang Xie

CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking (2022.aacl-short)

Challenge:	Evidence-intensive reports often produce fluent but under-supported drafts . eviReport is an evidence-grounded workflow for automated long-form report generation .
Approach:	They propose an evidence-tracked workflow that organizes corpus evidence into compact, traceable units and retrieves query-relevant subgraphs into retrieval-ready packages.
Outcome:	The proposed workflow outperforms baselines in factual coverage, factual accuracy and visual evidence integration.

Copied to clipboard

Haoning Zhang, Junwei Bao, Haipeng Sun, Huaishao Luo, Wenye Li, Shuguang Cui

Low-Resource NLP

Challenge:	Existing few-shot dialogue state tracking (DST) methods transfer knowledge from labeled data into DST, but collecting large amount of labeles is laborious.
Approach:	They propose a few-shot dialogue state tracking framework that integrates self-training and self-supervised learning methods into the framework.
Outcome:	The proposed framework achieves competitive performance in several few-shot scenarios.

EDeR: Towards Understanding Dependency Relations Between Events (2023.emnlp-main)

Copied to clipboard

Ruiqi Li, Patrik Haslum, Leyang Cui

Information Extraction & Text Mining

Challenge:	Existing work on event relation extraction focuses on hierarchical, temporal and causal relations but ignores the interdependence between events.
Approach:	They propose to use a human-annotated Event Dependency Relation dataset to identify event dependency relations between two events.
Outcome:	The proposed dataset integrates existing annotations with the OntoNotes dataset and shows that recognizing such event dependency relations can further benefit critical NLP tasks, including semantic role labelling and co-reference resolution.

OssCSE: Overcoming Surface Structure Bias in Contrastive Learning for Unsupervised Sentence Embedding (2023.emnlp-main)

Copied to clipboard

Zhan Shi, Guoyin Wang, Ke Bai, Jiwei Li, Xiang Li, Qingjun Cui, Belinda Zeng, Trishul Chilimbi, Xiaodan Zhu

Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)

Challenge:	Recent studies show that contrastive learning is effective in sentence representation learning . but, the surface structure bias is a problem in the current model .
Approach:	They propose to combine a sentence with a sub-semantic sentence to investigate the surface structure bias.
Outcome:	The proposed model achieves state-of-the-art on standard semantic textual similarity tasks using different pre-trained backbones.

Copied to clipboard

Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin

Challenge:	e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features.
Approach:	They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent.
Outcome:	The proposed model outperforms baseline models and provides better recall and triage for specialized agents.

The Best of Both Worlds: Combining Parallel and Sequential Inference Scaling via Aggregation Fine-Tuning (2026.findings-acl)

Copied to clipboard

Yafu Li, Zhilin Wang, Tingchen Fu, Ganqu Cui, Sen Yang, Yu Cheng

Descriptive Prompt Paraphrasing for Target-Oriented Multimodal Sentiment Classification (2023.findings-emnlp)

Challenge:	Empirical results show that AFT-trained models achieve substantial gains with test-time scaling.
Approach:	They introduce a supervised fine-tuning paradigm where models synthesize multiple draft responses into a single, refined answer.
Outcome:	Empirical results show that AFT-trained models outperform baseline models while eliminating external guidance.

Copied to clipboard

Dan Liu, Lin Li, Xiaohui Tao, Jian Cui, Qing Xie

Information Retrieval

Challenge:	Current researches mainly work on either of two types of targets in a decentralized manner.
Approach:	They propose a model to perform sentiment polarity on a target jointly considering its corresponding multiple modalities including text, image, and others.
Outcome:	The proposed model performs well on four datasets spanning the above two target types and is prompt-based language modelling.

When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario (2023.findings-acl)

Copied to clipboard

Chengcheng Han, Liqing Cui, Renyu Zhu, Jianing Wang, Nuo Chen, Qiushi Sun, Xiang Li, Ming Gao

Fine-tune BERT with Sparse Self-Attention Mechanism (D19-1)

Challenge:	Large pre-trained language models (PLMs) are expensive and may not be open-sourced due to commercial considerations and potential risks of misuse.
Approach:	They propose to introduce gradient descent into black-box tuning scenario . they propose a method which integrates gradient descent and derivative-free optimization .
Outcome:	The proposed method achieves significant performance gains over previous state-of-the-art methods.

Copied to clipboard

Baiyun Cui, Yingming Li, Ming Chen, Zhongfei Zhang

Misleading Relation Classifiers by Substituting Words in Texts (2023.findings-acl)

Challenge:	Existing sparse self-attention fine-tuning models have been used to improve sentiment analysis, question answering, and natural language inference tasks.
Approach:	They propose a Sparse Self-Attention Fine-tuning model which integrates sparsity into self-attention mechanism to enhance the fine-tune performance of BERT.
Outcome:	The proposed model outperforms the baseline models on sentiment analysis, question answering, and natural language inference tasks and is able to interpret the input better.

Copied to clipboard

Tian Jiang, Yunqi Liu, Yan Feng, Yuqing Li, Xiaohui Cui

Information Extraction & Text Mining

Challenge:	Existing methods to generate adversarial examples for relation classification are vulnerable to adversarials.
Approach:	They propose a method that uses most important parts of speech to substitute words with synonyms or hyponyms to generate adversarial texts of high quality.
Outcome:	The proposed method can generate adversarial texts of high quality and most relationships can be correctly identified in the process of human evaluation.

Divide-Conquer-Reasoning for Consistency Evaluation and Automatic Improvement of Large Language Models (2024.emnlp-industry)

Copied to clipboard

Wendi Cui, Zhuohang Li, Damien Lopez, Kamalika Das, Bradley Malin, Sricharan Kumar, Jiaxin Zhang