Papers by Zhen Zhang

Span-level Aspect-based Sentiment Analysis via Table Filling (2023.acl-long)

Challenge:	Out-of-distribution (OOD) detection is a fundamental task vexing real-world applications . fine-tuning based methods require storing fine- tuned models for each scenario .
Approach:	They propose an unsupervised prefix-tuning based OOD detection framework called PTO . they propose to take advantage of optional training data labels and targeted OOD data .
Outcome:	The proposed framework performs better than existing methods under a wide range of metrics, detection settings, and OOD types.

Copied to clipboard

Mao Zhang, Yongxin Zhu, Zhen Liu, Zhimin Bao, Yunfei Wu, Xing Sun, Linli Xu

Sentiment Analysis

Challenge:	Existing methods to analyze aspect-based sentiment analysis focus on word-level dependencies between aspect and opinion expressions.
Approach:	They propose a span-level ABSA model which considers consistency of multi-word opinion expressions at the span- level.
Outcome:	The proposed model can be used to identify the sentiment polarity of a given aspect . it is based on a table filling method and a regularizer to guarantee consistency .

DMHM: Density-aware Manifold Learning and Hybrid Mahalanobis Energy for LLMs-generated Text Detection (2026.acl-long)

Copied to clipboard

Tianle Liu, Zhiliang Tian, Zhen Huang, Tianlun Liu, Jingyuan Huang, Zhaoning Zhang, Chengcheng Shao, Dongsheng Li

OceanGPT: A Large Language Model for Ocean Science Tasks (2024.acl-long)

Challenge:	Existing methods for LGT detection assume that it is a single homogeneous distribution.
Approach:	They propose a framework for LGT detection based on density-aware manifold learning and hybrid Mahalanobis energy.
Outcome:	The proposed framework outperforms baselines in detecting LLM-generated text (LGT) it is based on density-aware manifold learning and hybrid Mahalanobis energy .

Copied to clipboard

Zhen Bi, Ningyu Zhang, Yida Xue, Yixin Ou, Daxiong Ji, Guozhou Zheng, Huajun Chen

N24News: A New Dataset for Multimodal News Classification (2022.lrec-1)

Challenge:	Recent advances in Large Language Models (LLMs) have transformed the paradigm in ocean science.
Approach:	They propose a framework to automatically obtain large volume of ocean domain instruction data, which generates instructions based on multi-agent collaboration.
Outcome:	The proposed framework shows a higher level of knowledge expertise for ocean science tasks and gains preliminary embodied intelligence capabilities in ocean technology.

Copied to clipboard

Zhen Wang, Xu Shan, Xiangxie Zhang, Jie Yang

CroAno : A Crowd Annotation Platform for Improving Label Consistency of Chinese NER Dataset (2021.emnlp-demo)

Challenge:	Current news datasets focus on text features and rarely leverage the feature of images.
Approach:	They propose a news dataset that uses both images and text to achieve better news classification.
Outcome:	The proposed model improves on the existing dataset N24News with text and image information.

Copied to clipboard

Baoli Zhang, Zhucong Li, Zhen Gan, Yubo Chen, Jing Wan, Kang Liu, Jun Zhao, Shengping Liu, Yafei Shi

Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2026.acl-long)

Challenge:	Existing crowd annotation tools for named entity recognition (NER) focus on efficiency and don't consider consistency of datasets.
Approach:	They propose a crowd annotation platform for Chinese named entity recognition (NER) CroAno provides a systematic solution for improving label consistency of Chinese NER datasets.
Outcome:	The proposed platform improves label consistency of Chinese NER datasets.

Copied to clipboard

Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, Zhiting Hu

AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning (2024.emnlp-main)

Challenge:	closed-ended question-based benchmarks struggle with saturation as newer models emerge . crowd-sourced leaderboards rely on costly and slow human judges .
Approach:	They propose a framework that leverages collective intelligence from all large language models to evaluate each other.
Outcome:	a new framework enables a democratic, pairwise evaluation of all large language models . it achieves 97% correlation with human judgements, while significantly reducing the cost.

Copied to clipboard

Yifan Yang, Kai Zhen, Ershad Banijamali, Athanasios Mouchtaris, Zheng Zhang

FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts (2025.findings-emnlp)

Challenge:	Recent advances in memory-efficient zeroth-order methods have limited their widespread adoption due to performance drops and a high risk of divergence.
Approach:	They propose a memory-efficient zeroth-order framework to improve performance and convergence of the MeZO methods by using only forward passes.
Outcome:	The proposed framework improves performance and convergence of the proposed methods on Roberta-Large and Llama-2-7B models.

Copied to clipboard

Ziyi Zhang, Zhen Sun, Zongmin Zhang, Jihui Guo, Xinlei He

Diversify Question Generation with Continuous Content Selectors and Question Type Modeling (2020.findings-emnlp)

Challenge:	Recent research shows that multimodal large language models are vulnerable to jailbreak attacks .
Approach:	They propose a jailbreak attack method based on auto-generated flowcharts . the flowchartings are then combined with a benign textual prompt to execute the attack .
Outcome:	The proposed method achieves an attack success rate of up to 96% via images and 78% via videos across multiple MLLMs.

Copied to clipboard

Zhen Wang, Siwei Rao, Jie Zhang, Zhen Qin, Guangjian Tian, Jun Wang

Text Generation

Challenge:	Existing methods to generate questions based on answers and relevant contexts are not suitable for all questions .
Approach:	They propose a method to generate questions from a given answer and its relevant context.
Outcome:	The proposed method achieves a better trade-off between generation quality and diversity compared with existing approaches.

Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models (2026.findings-acl)

Copied to clipboard

Zhen Yang, Xinyue Zhang, Ping Jian, Chengzhi Li, Zhongbin Guo, Jiaping Feng, Wenpeng Lu

ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models (2026.findings-acl)

Challenge:	Large Language Models (LLMs) exhibit notable deficiencies in temporal reasoning . phrasing changes can lead LLMs to produce inconsistent outputs .
Approach:	They investigate the mechanistic interpretability of temporal ordering within event temporal reasoning . they identify a sparse subset of attention heads that are causally responsible for reasoning outcomes .
Outcome:	The proposed model outperforms other models in a variety of tasks and is validated by intervention-based experiments.

Copied to clipboard

Zhen Wang, Yuqi Ren, Yuehan Cui, Hongxiang Wang, Jianxiang Peng, Zhaoxia Zhang, Bingkun Zhu, Tongxuan Zhang, Dezhi Tong, Deyi Xiong

Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction (2024.lrec-main)

Challenge:	Existing methods for social simulations mechanically stitch survey responses into prompts, which suffer from semantic fragmentation, failing to capture the internal coherence of human value systems.
Approach:	They propose a framework employing 14 Sociological Expert Agents to interpret World Values Survey responses through structured professional perspectives rather than direct responses concatenation.
Outcome:	Experiments on 480 individuals from 12 countries show that ExpertIVS outperforms baselines in value generalization and significantly outperfies the existing methods.

Copied to clipboard

Yongliang Lin, Zhen Zhang, Mengting Hu, Yufei Sun, Yuzhi Zhang

E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition (2023.findings-acl)

Challenge:	Chinese spelling correction (CSC) aims to detect and correct spelling errors in Chinese texts.
Approach:	They propose a framework that incorporates uncertainty into feature learning and correction stages . they propose to combine the uncertainty of multimodal features with model learning .
Outcome:	The proposed framework improves on three public datasets.

Copied to clipboard

Zhen Zhang, Mengting Hu, Shiwan Zhao, Minlie Huang, Haotian Wang, Lemao Liu, Zhirui Zhang, Zhe Liu, Bingzhe Wu

Wanda++: Pruning Large Language Models via Regional Gradients (2025.findings-acl)

Challenge:	Named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty.
Approach:	They propose to introduce two uncertainty-guided loss terms to the conventional EDL and a series of uncertainty-guiding training strategies to solve these challenges.
Outcome:	The proposed method achieves better OOV/OOD detection performance and generalization ability on OOV entities compared to state-of-the-art methods.

Copied to clipboard

Yifan Yang, Kai Zhen, Bhavana Ganesh, Aram Galstyan, Goeric Huybrechts, Markus Müller, Jonas M. Kübler, Rupak Vignesh Swaminathan, Athanasios Mouchtaris, Sravan Babu Bodapati, Nathan Susanj, Zheng Zhang, Jack FitzGerald, Abhishek Kumar

A Semi-supervised Scalable Unified Framework for E-commerce Query Classification (2025.acl-industry)

Challenge:	Existing pruning methods suffer from accuracy degradation without full-model sparsity-aware fine-tuning.
Approach:	They propose a pruning framework that uses decoder-block-level regional gradients to improve pruning accuracy.
Outcome:	The proposed pruning framework outperforms the state-of-the-art pruning frameworks by utilizing decoder-block-level regional gradients.

Copied to clipboard

Chunyuan Yuan, Chong Zhang, Zhen Fang, Ming Pang, Xue Jiang, Changping Peng, Zhangang Lin, Ching Law

M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis (2023.emnlp-main)

Challenge:	Existing query classification methods rely on posterior click behavior to construct training samples, resulting in insufficient prior information for modeling.
Approach:	They propose a semi-supervised scaleable unified framework that integrates enhanced modules to unify query classification tasks.
Outcome:	The proposed framework outperforms the state-of-the-art models in offline and online A/B experiments.

Copied to clipboard

Fei Zhao, Chunhui Li, Zhen Wu, Yawen Ouyang, Jianbing Zhang, Xinyu Dai

Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain (2024.findings-acl)

Challenge:	Existing work mainly utilizes image information to improve the performance of MABSA task.
Approach:	They propose a multimodal Aspect-based Sentiment Analysis task that uses image information to improve model performance.
Outcome:	The proposed framework outperforms state-of-the-art work on three sub-tasks of MABSA.

Copied to clipboard

Zhen Wan, Yating Zhang, Yexiang Wang, Fei Cheng, Sadao Kurohashi

OpenDelta: A Plug-and-play Library for Parameter-efficient Adaptation of Pre-trained Models (2023.acl-demo)

Challenge:	Recent large language models like GPT-4 have demonstrated astonishing zero-shot capabilities in general domain tasks, but they often generate content with hallucinations in specific domains such as Chinese law.
Approach:	They propose a framework for adapting large language models (LLMs) to Chinese legal domains by reformulating generation as an adapt-retrieve-revise process.
Outcome:	The proposed framework outperforms existing models in the Chinese legal domain by +33.6 points in the zero-shot setting.

Copied to clipboard

Shengding Hu, Ning Ding, Weilin Zhao, Xingtai Lv, Zhen Zhang, Zhiyuan Liu, Maosong Sun

Towards General Agentic Intelligence via Environment Scaling (2026.findings-acl)

Challenge:	Existing implementations that modify the code of the backbone PTMs and hard-code specific delta tuning methods for each PTM have limited the practicality and flexibility of delta tuning.
Approach:	They propose an open-source library that provides a plug-and-play implementation of delta tuning methods for pre-trained models.
Outcome:	The proposed methods eliminate the need to modify the backbone PTMs’ code, making OpenDelta compatible with different, even novel PTM.

Copied to clipboard

Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Ningyu Zhang, Fei Huang, Wentao Zhang, Jingren Zhou

ExploraCoder: Advancing Code Generation for Multiple Unseen APIs via Planning and Chained Exploration (2025.acl-long)

Challenge:	Diverse real-world APIs require precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments.
Approach:	They propose a framework that scales up environments to enable agentic intelligence . they use a two-phase agent fine-tuning strategy to first endow agents with basic agentic capabilities, then specializing them for domain-specific contexts.
Outcome:	Experiments on -bench, -Bench, and ACEBench show that the model significantly enhances the models’ function-calling capability.

Copied to clipboard

Yunkun Wang, Yue Zhang, Zhen Qin, Chen Zhi, Binhua Li, Fei Huang, Yongbin Li, Shuiguang Deng

Programming Languages in NLP

Challenge:	Large language models face intrinsic limitations in coding with unseen APIs in training corpora.
Approach:	They propose a training-free framework that empowers LLMs to invoke multiple unseen APIs in code solution by planning a complex problem into several API invocation subtasks and experimenting with correct API usage at intermediate steps.
Outcome:	The proposed framework significantly improves performance for models lacking prior API knowledge, achieving 11.99% over retrieval-based approaches and 17.28% over pretraining-based methods in pass@10.

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)

Copied to clipboard

Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks.
Approach:	They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes.
Outcome:	The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset.

QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models (2025.emnlp-main)

Copied to clipboard

Jiajun Zhou, Yifan Yang, Kai Zhen, Ziyue Liu, Yequan Zhao, Ershad Banijamali, Athanasios Mouchtaris, Ngai Wong, Zheng Zhang

Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) are quantized to lower precision to reduce memory cost and latency in inference.
Approach:	They propose a quantized zeroth-order framework for fine-tuning Large Language Models (LLMs) using low-precision forward passes.
Outcome:	The proposed method achieves comparable results to first-order methods in FP8 and superior accuracy in INT8 and INT4 training.

Copied to clipboard

Shiji Yang, Shu Zhao, Congyao Mei, Zhen Yang, Jie Chen, Fulan Qian, Zhen Duan, Yanping Zhang

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction (2026.findings-acl)

Challenge:	Existing methods for prompt tuning for Large Language Models find backdoor attacks to be significant in data-rich scenarios.
Approach:	They propose a backdoor attacks through contrastive-enhanced machine unlearning in data-limited scenarios . they use a machine un learning method to capture precise backdoor patterns .
Outcome:	The proposed method captures precise backdoor patterns without association between triggers and backdoors, reducing side effects.

Copied to clipboard

Xu Shen, Qi Zhang, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen

Data-Anonymous Encoding for Text-to-SQL Generation (D19-1)

Challenge:	Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors.
Approach:	They propose a metacognitive framework that enables step-level error detection and self-correction in Large Language Model based multi-agent systems (MAS) .
Outcome:	The proposed framework outperforms baselines on the Who When benchmark and delivers consistent gains on AgentErrorBench.

Copied to clipboard

Zhen Dong, Shizhao Sun, Hongzhi Liu, Jian-Guang Lou, Dongmei Zhang

PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting (2022.findings-naacl)

Challenge:	Existing approaches to handle table-related tokens before the semantic parser are not efficient . existing approaches ignore handling table- related tokens or use deterministic approaches based on string-match or word embedding similarity.
Approach:	They propose a more efficient approach to handle table-related tokens before the parser . they propose tagging a sequential tabbing problem and an implicit supervision approach .
Outcome:	The proposed approach significantly outperforms deterministic approaches.

Copied to clipboard

Zhen Zhang, Wei Zhu, Jinfan Zhang, Peng Wang, Rize Jin, Tae-Sun Chung

StructAM: Enhancing Address Matching through Semantic Understanding of Structure-aware Information (2024.lrec-main)

Challenge:	Pre-trained language models (PLMs) are the state-of-the-art (SOTA) models for natural language processing (NLP).
Approach:	They propose a patient and confident early exiting BERT (PCEE-BERT) that can work with different PLMs and popular model compression methods.
Outcome:	The proposed method outperforms existing models on the GLUE benchmarks and achieves different speed-up ratios.

Copied to clipboard

Zhaoqi Zhang, Pasquale Balsebre, Siqiang Luo, Zhen Hai, Jiangping Huang

Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction (2023.findings-acl)

Challenge:	Existing approaches to address matching rely on string-based similarity matching or manually-designed rules.
Approach:	They propose a method to match unstructured addresses to standard ones in a database using pre-trained language models and graph neural networks.
Outcome:	The proposed method outperforms state-of-the-art methods on real-world addresses . it incorporates spatial coordinates and contextual information from the surrounding area as auxiliary guidance.

Copied to clipboard

Mengting Hu, Yinhao Bai, Yike Wu, Zhen Zhang, Liqi Zhang, Hang Gao, Shiwan Zhao, Minlie Huang

Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation (2025.acl-long)

Challenge:	Existing studies focus on what to generate but ignore what not to generate . a template-agnostic method boosts original learning and reduces mistakes simultaneously .
Approach:	They propose a template-agnostic method to control the token-level generation . they introduce Monte Carlo dropout to understand the built-in uncertainty of pre-trained language models .
Outcome:	The proposed method boosts original learning and reduces mistakes simultaneously on four public datasets.

Copied to clipboard

Guoqiang Gong, Jiaxing Wang, Jin Xu, Deping Xiang, Zicheng Zhang, Leqi Shen, Yifeng Zhang, JunhuaShu JunhuaShu, ZhaolongXing ZhaolongXing, Zhen Chen, Pengzhang Liu, Ke Zhang

Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment (2023.findings-emnlp)

Challenge:	Knowledge distillation (KD) compresses large language models into lightweight versions called student models.
Approach:	They propose to align the entire feature dynamics between teacher and student models by using two additional loss terms to achieve this.
Outcome:	The proposed method matches the entire feature dynamics between teacher and student models rather than just the final states.

Copied to clipboard

Zhen Zhang, Jialu Wang, Xin Wang

Multilinguality

Challenge:	Existing cross-lingual transfer methods that use labeled data and linguistic resources would consume excessive resources for a large number of languages.
Approach:	They propose a parameter-efficient cross-lingual transfer learning framework that utilizes a translation-based alignment method to mitigate multilingual disparities.
Outcome:	The proposed framework reduces disparities among languages and improves cross-lingual transfer results in low-resource scenarios while keeping and fine-tuning only a small number of parameters.

Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales (2025.findings-naacl)

Copied to clipboard

Zhen Qian, Xiuzhen Zhang, Xiaofei Xu, Feng Xia

Multimodal Fusion with Co-Attention Networks for Fake News Detection (2021.findings-acl)

Challenge:	Existing studies focus only on textual quality and numerical accuracy for headline generation.
Approach:	They propose a framework for using rationales of key elements of Topic, Entities, and Numerical reasoning in news articles to enhance LLMs' ability to generate topic-aligned texts with precise numerical accuracy.
Outcome:	The proposed framework improves the ability of large language models to generate high-quality texts with precise numerical accuracy.

Copied to clipboard

Yang Wu, Pengwei Zhan, Yunjian Zhang, Liming Wang, Zhen Xu

DCP: Dual-Cue Pruning for Efficient Large Vision-Language Models (2025.emnlp-main)

Challenge:	Existing methods to detect fake news with textual and visual contents are ineffective because they concatenate unimodal features without considering inter-modality relations.
Approach:	They propose to fuse textual and visual features for fake news detection using multimodal co-attention networks to learn inter-dependencies between multimodal features.
Outcome:	Extensive experiments on two realworld datasets show that the proposed network outperforms state-of-the-art methods and learns inter-dependencies among multimodal features.

Copied to clipboard

Lei Jiang, Zixun Zhang, Yuting Zeng, Chunzhao Xie, Tongxuan Liu, Zhen Li, Lechao Cheng, Xiaohua Xu

EFUF: Efficient Fine-Grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models (2024.emnlp-main)

Challenge:	Existing pruning methods for large vision language models use visual tokens to prune . existing methods fail to balance efficiency and semantic alignment due to large number of visual token.
Approach:	They propose a cross-modal pruning framework that considers textual semantics and visual self-attention to combine them to achieve efficient inference acceleration.
Outcome:	The proposed pruning framework can retain only 25% of the visual tokens, with a minimal performance degradation of only 0.063% on LLaVA-1.5-13B.

Copied to clipboard

Shangyu Xing, Fei Zhao, Zhen Wu, Tuo An, Weihao Chen, Chunhui Li, Jianbing Zhang, Xinyu Dai

Multi-Level Cross-Modal Alignment for Speech Relation Extraction (2024.emnlp-main)

Challenge:	Existing methods to eliminate hallucinations require expensive human annotation . hallucination in multimodal large language models poses unique challenges for current research .
Approach:	They propose a fine-grained unlearning framework that performs gradient ascent to eliminate hallucinations without paired data.
Outcome:	The proposed method reduces hallucinations while preserving quality with modest computational overhead.

Copied to clipboard

Liang Zhang, Zhen Yang, Biao Fu, Ziyao Lu, Liangying Shao, Shiyu Liu, Fandong Meng, Jie Zhou, Xiaoli Wang, Jinsong Su

RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue (2023.acl-long)

Challenge:	Existing studies use synthetic speech to train and evaluate SpeechRE models, hindering their development . modality gap issue limits performance of existing models, limiting future researches .
Approach:	They propose to use speech data to train and evaluate SpeechRE models by using real speech . they propose to train a cross-modal alignment model to bridge the modality gap .
Outcome:	The proposed model can train to bridge the modality gap between speech encoder and text decoder . the proposed model is based on two real SpeechRE datasets .

Copied to clipboard

Zhengliang Shi, Weiwei Sun, Shuo Zhang, Zhen Zhang, Pengjie Ren, Zhaochun Ren

Dialogue Systems & Conversational Agents

Challenge:	Evaluating open-domain dialogue systems is challenging because of the one-to-many problem.
Approach:	They propose a reference-based dialogue evaluation approach that leverages the pre-created utterance as reference other than the gold response to relieve the one-to-many problem.
Outcome:	The proposed method outperforms state-of-the-art evaluation methods on three datasets and two existing benchmarks.

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)

Copied to clipboard

Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention (2026.acl-long)

Challenge:	RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach:	They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome:	The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.

Copied to clipboard

Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, Xin Tao, Ying-Cong Chen

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media (2025.acl-long)

Challenge:	Recent advances in large language models (LLMs) have focused on test-time scaling to improve reasoning quality but at the cost of efficiency.
Approach:	They propose a training-free framework that enhances reasoning accuracy and stability with minimal overhead.
Outcome:	The proposed framework yields consistent gains across general, coding, and STEM tasks while remaining highly efficient.

Copied to clipboard

Zhen Sun, Zongmin Zhang, Xinyue Shen, Ziyi Zhang, Yule Liu, Michael Backes, Yang Zhang, Xinlei He

Text Generation

Challenge:	Social media platforms are experiencing a growing presence of AI-Generated Texts (AIGTs) however, the misuse of AIGTs could have profound implications for public opinion .
Approach:	They collect a dataset with 2.4M posts from 3 major social media platforms . they then construct a diverse dataset to train and evaluate AIGT detectors .
Outcome:	The proposed dataset analyzes 2.4M posts from 3 major social media platforms from 2022 to 2024 . it finds that Medium and Quora show marked increases in AAR .

KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang

LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning (2024.findings-acl)

Challenge:	Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question .
Approach:	They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance .
Outcome:	The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered .

Copied to clipboard

Mingyang Zhang, Hao Chen, Chunhua Shen, Zhen Yang, Linlin Ou, Xinyi Yu, Bohan Zhuang

TRUST: Towards Robust Social Bot Detection via Uncertainty-Guided Pseudo-Labeling and Graph Structure Purification (2026.findings-acl)

Challenge:	Low-rank adaption (LoRA) is a low-level pruning method that can be expensive and slow to deploy.
Approach:	They propose a low-rank adaption pruning framework that provides an accurate structured pruned model in a memory-efficient manner.
Outcome:	The proposed pruning framework reduces perplexity and memory usage by 52.6% on LLaMA and T5 models while reducing memory usage.

Copied to clipboard

Ruixuan Xu, Mengting Hu, Zhunheng Wang, Ming Jiang, Rui Ying, Zhen Zhang, Hang Gao, Shuaipeng Liu, Renhong Cheng

VIDA: A Visual Intent-driven Design Assistant for Proactive Multimodal Clarification (2026.findings-acl)

Challenge:	Existing graph-based detection models are vulnerable to deceptive message propagation, where bots deliberately interact with legitimate users.
Approach:	They propose a framework to mitigate deceptive message propagation by node-level uncertainty estimation and graph structure purification.
Outcome:	The proposed framework improves on three benchmark datasets and six GNN backbones on real-world social bots.

Copied to clipboard

Yanshan Liu, Hongbo Zhang, Zhen Sun, Jiaheng Wei, Kaishun Wu

Active Learning for Abstractive Text Summarization via LLM-Determined Curriculum and Certainty Gain Maximization (2024.findings-emnlp)

Challenge:	Existing vision-language models fail to provide accurate and complete answers to user requests . a new strategy-aware design assistant is developed to help designers create proactive, visually grounded, and strategically prioritized clarification questions.
Approach:	They propose a visual intent-driven design assistant to generate proactive, visually grounded, and strategically prioritized clarification questions.
Outcome:	The proposed assistant improves the strategic alignment score by 20.59% over baselines and restores visual grounding capabilities lost during fine-tuning.

Copied to clipboard

Dongyuan Li, Ying Zhang, Zhen Wang, Shiyin Tan, Satoshi Kosugi, Manabu Okumura

TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understanding (2025.findings-emnlp)

Challenge:	Abstractive text summarization (ATS) requires laborious data annotation and time-consuming model training.
Approach:	They propose a novel active learning framework that asks large language models to rate difficulty of instances and then uses certainty gain maximization to select instances with a distribution that aligns well with the overall distribution.
Outcome:	The proposed framework improves stability, effectiveness, and efficiency of abstractive text summarization backbones.

Copied to clipboard

Kun Zhang, Liqiang Niu, Zhen Cao, Fandong Meng, Jie Zhou

Proactive Human-Machine Conversation with Explicit Conversation Goal (P19-1)

Challenge:	Existing text-rich image understanding benchmarks lack scale and fragmented scenarios . a new full-image structured output format is proposed to enable fine-grained evaluation of perception and reasoning capabilities.
Approach:	They propose a large-scale, multilingual benchmark that includes over 100,000 annotations and 22,000 question-answer pairs.
Outcome:	The proposed framework provides a comprehensive platform for developing and evaluating next-generation multimodal AI systems.

Copied to clipboard

Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian, Haifeng Wang

Natural Language Interfaces

Challenge:	Typical human-machine conversation systems only use utterances and responses as training data, which results in uninformative and inappropriate responses.
Approach:	They propose a dataset where one acts as a conversation leader and the other as 'follower' they establish baseline results on a 270K utterances and 30k dialogues dataset using state-of-the-art models.
Outcome:	The proposed model can generate diverse multi-turn conversations using knowledge from a new dataset .

Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information (2023.findings-emnlp)

Copied to clipboard

Yun Luo, Zhen Yang, Fandong Meng, Yingjie Li, Jie Zhou, Yue Zhang

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)

Challenge:	Argument structure extraction (ASE) aims to identify the discourse structure of arguments within documents.
Approach:	They propose an Efficient Context-aware ASE model that fully exploits contextual information by augmenting modeling capacity and augmenting training data.
Outcome:	The proposed model can extract argumentative discourse structure from documents and reduce reliance on specific words or less informative sentences.

Copied to clipboard

Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong

AIGuard: A Benchmark and Lightweight Detection for E-commerce AIGC Risks (2025.findings-acl)

Challenge:	Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages.
Approach:	They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English.
Outcome:	The proposed model outperforms open-source and Tibetan-focused models on diverse tasks.

Copied to clipboard

Wenhua Zhang, Weicheng Li, Xuanrong Rao, Lixin Zou, Xiangyang Luo, Chubin Zhuang, Yongjie Hong, Zhen Qin, Hengyu Chang, Chenliang Li, Bo Zheng

Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation (2022.naacl-main)

Challenge:	Existing detection methods lack real-world scenarios and corresponding risk datasets . current MLLMs lack knowledge and have limited capability to detect the risk of AIGC content.
Approach:	They propose a benchmark for AIGC risk detection in real-world e-commerce . it includes 253,420 image-text pairs across four critical categories .
Outcome:	The proposed method achieves 9.68% higher recall than leading multimodal models while using only 25% of training resources.

Copied to clipboard

Siyu Lai, Zhen Yang, Fandong Meng, Xue Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners (2024.naacl-long)

Challenge:	Existing approaches to generate adversarial examples for NMT use the meaning-preserving restriction.
Approach:	They propose a new definition for adversarial examples based on the Doubly Round-Trip Translation (DRTT) they introduce masked language models to construct bilingual adversarials based upon DRTT .
Outcome:	The proposed approach significantly improves the robustness of the NMT model on clean and noisy test sets.

Copied to clipboard

Yun Luo, Zhen Yang, Fandong Meng, Yingjie Li, Fang Guo, Qinglin Qi, Jie Zhou, Yue Zhang

LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)

Challenge:	Existing methods for active learning rely on model uncertainty or disagreement to pick unlabeled data, leading to over-confidence in superficial patterns and lack of exploration.
Approach:	They propose to use a bi-directional encoder and a uni-directional decoder to generate and score an explanation for low-resource text classification.
Outcome:	The proposed model improves on 9 strong baselines on six datasets and can generate explanations for its predictions.

Copied to clipboard

Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu

Challenge:	Large language model (LLM) routing assigns each query to the best suitable model from an ensemble.
Approach:	They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation .
Outcome:	The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing.

CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models (2026.findings-acl)

Copied to clipboard

Linggang Kong, Lei Wu, Yunlong Zhang, Xiaofeng Zhong, Wang Zhen, Yongjie Wang, Yao Pan

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Existing classification-based methods capture noise and spurious correlations while overlooking the underlying causal mechanisms.
Approach:	They propose a hallucination detection framework based on structural causal models that captures static and passive signals from internal states and employs counterfactual interventions to disentangle causal reasoning paths from incidental noise.
Outcome:	Experiments on four datasets and three widely used LLMs show that the proposed framework improves AUROC and interpretability.

Copied to clipboard

Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang

Chinese Opinion Role Labeling with Corpus Translation: A Pivot Study (2021.emnlp-main)

Challenge:	Existing methods for hallucination detection depend on internal signals like uncertainty and self-consistency checks to identify unreliable outputs.
Approach:	They propose a retrieval-augmented generation method to enhance hallucination detection by addressing information updating challenges.
Outcome:	The proposed method improves on existing methods with strong generalization capabilities.

Copied to clipboard

Ranran Zhen, Rui Wang, Guohong Fu, Chengguo Lv, Meishan Zhang

Multilinguality

Challenge:	Unlike most of the previous work focusing on the English language, this paper focuses on the Chinese ORL task.
Approach:	They propose to use a standard English MPQA dataset to construct a Chinese ORL dataset and investigate the effectiveness of cross-lingual transfer methods.
Outcome:	The proposed method is able to detect and improve the performance of the proposed method in Chinese.

Constructing Your Model’s Value Distinction: Towards LLM Alignment with Anchor Words Tuning (2025.findings-emnlp)

Copied to clipboard

Zhen Yang, Ping Jian, Chengzhi Li, Chenxu Wang, Xinyue Zhang, Wenpeng Lu

Challenge:	a study of large language models (LLMs) shows that they can generate outputs that are honest, positive, harmless, etc.
Approach:	They propose a method that amplifies logits difference between positive and negative tokens . they propose to use the logits gap to generate positive and positive tokens after alignment .
Outcome:	The proposed method achieves effective alignment, but requires fewer computational resources compared to training-time alignment methods.

WeTS: A Benchmark for Translation Suggestion (2022.emnlp-main)

Copied to clipboard

Zhen Yang, Fandong Meng, Yingxue Zhang, Ernan Li, Jie Zhou

Text Generation

Challenge:	Existing studies focus on overall performance of machine translation but ignore TS performance, authors say . if TS is applied into post-editing, it will reduce the time and cost of post-production.
Approach:	They propose to use a golden corpus annotated by experts to generate a translation suggestion model.
Outcome:	The proposed model improves on the golden corpus annotated by translators on four translation directions.

Advancing the Robustness of Large Language Models through Self-Denoised Smoothing (2024.naacl-short)

Copied to clipboard

Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang

RECAL: Sample-Relation Guided Confidence Calibration over Tabular Data (2023.findings-emnlp)

Challenge:	Existing adversarial attacks can cause LLMs to make wrong predictions on downstream tasks or generate harmful content misaligned with human values.
Approach:	They propose to use randomized smoothing to add noise to the input and then make predictions based on these denoised versions.
Outcome:	The proposed method surpasses existing methods in both empirical and certified robustness in defending against adversarial perturbations for both downstream tasks and human alignments (i.e., jailbreak attacks).

Copied to clipboard

Wang HaoTian, Zhen Zhang, Mengting Hu, Qichao Wang, Liang Chen, Yatao Bian, Bingzhe Wu

Visual Question Decomposition on Multimodal Large Language Models (2024.findings-emnlp)

Challenge:	Various machine learning methods for tabular data lack accurate confidence estimation, which is needed for high-risk sensitive applications such as credit modeling and financial fraud detection.
Approach:	They propose a general post-training confidence calibration framework to calibrate the confidence of current machine learning models by employing graph neural networks to model the relationships between different samples.
Outcome:	The proposed framework improves the confidence estimation on tabular datasets by using graph neural networks to model the relationships between different samples.

Copied to clipboard

Haowei Zhang, Jianzhe Liu, Zhen Han, Shuo Chen, Bailan He, Volker Tresp, Zhiqiang Xu, Jindong Gu

Sign2Vis: Automated Data Visualization from Sign Language (2025.findings-acl)

Challenge:	Existing methods for question decomposition focus on unimodal language models, but question decomposing capability of Multimodal Large Language Models (MLLMs) has yet to be explored.
Approach:	They propose a finetuning dataset and a training objective for selective decomposition to enhance the model's question decomposing capability.
Outcome:	The proposed dataset shows that existing models struggle to produce high-quality sub-questions.

Copied to clipboard

Yao Wan, Yang Wu, Zhen Li, Guobiao Zhang, Hongyu Zhang, Zhou Zhao, Hai Jin, April Wang

Challenge:	Existing methods to translate natural language descriptions into visualization queries focus on spoken languages, not sign languages.
Approach:	They propose a sign language interface that enables the DHH community to engage more fully with data analysis.
Outcome:	The proposed interface can be used by the deaf and hard-of-hearing community.

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)

Copied to clipboard

Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun

Parallel Attention Network with Sequence Matching for Video Grounding (2021.findings-acl)

Challenge:	Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks.
Approach:	They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions.
Outcome:	The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning.

Copied to clipboard

Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Siow Mong Rick Goh

Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference (2025.emnlp-main)

Challenge:	Existing approaches to video grounding are sensitive to quality of proposals and inefficient because all proposal-query pairs are compared.
Approach:	They propose a Parallel Attention Network with Sequence matching to capture selfmodal contexts and cross-modal attentive information between video and text.
Outcome:	The proposed approach is superior to state-of-the-art methods on three datasets.

Copied to clipboard

Zhuo Chen, Xinyu Wang, Yong Jiang, Zhen Zhang, Xinyu Geng, Pengjun Xie, Fei Huang, Kewei Tu

Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats (2026.acl-long)

Challenge:	Existing methods to detect the knowledge boundary of Vision Large Language Models (VLLMs) are expensive and require indiscriminate retrieval to address questions that require real-time information or are knowledge-intensive.
Approach:	They propose a method that fine-tunes a VLLM on an automatically constructed dataset for boundary identification.
Outcome:	The proposed method reduces indiscriminate retrieval while maintaining or improving the performance of a VLLM on an automatically constructed dataset.

Copied to clipboard

Manyi Zhang, Ji-Fu Li, Zhongao Sun, Haoli Bai, Hui-Ling Zhen, Zhenhua Dong, Xianzhi Yu

PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs (2024.findings-acl)

Challenge:	Microscaling Floating-Point (MXFP) is a low-precision format for large language models (LLMs).
Approach:	They conduct systematic evaluations of PTQ under Microscaling Floating-Point (MXFP) . they find that MXFP8 consistently achieves near-lossless performance .
Outcome:	The proposed method achieves near-lossless performance while MXFP4 introduces substantial accuracy degradation and remains challenging.

Copied to clipboard

Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Haorui Wang, Zhen Qin, Feng Han, Jialu Liu, Simon Baumgartner, Michael Bendersky, Chao Zhang

DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models (2024.emnlp-main)

Challenge:	Knowledge distillation (KD) is a technique for transferring expertise from large teacher models to compact student models with reduced memory footprints and inference costs.
Approach:	They propose to transfer knowledge from large teacher models to compact student models by exploiting teacher-student capacity discrepancies to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.
Outcome:	The proposed framework exploits teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.

Copied to clipboard

Ranchi Zhao, Zhen Thai, Yifan Zhang, Shengding Hu, Jie Zhou, Yunqi Ba, Jie Cai, Zhiyuan Liu, Maosong Sun

Addressing Linguistic Bias through a Contrastive Analysis of Academic Writing in the NLP Domain (2023.emnlp-main)

Challenge:	Large Language Models (LLMs) are pre-trained on vast datasets composed of billions of tokens harvested from diverse text sources.
Approach:	They propose a data engineering method to refine the pretraining corpus through data rating, tagging and editing.
Outcome:	The proposed method improves the quality of the pretraining corpus by enhancing 100 billion tokens of the training corpus.

Copied to clipboard

Robert Ridley, Zhen Wu, Jianbing Zhang, Shujian Huang, Xinyu Dai

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration (2025.findings-acl)

Challenge:	a reviewer’s opinion of the nativeness of expression in an academic paper affects the likelihood of it being accepted for publication.
Approach:	They conduct a statistical analysis of paper abstracts from the natural language processing domain to identify how authors from different linguistic backgrounds differ in the lexical, morphological, syntactic and cohesive aspects of their writing.
Outcome:	The results suggest that there is potential for linguistic bias in the domain of natural language processing.

Copied to clipboard

Yang Zhang, Shixin Yang, Chenjia Bai, Fei Wu, Xiu Li, Zhen Wang, Xuelong Li

Green & Sustainable NLP

Challenge:	Existing methods for grounding large language models suffer from inefficient querying . Existing approaches that rely on physical verification or self-reflection suffer from excessive querying.
Approach:	They propose a framework that introduces Reinforced Advantage feedback for efficient self-refinement of plans.
Outcome:	The proposed framework surpasses baselines in success rate and significantly decreases interaction steps of agents and query rounds of LLMs.

Lexical Translation Inconsistency-Aware Document-Level Translation Repair (2023.findings-acl)

Copied to clipboard

Zhen Zhang, Junhui Li, Shimin Tao, Hao Yang

Machine Translation

Challenge:	Experimental results show document-level translation repair improves translation consistency but still suffers from lexical translation inconsistency due to the lack of inter-sentence context.
Approach:	They propose a document-level translation repair model to model translation inconsistency via automatic post-editing.
Outcome:	The proposed model improves translation quality and lexical consistency on document-level translation datasets.

How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study (2026.acl-long)

Copied to clipboard

Zhen Yang, Ping Jian, Zhongbin Guo, Zuming Zhang, Chengzhi Li, Yonghong Deng, Xinyue Zhang, Wenpeng Lu

Explainability & Interpretability in NLP

Challenge:	Existing studies on spatial intelligence from the perspective of visual-spatial intelligence have not explored whether visual intelligence alone is sufficient to endow models with spatial intelligence.
Approach:	They propose to use a linguistic perspective to investigate spatial intelligence from a theoretical perspective.
Outcome:	The proposed model performs poorly on the proposed dataset while human can easily achieve 100% accuracy.

Where CoT Reasoning Commits: Entropy Traces Identify Interpretable Attention Heads (2026.findings-acl)

Copied to clipboard

Tianhe Zhang, Yonghong Deng, Ping Jian, Zhen Yang, Boyang Wang, Xinyue Zhang

CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension (2023.findings-eacl)

Challenge:	a growing body of work suggests a disconnect between the generated rationale and the model's actual choice.
Approach:	They propose a mechanism-aware framework that interprets the evolving "choice state" of attention heads during CoT generation . they identify a set of intervention targets and perform Selective Head Fine-Tuning .
Outcome:	The proposed framework interprets the "choice state" of attention heads during CoT generation . it detects two functional behaviors: Steadfast Heads and Wavering Heads .

Copied to clipboard

Zhi Zhang, Helen Yannakoudakis, Xiantong Zhen, Ekaterina Shutova

Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes (2025.emnlp-main)

Challenge:	Existing frameworks for referring expression comprehension with commonsense knowledge are lacking in the field of multimodal referring .
Approach:	They propose a framework for commonsense knowledge Enhanced Transformers which integrates commonsensible knowledge into representations of objects in an image.
Outcome:	The proposed framework improves on the existing state of the art in referring expression comprehension with commonsense knowledge (CK-Transformer) it achieves 3.14% accuracy over the existing framework.

Copied to clipboard

Qiunan Du, Zhiliang Tian, Zhen Huang, Kailun Bian, Tianlun Liu, Zhaoning Zhang, Xinwang Liu, Feng Liu, Dongsheng Li

Low-Resource NLP

Challenge:	Existing studies on in-context learning (ICL) focus on the selection of individual examples and ignore correlations among examples.
Approach:	They propose a method to capture positive and negative correlations using the determinantal point process . they optimize the method via kernel decomposition-based MLE to fit a constructed pseudo-labeled dataset .
Outcome:	The proposed method outperforms baselines in ICL example selection.

Adaptive Threshold Selective Self-Attention for Chinese NER (2022.coling-1)

Copied to clipboard

Biao Hu, Zhen Huang, Minghao Hu, Ziwen Zhang, Yong Dou

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation (2024.emnlp-demo)

Challenge:	Named entity recognition (NER) is a computationally difficult task in Chinese since there is no natural delimiter between words in sentences.
Approach:	They propose a data-driven Adaptive Threshold Selective Self-Attention mechanism to select the most relevant characters to enhance Transformer architecture for Chinese named entity recognition.
Outcome:	Experiments on four benchmark Chinese NER datasets show the proposed mechanism improves performance.

Copied to clipboard

Xuanwang Zhang, Yun-Ze Song, Yidong Wang, Shuyun Tang, Xinfeng Li, Zhengran Zeng, Zhen Wu, Wei Ye, Wenyuan Xu, Yue Zhang, Xinyu Dai, Shikun Zhang, Qingsong Wen

AutoFigure-Edit: Generating Editable Scientific Illustrations via Reference-Guided Styling (2026.acl-demo)

Challenge:	Existing research on Retrieval Augmented Generation (RAG) does not address the problem of hallucinations and real-time updating of knowledge.
Approach:	They propose a modular open-source library to equip LLMs with external knowledge.
Outcome:	The proposed approach reduces the need for expensive open-source tools and lacks fair comparisons between novel RAG algorithms.

Copied to clipboard

Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li, QiYao Sun, Enhao Gu, Yiran Ding, Ke Sun, Fang Guo, Panzhong Lu, Zhiyuan Ning, Yixuan Weng, Yue Zhang

Green & Sustainable NLP

Challenge:	Existing automated systems for scientific illustrations are limited in editability, stylistic controllability, and efficiency.
Approach:	They propose an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images.
Outcome:	The proposed system generates fully editable scientific illustrations from long-form scientific texts while enabling flexible style adaptation through user-provided reference images.

FCGCL: Fine- and Coarse-Granularity Contrastive Learning for Speech Translation (2022.findings-emnlp)

Copied to clipboard

Hao Zhang, Nianwen Si, Yaqi Chen, Zhen Li, Tong Niu, Xukui Yang, Dan Qu

FocalOrder: Focal Preference Optimization for Reading Order Detection (2026.acl-long)

Challenge:	Existing methods to perform implicit knowledge transfer from machine translation to ST model are difficult because of the task complexity and data scarcity.
Approach:	They recommend a method which conducts explicit knowledge transfer from MT to ST model by fine and coarse granularity contrastive learning.
Outcome:	The proposed method improves the performance of the end-to-end speech translation model on all 8 languages.

Copied to clipboard

Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Liang Jiaen, null Weihuang, Yining Wang, Junnan Zhu

Challenge:	Existing methods for document comprehension rely on uniform supervision, resulting in a performance degradation in the intermediate sections.
Approach:	They propose a framework driven by Focal Preference Optimization to detect reading order in document layouts.
Outcome:	The proposed framework outperforms competing baselines and surpasses large-scale general VLMs.

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)

Copied to clipboard

Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie

Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning (2026.acl-long)

Challenge:	Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach:	They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome:	The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.

Copied to clipboard

Hamed Damirchi, null Imezadelajara, Ehsan Abbasnejad, Afshar Shamsi, Zhen Zhang, Javen Qinfeng Shi

EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models (2024.acl-demos)

Challenge:	Existing explainability methods for Large Language Models treat hidden states as static points in activation space, but they are saturated with polysemantic features.
Approach:	They propose a framework that shifts analysis from static activations to layer-wise geometric displacement.
Outcome:	The proposed framework outperforms existing explainability methods on commonsense reasoning, question answering, and toxicity detection benchmarks.

Copied to clipboard

Yixin Ou, Ningyu Zhang, Honghao Gui, Ziwen Xu, Shuofei Qiao, Runnan Fang, Lei Li, Zhen Bi, Guozhou Zheng, Huajun Chen

Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings (2025.acl-long)

Challenge:	Large Language Models (LLMs) have improved performance across tasks and domains . instruction tuning is a crucial technique to enhance the capabilities of LLMs - but there is no standard open-source instruction processing framework available for the community .
Approach:	They propose an open-source instruction tuning framework for Large Language Models that modularizes instruction generation, selection, prompting and their combination and interaction.
Outcome:	The proposed framework is open-source and available on Github.

Copied to clipboard

Chenghao Sun, Zhen Huang, Yonggang Zhang, Le Lu, Houqiang Li, Xinmei Tian, Xu Shen, Jieping Ye

Bringing Pedagogy into Focus: Evaluating Virtual Teaching Assistants’ Question-Answering in Asynchronous Learning Environments (2025.findings-emnlp)

Challenge:	Large language models excel at downstream NLP tasks through in-context learning . however, the internal mechanisms behind ICL remain under-explored .
Approach:	They propose a PC patching approach to identify modules where input-label mappings function . they observe and verify that key heads utilize input-labeled mappings to generate target labels for new queries.
Outcome:	The proposed approach detects modules where input-label mappings function . it also detects that key heads use the mappings to generate labels for new queries .

Copied to clipboard

Li Siyan, Zhen Xu, Vethavikashini Chithrra Raghuram, Xuanming Zhang, Renzhe Yu, Zhou Yu

Natural Language Interfaces

Challenge:	Existing assessments rely on surface-level metrics and lack sufficient grounding in educational theory . a new framework is proposed to evaluate VTAs in asynchronous learning environments .
Approach:	They propose a pedagogically-oriented evaluation framework tailored to asynchronous forum discussions . they construct classifiers using expert annotations of VTA responses on a diverse set of forum posts .
Outcome:	The proposed evaluation framework is rooted in learning sciences and tailored to asynchronous forum discussions.

Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Ryan Solgi, Kai Zhen, Rupak Vignesh Swaminathan, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang

Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA (2026.acl-long)

Challenge:	Low-rank tensor compression techniques are used for over-parameterized neural networks, but their applications to compress pre-trained LLMs for downstream tasks remain challenging due to the high-rank nature of pre-training data.
Approach:	They propose sparse augmented tensor networks to enhance low-rank tenorized LLMs . they also propose a framework that enables full model compression .
Outcome:	The proposed framework improves accuracy and efficiency in tensorized language models.

Copied to clipboard

Minghan Zhang, Zhen Yang, Haodong Zou, Jie Chen, Zhen Duan, Shu Zhao

MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models (2025.emnlp-main)

Challenge:	Existing knowledge base question answering methods are limited by syntactic constraints and are prone to structural deviations that render queries unexecutable.
Approach:	They propose a framework that reframes semantic parsing as an iterative reasoning process driven by execution feedback.
Outcome:	The proposed method achieves significant improvements in query executability and answer accuracy on the WebQSP and CWQ datasets.

Copied to clipboard

Zhen Zhang, Yifan Yang, Kai Zhen, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang

Towards a Unified Framework for Reference Retrieval and Related Work Generation (2023.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated exceptional capabilities across diverse tasks, but their fine-tuning requires significant memory, posing challenges for resource-constrained environments.
Approach:	They propose a ZO-based framework that eliminates the need for backpropagation and provides a memory-efficient alternative to backprograming.
Outcome:	The proposed framework surpasses first-order methods in performance and accuracy.

Copied to clipboard

Zhengliang Shi, Shen Gao, Zhen Zhang, Xiuying Chen, Zhumin Chen, Pengjie Ren, Zhaochun Ren

Trust Within? Seek Beyond? Knowledge Boundary Aware Policy Optimization for Agentic Search (2026.acl-long)

Challenge:	Existing methods for related work generation use human-annotated references as information sources.
Approach:	They propose a model which combines reference retrieval and related work generation processes in a unified framework based on the large language model.
Outcome:	The proposed model outperforms the state-of-the-art models on two wide-applied datasets.

Copied to clipboard

Tao Feng, Xinke Jiang, Xinyan Hu, Yonggang Zhang, Zhen Tao, Wentao Zhang, Boyang Liu, Wenhao Jiang, Chao Wu

PathwiseRAG: Multi-Dimensional Exploration and Integration Framework (2025.emnlp-main)

Challenge:	Existing approaches to augment large language models with external knowledge suffer from a lack of calibration regarding the model’s knowledge boundary.
Approach:	They propose a reinforcement learning framework that explicitly aligns retrieval decisions with quantified knowledge states.
Outcome:	The proposed framework outperforms strong baselines while exhibiting reduced hallucination rates.

Copied to clipboard

Hengrui Zhang, Pin-Siang Huang, Zhen Zhang, Peican Lin, Yao-Ching Yu, Bo Hu, Yulu Du

ECOLA: Enhancing Temporal Knowledge Embeddings with Contextualized Language Representations (2023.findings-acl)

Challenge:	Existing retrieval-augmented generation systems employ rigid retrieval strategies . static retrieval produces knowledge blind spots, missing connections between quantum algorithms and encryption vulnerabilities .
Approach:	PathwiseRAG addresses these challenges through intent-aware strategy selection . it constructs a directed acyclic graph of interconnected sub-problems and explores multiple reasoning trajectories .
Outcome:	The proposed framework achieves higher accuracy and better reliability than current systems.

Copied to clipboard

Zhen Han, Ruotong Liao, Jindong Gu, Yao Zhang, Zifeng Ding, Yujia Gu, Heinz Koeppl, Hinrich Schütze, Volker Tresp

OpenUE: An Open Toolkit of Universal Extraction from Text (2020.emnlp-demos)

Challenge:	Existing enhancement approaches cannot be applied to temporal knowledge graphs (tKGs) existing enhancement approaches assume knowledge embedding is time-independent, whereas entity embedded in tKG models evolves .
Approach:	They propose to use textual data to enhance temporal knowledge embedding by Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations (ECOLA) to evaluate ECOLA, they introduce three new datasets for training and evaluation.
Outcome:	The proposed model significantly improves Hits@1 on the link prediction task.

Copied to clipboard

Ningyu Zhang, Shumin Deng, Zhen Bi, Haiyang Yu, Jiacheng Yang, Mosha Chen, Fei Huang, Wei Zhang, Huajun Chen

Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation (2026.findings-acl)

Challenge:	a large number of natural language processing tasks focus on token-level or sentence-level understandings.
Approach:	They propose an open-source and extensible toolkit for various extraction tasks . they deploy an online demo with restful APIs to support real-time extraction .
Outcome:	The proposed model can be used to extract information from text without training and deployment.

Copied to clipboard

Zhiyao Cui, Chenxu Wang, Shuyue Hu, Yiqun Zhang, Wenqi Shao, Qiaosheng Zhang, Zhen Wang

Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition (2020.coling-main)

Challenge:	Existing approaches to producing presentation slides rely on fixed templates or executable code . Existing methods rely only on predefined templates and emit executable codes .
Approach:	They propose a hierarchical slides generation workflow DeepSlides that organizes slide design tasks without any predefined template or style.
Outcome:	The proposed framework outperforms baseline methods on evaluated metrics and achieves superior performance in human preference evaluations.

Copied to clipboard

Huibin Ruan, Yu Hong, Yang Xu, Zhen Huang, Guodong Zhou, Min Zhang

Challenge:	Existing models for discourse relation recognition use self-attention and interactive-attention mechanisms.
Approach:	They develop a propagative attention learning model using a cross-coupled two-channel network.
Outcome:	The proposed model improves on the baseline models on a Penn Discourse Treebank.

UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets (2025.emnlp-main)

Copied to clipboard

Pengyu Wang, Shaojun Zhou, Chenkun Tan, Xinghao Wang, Wei Huang, Zhen Ye, Zhaowei Li, Botian Jiang, Dong Zhang, Xipeng Qiu

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

Challenge:	Existing datasets address understanding and generation in isolation, limiting the performance of unified vision large language models.
Approach:	They propose a dataset that facilitates mutual enhancement between multimodal understanding and generation.
Outcome:	The proposed framework integrates diverse visual and textual inputs and outputs, enabling comprehensive cross-modal reasoning and precise text-to-image alignment.

Copied to clipboard

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

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

Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning (2024.acl-long)

Copied to clipboard

Yue Yu, Jiaming Shen, Tianqi Liu, Zhen Qin, Jing Nathan Yan, Jialu Liu, Chao Zhang, Michael Bendersky

GraphNarrator: Generating Textual Explanations for Graph Neural Networks (2025.acl-long)

Challenge:	Recent advances in natural language processing (NLP) have witnessed the remarkable capabilities of Large Language Models (LLMs).
Approach:	They propose an Explanation-Aware Soft Ensemble framework to empower in-context learning with Large language models.
Outcome:	The proposed framework can be used to enhance in-context learning on seven natural language understanding tasks and four varying-size LLMs.

Copied to clipboard

Bo Pan, Zhen Xiong, Guanchen Wu, Zheng Zhang, Yifei Zhang, Yuntong Hu, Liang Zhao

Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs (2026.findings-eacl)

Challenge:	Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis.
Approach:	They propose to use a generative language model to map input-output pairs to explanations reflecting the model’s decision-making process to generate a model that generates pseudo-labels that capture the model's decisions from saliency-based explanations.
Outcome:	Extensive experiments show that GraphNarrator produces human-preferred explanations that are faithful, concise, and human-like.

Copied to clipboard

Minghan Zhang, Shu Zhao, Zhen Yang, Hongsheng Wu, Yongxing Lin, Haodong Zou, Jie Chen, Zhen Duan

Knowledge Representation

Challenge:	Existing methods for large language models adopt query-driven iterative reasoning from a local perspective, limiting efficiency and accuracy for complex multi-hop tasks.
Approach:	They propose a multi-view instructed adaptive reasoning of LLM on Knowledge Graphs that allows LLMs to plan, evaluate, and adapt reasoning paths from a global perspective.
Outcome:	The proposed model overcomes the limitations of local exploration by enabling LLMs to plan, evaluate, and adapt reasoning paths from a global perspective.

Distillation Enhanced Generative Retrieval (2024.findings-acl)

Copied to clipboard

Yongqi Li, Zhen Zhang, Wenjie Wang, Liqiang Nie, Wenjie Li, Tat-Seng Chua

Continual Named Entity Recognition without Catastrophic Forgetting (2023.emnlp-main)

Challenge:	Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target.
Approach:	They propose a framework that leverages generative language models to enhance generative retrieval by distillation.
Outcome:	The proposed framework achieves state-of-the-art performance among the generative retrieval methods.

Copied to clipboard

Duzhen Zhang, Wei Cong, Jiahua Dong, Yahan Yu, Xiuyi Chen, Yonggang Zhang, Zhen Fang

Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction (2022.coling-1)

Challenge:	Named Entity Recognition (CNER) is a burgeoning area of research . a new paradigm has ushered NER into a non-entity type at the current step t .
Approach:	They propose a pooled feature distillation loss that skillfully navigates the trade-off between retaining knowledge of old entity types and acquiring new ones.
Outcome:	The proposed method outperforms state-of-the-art approaches on ten CNER settings using three datasets.

Copied to clipboard

Yidong Wang, Hao Wu, Ao Liu, Wenxin Hou, Zhen Wu, Jindong Wang, Takahiro Shinozaki, Manabu Okumura, Yue Zhang

Low-Resource NLP

Challenge:	Existing methods to extract opinion words from sentences are limited due to the expensive annotation process.
Approach:	They propose to exploit massive unlabeled data to reduce distribution shift risk . they propose to use two filters specifically for TOWE to filter noisy data . results indicate superiority of MGCR over current state-of-the-art methods .
Outcome:	The proposed method reduces the risk of distribution shifts by increasing the exposure of the model to varying distribution shift.

Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation (2026.findings-acl)

Copied to clipboard

Zhen Bi, Zhenlin Hu, Xueshu Chen, Mingyang Chen, Cheng Deng, Yida Xue, Zhen Wang, Qing Shen, Ningyu Zhang, Jungang Lou

The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness (2026.acl-long)

Challenge:	Existing data-centric paradigms equate quality with factuality or diversity and ignore the internal logical complexity of training samples.
Approach:	They propose a density-aware re-cognizing optimization strategy that prioritizes high-density logical samples to align training with the model's reasoning boundary.
Outcome:	The proposed metric outperforms existing methods and improves reasoning performance without increasing total data volume.

Copied to clipboard

Yueheng Mao, Min Yu, Gengwang Li, Jianguo Jiang, Gang Li, Meng Zhang, Zhen Xu, Weiqing Huang, Ming Liu

On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration (2026.findings-acl)

Challenge:	Large Language Models (LLMs) often generate overconfident yet factually incorrect hallucinations.
Approach:	They propose a black-box-based framework that captures stubborn hallucinations by integrating internal geometric dynamics with output probability distributions.
Outcome:	The proposed framework outperforms white-box methods and reduces computational overhead by over 90%.

Copied to clipboard

Huaisheng Zhu, MingYu Liu, Junze Liu, Zhen Ge, Tian Wang, Jiri Gesi, Dakuo Wang, Weiqi Zhang, Houyu Zhang, Yufan Guo, Xian Li, Bing Yin, Sujay Sanghavi

TSAM: A Two-Stream Attention Model for Causal Emotion Entailment (2022.coling-1)

Challenge:	Recent studies have demonstrated that masked diffusion models (MDMs) can surpass autoregressive models (ARMs) in various tasks.
Approach:	They propose a method to calibrate early token predictions without demonstration data by distilling an unnormalized target distribution into the original model.
Outcome:	Experiments on math, planning, and RLHF tasks show that COPSD improves both effectiveness and efficiency, and further enhances performance when combined with supervised fine-tuning.

Copied to clipboard

Duzhen Zhang, Zhen Yang, Fandong Meng, Xiuyi Chen, Jie Zhou

Natural Language Interfaces

Challenge:	Existing studies on EAC focus on Emotion Recognition in Conversations (ERC), i.e., recognizing emotion labels of utterances.
Approach:	They propose a two-stream attention model to capture correlations between utterances in a global view and classify multiple utterrances synchronously to capture emotion and speaker information in parallel.
Outcome:	The proposed model outperforms baselines and achieves new State-Of-The-Art (SOTA) performance.

Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions (2026.findings-acl)

Copied to clipboard

Zhongbin Guo, Zhen Yang, Yushan Li, Xinyue Zhang, Wenyu Gao, Jiacheng Wang, Chengzhi Li, Xiangrui Liu, Ping Jian

The Adaptive Interrogator: Detecting Trojan LLMs in Multi-Agent Systems via Evolved Conversational Strategies (2026.findings-acl)

Challenge:	Existing advances in Spatial Intelligence rely on vision-Language Models . however, a critical question remains: does spatial understanding originate from visual encoders?
Approach:	They propose to evaluate the SI performance of Large Language Models without pixel-level input.
Outcome:	The proposed benchmark challenges large language models to perform symbolic reasoning rather than visual pattern matching.

Copied to clipboard

Rana Muhammad Shahroz Khan, Ruichen Zhang, Zhen Tan, Charles Fleming, Tianlong Chen

Time-dependent Entity Embedding is not All You Need: A Re-evaluation of Temporal Knowledge Graph Completion Models under a Unified Framework (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) have been focused on single-agent, white-box environments, but multi-agend systems (MAS) have a critical blind spot: supply chain vulnerabilities.
Approach:	They propose a black-box auditing framework that leverages an Evolutionary Algorithm to autonomously expose hidden threats.
Outcome:	The proposed framework achieves superior detection rates (up to 100% in specific configurations) and robustness across diverse architectures.

Copied to clipboard

Zhen Han, Gengyuan Zhang, Yunpu Ma, Volker Tresp