Papers by Zhe Li

SP3: Enhancing Structured Pruning via PCA Projection (2024.findings-acl)

Challenge:	Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach:	They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome:	The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.

Copied to clipboard

Yuxuan Hu, Jing Zhang, Zhe Zhao, Chen Zhao, Xiaodong Chen, Cuiping Li, Hong Chen

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models (2026.findings-eacl)

Challenge:	Structured pruning is a widely used technique for reducing the size of pre-trained language models, but current methods overlook the potential of compressing the hidden dimension d in PLMs.
Approach:	They propose a structured pruning approach that projectes features into a space defined by principal components before masking the hidden dimension d in pre-trained language models.
Outcome:	Experiments on benchmarks show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, and maintain over 96% accuracy.

Copied to clipboard

Wei Zhao, Zhe Li, Yige Li, Jun Sun

DOC-RAG: ASR Language Model Personalization with Domain-Distributed Co-occurrence Retrieval Augmentation (2024.lrec-main)

Challenge:	Despite significant efforts in safety alignment, large language models (LLMs) such as GPT-4 and LLaMA 3 remain vulnerable to jailbreak attacks that can induce harmful behaviors.
Approach:	They propose a feature extraction method to extract sample-agnostic features from benign datasets in the form of adversarial suffixes and propose 'suffix maybe features' they show that adversarials generated from jailbreak attacks may contain meaningful features, i.e. appending the same suffix to different prompts results in responses exhibiting specific characteristics.
Outcome:	The proposed method extracts sample-agnostic features from benign datasets and shows that they may contain meaningful features.

Copied to clipboard

Puneet Mathur, Zhe Liu, Ke Li, Yingyi Ma, Gil Karen, Zeeshan Ahmed, Dinesh Manocha, Xuedong Zhang

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

Challenge:	Extensive experiments on three user-specific speech-to-text tasks show that DOC-RAG significantly outperforms strong baselines with an 8-15% improvement in terms of perplexity and a 4-7% reduction in terms in terms . of Word Error Rates.
Approach:	They propose a domain-distributed co-occurrence augmentation approach to improve automatic speech recognition of rare word patterns in unseen domains by using n-gram co-existence distributions.
Outcome:	Experiments on three user-specific speech-to-text tasks show that DOC-RAG outperforms baselines with an 8-15% improvement in terms of perplexity and a 4-7% reduction in terms in terms . of Word Error Rates.

Copied to clipboard

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

VIVA+: Human-Centered Situational Decision-Making (2025.findings-emnlp)

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

Copied to clipboard

Zhe Hu, Yixiao Ren, Guanzhong Liu, Jing Li, Yu Yin

Reasoning

Challenge:	Multimodal Large Language Models (MLLMs) show promising results in complex, human-centered environments, yet evaluating their capacity for nuanced, humanlike reasoning and decision-making remains challenging.
Approach:	They introduce VIVA+, a cognitively grounded benchmark for evaluating the reasoning and decision-making of MLLMs in human-centered situations.
Outcome:	The VIVA+ model is based on 1,317 real-world situations paired with 6,373 multiple-choice questions . it consists of three core abilities for decision-making: (1) Foundational Situation Comprehension, (2) Context-Driven Action Justification, and (3) Reflective Reasoning.

Improve Vision Language Model Chain-of-thought Reasoning (2025.acl-long)

Copied to clipboard

Ruohong Zhang, Bowen Zhang, Yanghao Li, Haotian Zhang, Zhiqing Sun, Zhe Gan, Yinfei Yang, Ruoming Pang, Yiming Yang

SLARD: A Chinese Superior Legal Article Retrieval Dataset (2025.coling-main)

Challenge:	Current training recipes often rely on datasets dominated by short annotations with limited rationales, hindering the models' ability to generalize to tasks requiring comprehensive reasoning.
Approach:	They propose a two-stage post-training strategy that augments short answers with CoT reasoning generated by GPT-4o, enhancing the VLM's CoT capabilities through fine-tuning.
Outcome:	The proposed strategy enhances the model's CoT capabilities through fine-tuning and reinforcement learning.

Copied to clipboard

Zhe Chen, Pengjie Ren, Fuhui Sun, Xiaoyan Wang, Yujun Li, Siwen Zhao, Tengyi Yang

Information Retrieval

Challenge:	Existing retrieval methods struggle to achieve ideal results, a study finds . existing large language models lack prior knowledge of the content of superior legal articles .
Approach:	They propose to use a Chinese superior legal article retrieval dataset to find relevant articles with higher legal effectiveness.
Outcome:	The proposed dataset shows that existing retrieval methods struggle to achieve ideal results.

OptiCo: Adaptive Distributed Training Optimization via Collaborative Agent Reasoning (2026.acl-long)

Copied to clipboard

Sheng Chen, Tang Zhe, Weixing Zhang, Fei Yang, Yuanyuan. Wang, Tianlin Li, Yang Liu

Reasoning

Challenge:	Existing distributed training frameworks are plagued by over-reliance on prior profiling and poor generalization across models/hardware.
Approach:	They propose a model-driven multi-agent framework that leverages Large Language Models to enable automatic and explainable distributed training strategy configuration.
Outcome:	The proposed framework outperforms expert-designed training strategies within 20 iterations.

LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment (2026.findings-acl)

Copied to clipboard

Shipeng Li, Zhiqin Yang, Shikun Li, Xiaobo Xia, Hengyu Liu, Xinghua Zhang, Gaode Chen, Dong Fang, Ying Tai, Zhe Peng

Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective (2026.findings-acl)

Challenge:	Reinforcement learning with verifiable rewards (RLVR) is a key technique for enhancing LLMs’ reasoning abilities, yet its data inefficiency remains a major bottleneck.
Approach:	They propose a gradient-alignment-based method which intelligently selects the learnable and representative training reasoning data for RLVR post-training.
Outcome:	Experiments on five reasoning benchmarks show that the proposed method significantly reduces training data requirements while improving performance.

Copied to clipboard

Meifang Chen, Zhe Yang, Huang Nianchen, Yizhan Huang, Yichen LI, Zihan Li, Michael R. Lyu

Syntactic Text Processing

Challenge:	Code Large Language Models (CLLMs) are reshaping how software is built, maintained, and evolved.
Approach:	They propose to use BPE tokenization to inadvertently leak code secrets . they propose to mitigate the gibberish bias by using a newer tokenizer .
Outcome:	The proposed model is based on a novel method that can be used to detect and mitigate gibberish bias in CLLMs.

Syllogistic Reasoning for Legal Judgment Analysis (2023.emnlp-main)

Copied to clipboard

Wentao Deng, Jiahuan Pei, Keyi Kong, Zhe Chen, Furu Wei, Yujun Li, Zhaochun Ren, Zhumin Chen, Pengjie Ren

Are AI-Generated Text Detectors Robust to Adversarial Perturbations? (2024.acl-long)

Challenge:	Legal judgment assistants are developing fast due to impressive progress of large language models.
Approach:	They construct and manually correct a syllogistic reasoning dataset for legal judgment analysis using large language models as benchmarks.
Outcome:	The proposed dataset contains 11,239 criminal cases covering 4 criminal elements, 80 charges and 124 articles.

Copied to clipboard

Guanhua Huang, Yuchen Zhang, Zhe Li, Yongjian You, Mingze Wang, Zhouwang Yang

Robustness in NLP

Challenge:	Existing detectors for AI-generated text lack robustness against adversarial perturbations, with even minor changes in characters or words causing a reversal in distinguishing between human-created and AI-generated text.
Approach:	They propose a siamese calibration technique to train the model to make equally confident predictions under different noise, which improves the model’s robustness against adversarial perturbations.
Outcome:	The proposed detector outperforms baseline methods on four datasets and is more generalizable in cross-domain, cross-genre, and mixed-source scenarios.

MMedAgent: Learning to Use Medical Tools with Multi-modal Agent (2024.findings-emnlp)

Copied to clipboard

Binxu Li, Tiankai Yan, Yuanting Pan, Jie Luo, Ruiyang Ji, Jiayuan Ding, Zhe Xu, Shilong Liu, Haoyu Dong, Zihao Lin, Yixin Wang

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

Challenge:	Multi-modal Large Language Models (MLLMs) exhibit limited generality and often fall short when compared to specialized models.
Approach:	They propose a multi-modal medical agent that picks the most suitable medical tools based on user inputs.
Outcome:	The proposed agent performs better than open-source models and the closed-source model, GPT-4o.

Copied to clipboard

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

Programming Languages in NLP

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

DcLM: Output Length Control of Large Language Models via Dynamic Length Markers (2026.findings-acl)

Copied to clipboard

Zhe Chen, Jiaao Yu, Honglin Li

DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)

Challenge:	Large language models (LLMs) have limited awareness of output length, making it difficult to satisfy precise length requirements.
Approach:	They propose a model-agnostic approach that introduces dynamic length markers to guide length-controllable outputs.
Outcome:	The proposed method significantly reduces length deviation across multiple datasets.

Copied to clipboard

Xiaobo Liang, Wanfu Wang, Qipeng Huang, Yuyang Ding, Zecheng Tang, Yixin Ji, Qianben Chen, Zhe Zhao, Kehai Chen, Juntao Li, Min Zhang

Challenge:	Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation.
Approach:	They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward.
Outcome:	The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench.

DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction (2025.emnlp-main)

Copied to clipboard

Yiqi Li, Yusheng Liao, Zhe Chen, Yanfeng Wang, Yu Wang

An Empirical Study of Multimodal Model Merging (2023.findings-emnlp)

Challenge:	Large language models (LLMs) often prioritize reasoning over adherence to detailed instructions due to high computational costs and limited parameter access.
Approach:	They propose a lightweight framework that guides small language models to refine LLMs’ outputs through chain-of-thought correction.
Outcome:	The proposed framework improves the average format accuracy and content correctness of LLM outputs by 35.4% and 29.4%, respectively, achieving state-of-the-art (SOTA) performance over other competitive baselines.

Copied to clipboard

Yi-Lin Sung, Linjie Li, Kevin Lin, Zhe Gan, Mohit Bansal, Lijuan Wang

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities (2023.acl-demo)

Challenge:	Existing studies have shown that model merging can generate a multi-task solution without synchronous training.
Approach:	They propose to merge vision, language, and cross-modal transformers of a modality-specific architecture to create a parameter-efficient architecture.
Outcome:	The proposed model merging outperforms naive models on various tasks with improvements of 3% on VQA, 7% on COCO retrieval, 25% on NLVR2, 14% on Flickr30k and 3% ADE20k.

Copied to clipboard

Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Gou, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan

Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM Inference (2026.findings-acl)

Challenge:	Several pre-training models of different modalities are showing a rising trend of homogeneity in their model structures.
Approach:	They propose a toolkit that supports pre-training models of different modalities.
Outcome:	The proposed toolkit can match the performance of the original implementations on text, vision, and audio benchmarks.

Copied to clipboard

Yang Lyu, Jin Cao, Yang Xiao, Zhe Sun, Ben Niu, Fenghua Li, Hui LI

Theory-optimal Quantization Based on Flatness (2026.acl-long)

Challenge:	Distributed LLMs avoid raw inputs by transmitting intermediate hidden states, a practice widely assumed to preserve privacy.
Approach:	They propose a distributed inference framework that transmits intermediate hidden states to avoid sending raw inputs by exposing sensitive user attributes.
Outcome:	The proposed approach achieves Top-1 accuracy of 0.997 on CMS, 0.980 on Skytrax, and 0.986 on ECHR.

Copied to clipboard

Xiusheng Huang, Zhe Li, Xuanwu Yin, Lu Wang, Yequan Wang, Dong Li, Emad Barsoum, Kang Liu

Linguistic Theories

Challenge:	Recent approaches to quantization of Large Language Models (LLMs) have been widely adopted due to activation outliers, which degrade model performance especially at lower bit precision.
Approach:	They propose a new metric for quantization that strategically distributes outlier magnitudes across matrix dimensions via optimized diagonal operations.
Outcome:	The proposed framework achieves less than 1% accuracy drop in W4A4 quantization on the LLaMA-3-8B model and reduces the performance gap by 39.1% on the more challenging W2A4KV16 model.

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 .

LSDC: An Efficient and Effective Large-Scale Data Compression Method for Supervised Fine-tuning of Large Language Models (2025.findings-naacl)

Copied to clipboard

Zhaoguang Long, Yuhao Zhou, Shangqing Zhao, Yupei Ren, Li Cai, Chenghao Jia, Zhe Chen, Zhe Fang, Yuxiang Song, Man Lan

Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation (2025.coling-main)

Challenge:	Large Language Models (LLMs) are expanding in scale and size, increasing computational costs . large-scale data compression techniques can reduce the size of training datasets while maintaining data integrity.
Approach:	They propose a large-scale data compression method to reduce the size of training data . they use a bifurcated quantization strategy to maximize the diversity of samples .
Outcome:	The proposed method significantly reduces the size of training data while maximizing the submodular gain.

Copied to clipboard

Zhe Hu, Hou Pong Chan, Jing Li, Yu Yin

Challenge:	Writing arguments requires integrating high-level beliefs from various perspectives . current language models generate outputs autoregressively, resulting in limited diversity and coherence .
Approach:	They propose a persona-based multi-agent framework for argument writing that integrates beliefs from different perspectives into a coherent narrative.
Outcome:	The proposed framework generates more diverse arguments by both automatic and human evaluations.

VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values (2024.emnlp-main)

Copied to clipboard

Zhe Hu, Yixiao Ren, Jing Li, Yu Yin

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters (2026.acl-long)

Challenge:	Recent large vision language models (VLMs) have demonstrated remarkable intelligence and proficiency across diverse tasks.
Approach:	They propose a benchmark for VIsion-grounded decision-making driven by human VA.
Outcome:	The proposed model can make decisions under a vision-depicted situation using human values and human values.

Copied to clipboard

Ao Sun, Xiaoyu Wang, Zhe Tan, Yu Li, Zhu Jiachen, Yuheng Jia, Shu Su

Do Influence Functions Work on Large Language Models? (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have a global audience, so alignment must extend to cultural resonance.
Approach:	They propose a framework that frames alignment as a conditional capacity separation problem.
Outcome:	The proposed framework outperforms both dense baselines and semantic-only MoEs on three large language models.

Copied to clipboard

Zhe Li, Wei Zhao, Yige Li, Jun Sun

TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image Models (2025.acl-long)

Challenge:	Influence functions are important for quantifying the impact of individual training data points on a model’s predictions.
Approach:	They conduct a systematic study to address a key question: do influence functions work on large language models?
Outcome:	The influence functions perform poorly across multiple tasks and are therefore unsuitable for large language models.

Copied to clipboard

Xindi Li, Zhe Liu, Tong Zhang, Jiahao Chen, Qingming Li, Jinbao Li, Shouling Ji

Robustness in NLP

Challenge:	Existing Trojan attacks require extensive training data and poor generalization, limiting effectiveness and scalability.
Approach:	They propose a method for embedding Trojans into plugins using a single edit layer . they find that the method reduces modified parameters by 8-fold and cuts injection time to 25 seconds .
Outcome:	The proposed method achieves an average attack success rate of 91%, a 78% improvement over the state-of-the-art (SOTA) method.

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)

Copied to clipboard

Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun

Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing (2024.findings-emnlp)

Challenge:	Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks.
Approach:	They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies.
Outcome:	The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%.

Copied to clipboard

Wei Zhao, Zhe Li, Yige Li, Ye Zhang, Jun Sun

CSL: A Large-scale Chinese Scientific Literature Dataset (2022.coling-1)

Challenge:	Existing defense methods focus on detecting harmful prompts or reducing the likelihood of harmful responses.
Approach:	They propose a layer-specific editing method to align LLMs to harmful prompts by supervised fine-tuning and reinforcement learning.
Outcome:	The proposed method improves the performance of large language models against jailbreak attacks while maintaining performance on benign prompts.

Copied to clipboard

Yudong Li, Yuqing Zhang, Zhe Zhao, Linlin Shen, Weijie Liu, Weiquan Mao, Hui Zhang

Information Extraction & Text Mining

Challenge:	Existing datasets centered around the English language restrict development of Chinese scientific NLP.
Approach:	They present a large-scale Chinese scientific literature dataset based on Chinese papers . they use semi-structured data as a natural annotation for many supervised NLP tasks .
Outcome:	The proposed dataset can serve as a Chinese corpus and perform many supervised tasks.

Novel Slot Detection With an Incremental Setting (2023.findings-emnlp)

Copied to clipboard

Chen Liang, Hongliang Li, Changhao Guan, Qingbin Liu, Jian Liu, Jinan Xu, Zhe Zhao

Dialogue Systems & Conversational Agents

Challenge:	Current dialogue systems face diverse user requests and rapid change domains, making quickly adapt to scenarios with previous unseen slot types becomes a major challenge.
Approach:	They propose an incremental novel slot detection task which separates the dialogue system to deal with novel types as two major phrases: 1) model discovers unknown slots; 2) training model to possess the capability to handle new classes.
Outcome:	The proposed approach overcomes catastrophic forgetting during the process of INSD and is highly effective.

Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog (P19-1)

Copied to clipboard

Zhe Gan, Yu Cheng, Ahmed Kholy, Linjie Li, Jingjing Liu, Jianfeng Gao

Natural Language Interfaces

Challenge:	Existing models for visual dialog infer the answer through multiple reasoning steps.
Approach:	They propose a model for visual dialog that uses multi-step reasoning to answer questions about an image.
Outcome:	The proposed model achieves a new state-of-the-art of 64.47% on the VisDial v1.0 dataset .

Parameter-efficient Continual Learning Framework in Industrial Real-time Text Classification System (2022.naacl-industry)

Copied to clipboard

Tao Zhu, Zhe Zhao, Weijie Liu, Jiachi Liu, Yiren Chen, Weiquan Mao, Haoyan Liu, Kunbo Ding, Yudong Li, Xuefeng Yang

Information Retrieval

Challenge:	Existing continual learning methods use data replay, parameter isolation and regularization to mitigate catastrophic forgetting.
Approach:	They propose a parameter-efficient continual learning framework that updates parameters offline and then trains using an online regularization method.
Outcome:	The proposed framework reduces catastrophic forgetting and saves the model with the changed parameters instead of all parameters.

PersonaLM: Language Model Personalization via Domain-distributed Span Aggregated K-Nearest N-gram Retrieval Augmentation (2023.findings-emnlp)

Copied to clipboard

Puneet Mathur, Zhe Liu, Ke Li, Yingyi Ma, Gil Keren, Zeeshan Ahmed, Dinesh Manocha, Xuedong Zhang

RFBFN: A Relation-First Blank Filling Network for Joint Relational Triple Extraction (2022.acl-srw)

Challenge:	Existing language modeling tools for automatic speech recognition (ASR) are difficult to personalize.
Approach:	They propose a domain-distributed Span-Aggregated K-nearest N-gram retrieval augmentation to improve language modeling for automatic speech recognition (ASR) personalization.
Outcome:	The proposed model outperforms baselines on Wikitext-103, UserLibri, and ASAP datasets with a 10-16% improvement in perplexity and a 5-8% reduction in word error rates.

Copied to clipboard

Zhe Li, Luoyi Fu, Xinbing Wang, Haisong Zhang, Chenghu Zhou

Information Extraction & Text Mining

Challenge:	Existing methods for relational triple extraction ignore semantic information of relations or predict subjects and objects sequentially.
Approach:	They propose a relation-first blank filling network to capture semantic information of relations . they transform relations into relation templates with blanks which contain the fine-grained semantic representation of relations.
Outcome:	The proposed model outperforms current state-of-the-art methods on public benchmark datasets.

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs’ Instruction Following Capability (2026.findings-acl)

Copied to clipboard

Jiaming Wang, Yunke Zhao, Peng Ding, Jun Kuang, Yibin Shen, Zhe Tang, Yilin Jin, ZongYu Wang, Xiaoyu Li, Xuezhi Cao

POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training (2020.emnlp-main)

Challenge:	Existing models lack the ability to adhere to instructions, resulting in suboptimal performance.
Approach:	They propose an automated iterative instruction-following benchmark with integrated feedback mechanism.
Outcome:	The proposed benchmark identifies erroneous components in model responses and provides feedback accurately.

Copied to clipboard

Yizhe Zhang, Guoyin Wang, Chunyuan Li, Zhe Gan, Chris Brockett, Bill Dolan

SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026.findings-acl)

Challenge:	Existing pre-trained language models cannot be directly employed to generate text under specified lexical constraints.
Approach:	They propose a method for insertion-based text generation that inserts tokens between existing tokens in a parallel manner.
Outcome:	The proposed method is intuitive and interpretable on Wikipedia and Yelp datasets.

Copied to clipboard

Jiaming Wang, Zhe Tang, Zehao Jin, Hefei Chen, Yilin Jin, Peng Ding, Xiaoyu Li, Xuezhi Cao

Domain Adaptive Text Style Transfer (D19-1)

Challenge:	Large language models (LLMs) are widely deployed as domain-specific agents, but evaluation of their capabilities in such contexts has not been fully explored.
Approach:	They propose a benchmark to evaluate LLMs' ability to follow instructions and make decisions in real-world scenarios.
Outcome:	The proposed benchmark is constructed from real-world business data and adapted into 23 complex SOP scenarios.

Copied to clipboard

Dianqi Li, Yizhe Zhang, Zhe Gan, Yu Cheng, Chris Brockett, Bill Dolan, Ming-Ting Sun

Text Generation

Challenge:	Text style transfer without parallel data is a promising method for learning, but in the scenario where less data is available, it may yield poor performance.
Approach:	They propose to leverage available data to learn domain-adaptive text style transfer models . they evaluate two style transfer tasks where only limited non-parallel data is available .
Outcome:	The proposed models learn from the source domain to: (i) distinguish stylized information and generic content information; (ii) maximally preserve content information and (iv) adaptively transfer the styles in a domain-aware manner.

Analogical Reasoning on Chinese Morphological and Semantic Relations (P18-2)

Copied to clipboard

Shen Li, Zhe Zhao, Renfen Hu, Wensi Li, Tao Liu, Xiaoyong Du

Syntactic Text Processing

Challenge:	Analogical reasoning is effective in capturing linguistic regularities.
Approach:	They propose to use Chinese lexical knowledge to build an analogical reasoning task using a large dataset.
Outcome:	The proposed dataset proves to be reliable benchmark for evaluating Chinese word embeddings.

Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding (2024.findings-acl)

Copied to clipboard

Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, Zhifang Sui

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models (2024.emnlp-industry)

Challenge:	Large Language Models (LLMs) have a high inference latency stemming from autoregressive decoding.
Approach:	They propose a novel decoding paradigm that drafts multiple tokens and verifies them in parallel . they aim to provide a catalyst for further research on Speculative Decoding .
Outcome:	The proposed method drafts multiple tokens and verifies them in parallel . it can be used to accelerate inference in large language models.

Copied to clipboard

Wenjing Ke, Zhe Li, Dong Li, Lu Tian, Emad Barsoum

HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks (2026.findings-acl)

Challenge:	Quantization-aware Training (QAT) is a popular technique for reducing memory usage and improving computational efficiency in large language models.
Approach:	They propose a weight-decomposed low-rank quantization-aware training approach that integrates QAT with a group-specific quantization magnitude adjustment.
Outcome:	The proposed method outperforms the state-of-the-art method on LLaMA and LLama2 models.

Copied to clipboard

Zhe Chen, Yusheng Liao, Zhiyuan Zhu, Haolin Li, Hongcheng Liu, Yanfeng Wang, Yu Wang

Beyond Superficial Tests: Adversarial Refinement for Reliable Property-Based Testing (2026.findings-acl)

Challenge:	Medical large vision-language models suffer from factual inaccuracies and unreliable outputs.
Approach:	They propose a framework that enhances Med-LVLMs through heterogeneous knowledge sources.
Outcome:	The proposed framework improves Med-LVLMs through heterogeneous knowledge sources.

Copied to clipboard

Xiao Li, Runlin Liu, Zhe Zhang, Xiang Gao, Hailong Sun

Robustness in NLP

Challenge:	Large Language Models (LLMs) have demonstrated remarkable proficiency in code generation, yet their application to Property-Based Testing (PBT) remains fraught with a superficiality gap.
Approach:	They propose an agentic framework that hardens software properties through Adversarial Refinement.
Outcome:	a new framework hardens software properties through Adversarial Refinement that detects and fixes bugs in top-tier libraries.

Encoding Sentiment Information into Word Vectors for Sentiment Analysis (C18-1)

Copied to clipboard

Zhe Ye, Fang Li, Timothy Baldwin

Weakly Supervised Named Entity Tagging with Learnable Logical Rules (2021.acl-long)

Challenge:	Existing methods for embedding sentiment knowledge into word vectors are generally trained independently of the downstream task.
Approach:	They propose to encode sentiment knowledge into pre-trained word vectors to improve sentiment analysis.
Outcome:	The proposed method improves sentiment analysis on four popular sentiment datasets compared to benchmark methods.

Copied to clipboard

Jiacheng Li, Haibo Ding, Jingbo Shang, Julian McAuley, Zhe Feng

Contextual Text Style Transfer (2020.findings-emnlp)

Challenge:	Existing methods for building entity tagging systems use weak supervision . previous methods focus on disambiguating entity types based on contexts and expert-provided rules .
Approach:	They propose a method that bootstraps high-quality logical rules to train a neural tagger in a fully automated manner.
Outcome:	The proposed method outperforms weakly supervised methods on three datasets . it rivals state-of-the-art supervised method with lexicon of over 2,000 terms .

Copied to clipboard

Yu Cheng, Zhe Gan, Yizhe Zhang, Oussama Elachqar, Dianqi Li, Jingjing Liu

Text Generation

Challenge:	Existing methods for text style transfer are limited by the lack of parallel data.
Approach:	They propose a task to translate a sentence into a desired style with its surrounding context taken into account.
Outcome:	The proposed model outperforms state-of-the-art methods across style accuracy, content preservation and contextual consistency metrics.

Weight-Inherited Distillation for Task-Agnostic BERT Compression (2024.findings-naacl)

Copied to clipboard

Taiqiang Wu, Cheng Hou, Shanshan Lao, Jiayi Li, Ngai Wong, Zhe Zhao, Yujiu Yang

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

Challenge:	Knowledge Distillation (KD) is a predominant approach for BERT compression.
Approach:	They propose a weight-inherited distillation method which directly transfers knowledge from the teacher to a compact student model by inheriting the weights.
Outcome:	The proposed method outperforms state-of-the-art KD-based methods on GLUE and SQUAD benchmarks.

Copied to clipboard

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

Reasoning

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

HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training (2020.emnlp-main)

Copied to clipboard

Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan, Licheng Yu, Jingjing Liu

Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs (2025.findings-emnlp)

Challenge:	HERO is a framework for large-scale video+language omni-representation learning.
Approach:	They propose a framework for large-scale video+language omni-representation learning that encodes multimodal inputs in a hierarchical structure and uses Masked Language Modeling and Masked Frame Modeling to train models.
Outcome:	The proposed framework achieves state-of-the-art on multiple benchmarks over text-based video/video-moment retrieval, video question answering (QA), Video-and-language Inference and video Captioning tasks across different domains.

Copied to clipboard

Wei Zhao, Zhe Li, Yige Li, Jun Sun