Papers by Zhe Zhao

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

Challenge:	CLIP revolutes vision-language pretraining by using contrastive learning on paired web data.
Approach:	They propose to combine a "adapter ensemble" with traditional machine learning techniques to augment large-scale pretrained vision-language models.
Outcome:	The proposed model outperforms baselines and derives improvement when the number of ensemble parameters increases.

Copied to clipboard

Wei Zhao, Zhe Li, Yige Li, Jun Sun

Document-Level Event Argument Extraction With a Chain Reasoning Paradigm (2023.acl-long)

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

Jian Liu, Chen Liang, Jinan Xu, Haoyan Liu, Zhe Zhao

Reasoning

Challenge:	Document-level event argument extraction aims to identify event arguments beyond sentence level, where a significant challenge is to model long-range dependencies.
Approach:	They propose a chain reasoning paradigm which captures long-range interdependence due to the chains’ compositional nature and generates decomposable first-order logic rules for reasoning.
Outcome:	The proposed method outperforms previous methods on two benchmarks and is robust enough to defend against adversarial attacks.

Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools (2026.eacl-long)

Copied to clipboard

Ha Min Son, Huan Ren, Xin Liu, Zhe Zhao

Reasoning

Challenge:	Large Language Models (LLMs) have been shown to be useful for building applications, but their use for fixing Android build errors remains underexplored.
Approach:	They propose a large-level language model agent with domain-specific tools for inspecting and manipulating the Gradle build environment.
Outcome:	The proposed agent outperforms a state-of-the-art coding agent that relies on a general-purpose shell significantly on 184 build errors.

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

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.

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

Copied to clipboard

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

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs (2026.acl-long)

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

Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Dongwon Jung, Hadi Askari, Wenxuan Zhou, Zhe Zhao, Muhao Chen

Programming Languages in NLP

Challenge:	Existing red-teaming approaches for code generation rely on extensive human effort and are prone to generating malicious code under adversarial environments.
Approach:	They propose a red-teaming agent that engages victim models in multi-turn conversations to elicit vulnerable code.
Outcome:	Experiments show that RedCoder outperforms red-teaming methods in inducing vulnerabilities in code generation.

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

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.

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

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

Multimodality

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.

PlotGen-Bench: Evaluating VLMs on Generating Visualization Code from Diverse Plots across Multiple Libraries (2026.findings-acl)

Copied to clipboard

Yi Zhao, Zhen Yang, Shuaiqi Duan, Wenmeng Yu, Zhe Su, Jibing Gong, Jie Tang

Multimodality

Challenge:	PlotGen-Bench evaluates vision-language models' ability to generate executable visualization code from plots under realistic and complex visualization requirements.
Approach:	They propose a benchmark to evaluate plot-to-code generation in vision-language models . they use Matplot, Matplos, Mat3D, Mat4D, and Mat4E to evaluate their performance .
Outcome:	The proposed benchmark covers 9 major categories, 30 subcategories, and 3 core tasks . it covers 2D, 3D and animated plots across 5 widely used visualization libraries.

A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning (2022.coling-1)

Copied to clipboard

Kunbo Ding, Weijie Liu, Yuejian Fang, Weiquan Mao, Zhe Zhao, Tao Zhu, Haoyan Liu, Rong Tian, Yiren Chen

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

Challenge:	Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries . however, its effect is limited by the gap between embedding clusters of different languages .
Approach:	They propose Embedding-Push, Attention-Pull, and Robust targets to transfer English embeddings to virtual multilingual embedders without semantic loss.
Outcome:	Experimental results show that the proposed method outperforms existing methods on cross-lingual tasks and can achieve a better multilingual alignment.

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

AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents (2025.findings-emnlp)

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

Zhun Wang, Vincent Siu, Zhe Ye, Tianneng Shi, Yuzhou Nie, Xuandong Zhao, Chenguang Wang, Wenbo Guo, Dawn Song

Responsible & Trustworthy NLP

Challenge:	AGENTVIGIL is a black-box optimization framework to exploit indirect prompt injection vulnerabilities . indirect prompts compromise the core of LLM agents by manipulating contextual information rather than direct user prompts.
Approach:	They propose a black-box optimization framework to exploit indirect prompt injection vulnerabilities . they use a Monte Carlo tree-based algorithm to iteratively refine inputs .
Outcome:	The proposed framework achieves 71% and 70% success rates against two public benchmarks .

Bloom-Eval: A Hierarchical Evaluation Benchmark for Automatic Survey Generation Based on Bloom’s Taxonomy (2026.acl-long)

Copied to clipboard

Fei Zhang, Zhe Zhao, HaiBin Wen, Tianshuo Wei, Zaixi Zhang, Chao Yang, Ye Wei

Text Generation

Challenge:	Existing evaluation methods suffer from cognitive dimensional simplification and methodological unreliability due to the ”LLM-as-a-Judge” approach.
Approach:	They propose a six-tiered benchmark that evaluates ASG systems by prioritizing deterministic algorithms and introducing a GRADE approach for abstract abilities.
Outcome:	The proposed method provides the ASG field with a systematic, reproducible, and theoretically grounded benchmark to guide future research.

Feedback Is The Key for Automated Survey Generation (2026.findings-acl)

Copied to clipboard

Tianyi Xu, Zhe Zhao, Tianshuo Wei, Yiqun Kou, Liuliu Han, Ye Wei

Challenge:	Large Language Models (LLMs) provide a promising foundation for literature surveys, but guiding them to generate accurate, reliable content remains a fundamental challenge.
Approach:	They propose a feedback-driven framework that incorporates feedback across three dimensions: outline feedback for structural clarity, citation feedback for evidence validation, and content feedback for readability and analytical depth.
Outcome:	The proposed framework significantly improves both citation and content quality, demonstrating feedback as the critical mechanism for automatic survey generation.

Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? (2025.findings-emnlp)

Copied to clipboard

Zhihui Yang, Yupei Wang, Kaijie Mo, Zhe Zhao, Renfen Hu

SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precision (2023.emnlp-industry)

Challenge:	Despite significant progress in multimodal language models, it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models.
Approach:	They propose to assess vision-language models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.
Outcome:	The proposed benchmark assesses the models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions.

Copied to clipboard

Rong Tian, Zijing Zhao, Weijie Liu, Haoyan Liu, Weiquan Mao, Zhe Zhao, Kan Zhou

Challenge:	Existing methods for quantization of models are too complicated and can cause performance damage.
Approach:	They propose a self-adaptive mixed-precision (SAMP) toolkit to automatically control quantization rate by a mixed-presence architecture to balance model accuracy and efficiency.
Outcome:	The proposed toolkit has a higher speedup than PyTorch and FasterTransformer while ensuring the required accuracy.

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

Copied to clipboard

Zhe Li, Wei Zhao, Yige Li, Jun Sun

Learning with Partial Annotations for Event Detection (2023.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

Jian Liu, Dianbo Sui, Kang Liu, Haoyan Liu, Zhe Zhao

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

Challenge:	Event detection (ED) requires fully labeled and high-quality training data.
Approach:	They propose a new trigger localization formulation using contrastive learning to distinguish ground-truth triggers from contexts and show a decent robustness for addressing partial annotation noise.
Outcome:	The proposed approach achieves an F1 score of over 60% in an extreme scenario where 90% of events are unlabeled.

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

Responsible & Trustworthy NLP

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.

Mixture-of-Subspaces in Low-Rank Adaptation (2024.emnlp-main)

Copied to clipboard

Taiqiang Wu, Jiahao Wang, Zhe Zhao, Ngai Wong

Reasoning

Challenge:	Using a subspace-inspired Low-Rank Adaptation method, large language models can be optimized for downstream tasks using parameter-efficient finetuning.
Approach:	They propose a subspace-inspired Low-Rank Adaptation method that decomposes LoRA weights into two subspaces and merges them into the frozen original weight.
Outcome:	The proposed method outperforms LoRA on commonsense reasoning, visual instruction tuning, and subject-driven text-to-image generation tasks.

Improving Slot Filling in Spoken Language Understanding with Joint Pointer and Attention (P18-2)

Copied to clipboard

Lin Zhao, Zhe Feng

GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition (2021.eacl-main)

Challenge:	Experimental results show the effectiveness of our slot filling model at addressing the OOV problem.
Approach:	They propose a generative neural network model for slot filling based on a sequence-to-sequence model and a pointer network.
Outcome:	The proposed model is able to predict slot values on spoken language data.

Copied to clipboard

Xinyan Zhao, Haibo Ding, Zhe Feng

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

Challenge:	Named entity recognition (NER) models often need to be trained with many manual labels to perform well.
Approach:	They propose to train named entity recognition systems using heuristic labeling rules . they create a graph with nodes representing candidate rules extracted from unlabeled data .
Outcome:	The proposed method achieves an average improvement of +20% over the baseline on three NER datasets.

Copied to clipboard

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

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

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.

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.

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.

Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models (2025.coling-main)

Copied to clipboard

Taiqiang Wu, Chaofan Tao, Jiahao Wang, Runming Yang, Zhe Zhao, Ngai Wong

UER: An Open-Source Toolkit for Pre-training Models (D19-3)

Challenge:	Large Language Models (LLMs) have been used in Knowledge Distillation (KD) to compress large models.
Approach:	They propose a Kullback-Leiber divergence method which adaptively allocates weights to combine RKL and FKL to reduce the size of Large Language Models (LLMs).
Outcome:	The proposed method outperforms baselines and improves diversity and quality of generated responses.

Copied to clipboard

Zhe Zhao, Hui Chen, Jinbin Zhang, Xin Zhao, Tao Liu, Wei Lu, Xi Chen, Haotang Deng, Qi Ju, Xiaoyong Du

Addressing NER Annotation Noises with Uncertainty-Guided Tree-Structured CRFs (2023.emnlp-main)

Challenge:	Existing work on pre-training models have shown that it is important to use a framework to deploy various pre- training models efficiently.
Approach:	They propose an assemble-on-demand pre-training toolkit that assembles pre-trained models on demand and encapsulates them with rich modules.
Outcome:	The proposed framework can reproduce state-of-the-art models or develop models that remain unexplored.

Copied to clipboard

Jian Liu, Weichang Liu, Yufeng Chen, Jinan Xu, Zhe Zhao

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

Challenge:	Named entity recognition datasets are notorious for their noisy nature due to annotation errors, inconsistencies, and subjective interpretations.
Approach:	They propose a method that considers NER as a constituency tree parsing problem and uses a tree-structured Conditional Random Fields with uncertainty evaluation for integration.
Outcome:	The proposed model exhibits superb performance even in extreme scenarios with 90% annotation noise.

Copied to clipboard

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

Memory OS of AI Agent (2025.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

Jiazheng Kang, Mingming Ji, Zhe Zhao, Ting Bai

LAMCL: A Length-aware Momentum Contrastive Learning Framework for Multiscale Machine-Revised Text Detection (2026.acl-long)

Challenge:	Large Language Models (LLMs) face a shortage of long-term memory capabilities and limited personalization due to fixed context windows.
Approach:	They propose a Memory Operating System to achieve efficient memory management for AI agents . MemoryOS enables hierarchical memory integration and dynamic updating .
Outcome:	The proposed architecture enables hierarchical memory integration and dynamic updating.

Copied to clipboard

Bing Zhou, Zhe Huang, Shilei Tan, Kai Zhao, Zhou Yongcheng

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

Challenge:	Recent detection methods struggle to capture fine-grained semantic differences, especially for short texts.
Approach:	They propose a framework for machine-revised text detection that integrates two modules to enhance discriminative semantic features.
Outcome:	The proposed method outperforms existing detectors in identifying machine-revised text across diverse practical scenarios, tasks, and LLMs.

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.

REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing (2025.emnlp-main)

Copied to clipboard

Haitian Zhong, Yuhuan Liu, Ziyang Xu, Guofan Liu, Qiang Liu, Shu Wu, Zhe Zhao, Liang Wang, Tieniu Tan

KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation (2024.naacl-long)

Challenge:	Large language model editing methods suffer from overfitting, where factual updates can propagate beyond their intended scope, overemphasizing the edited target even when it’s contextually inappropriate.
Approach:	They propose a framework for precise and controllable knowledge editing that utilizes two-phase representations and a linear transformation to compute a directional "belief shift" vector.
Outcome:	The proposed framework significantly reduces overfitting across nearly all evaluation metrics and on COUNTERFACT and MQuAKE.

Copied to clipboard

Xindi Luo, Zequn Sun, Jing Zhao, Zhe Zhao, Wei Hu

Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs (2025.coling-main)

Challenge:	Existing methods for parameter-efficient finetuning (PEFT) are limited and only finetune a small number of parameters using limited instruction data.
Approach:	They propose a method that inserts an adaptation layer into an LLM to integrate embeddings of entities appearing in the input text.
Outcome:	The proposed method can activate parameterized knowledge in an LLM without changing its parameters or input prompts.

Copied to clipboard

Taiqiang Wu, Zhe Zhao, Jiahao Wang, Xingyu Bai, Lei Wang, Ngai Wong, Yujiu Yang

Green & Sustainable NLP

Challenge:	Existing methods to train low-latency multilayer perceptrons (MLPs) on graph tasks are based on graph nodes and lack graph structural information.
Approach:	They propose to distill graph structural information from Graph Neural Networks (GNNs) to low-latency multilayer perceptrons (MLPs) on graph tasks.
Outcome:	The proposed method does not require graph edges (edge-free setting) yet learns structure-aware MLPs.

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

FastBERT: a Self-distilling BERT with Adaptive Inference Time (2020.acl-main)

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

Weijie Liu, Peng Zhou, Zhiruo Wang, Zhe Zhao, Haotang Deng, Qi Ju

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

Challenge:	Pre-trained language models like BERT have proven to be highly performant, but are often computationally expensive in many practical scenarios.
Approach:	They propose a speed-tunable FastBERT with adaptive inference time that can be flexibly adjusted under varying demands.
Outcome:	The proposed model achieves promising results in English and Chinese datasets.

Copied to clipboard

Wei Zhao, Zhe Li, Yige Li, Jun Sun

Responsible & Trustworthy NLP

Challenge:	Existing safeguards relying on pre-filtering or fine-tuning are costly and diminish overall utility.
Approach:	They propose a lightweight method that leverages LVLMs’ inherent multimodal alignment for zero-shot toxic image detection.
Outcome:	The proposed method achieves a 66.9% defense success rate with only 3.2% false positive rate and 7.2% overhead.

Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals (2024.findings-emnlp)

Copied to clipboard

Yupei Wang, Renfen Hu, Zhe Zhao