Papers by Zhe Wu
Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent reinforcement learning approaches have advanced radiology report generation (RRG) however, there are two limitations: report-level rewards offer limited evidence-grounded guidance for clinical faithfulness . |
| Approach: | They propose a method that uses group-wise evidence-aware alignment rewards and self-correcting preference learning to build a reliable, disease-agnostic preference dataset without human supervision. |
| Outcome: | ESC-RL promotes clinically faithful, disease-aligned reward and supports continual self-improvement during training. |
A Learnable Skill Combination Strategy for Multi-task Learning in Natural Language Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | a novel multi-task learning framework for domain-specific natural language understanding tasks addresses these limitations by combing multiple tasks into a single framework. |
| Approach: | They propose a multi-task learning framework that decomposes the language model into modular skill components and employs a dynamic, learnable skill-combination mechanism to adaptively handle diverse tasks. |
| Outcome: | The proposed framework surpasses conventional multi-task learning approaches in performance. |
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
| 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. |
TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice (2025.naacl-industry)
Copied to clipboard
| Challenge: | Existing methods for jailbreaking large-language models are limited by their limitations . authors present a mutation-based fuzzing technique that generates effective jailbreaking templates . |
| Approach: | They propose a mutation-based fuzzing technique for efficiently finding effective jailbreaking templates that combine with harmful questions to generate harmful responses. |
| Outcome: | The proposed technique achieves 95% attack success rates on public datasets for leading LLMs . it also shows impressive generalizability to unseen harmful questions and improves model defenses to prompt attacks. |
LenAtten: An Effective Length Controlling Unit For Text Summarization (2021.findings-acl)
Copied to clipboard
| Challenge: | Fixed length summarization (FLS) requires generating summaries with a preset number of characters or words. |
| Approach: | They propose a length control unit called LenAtten to break this trade-off by generating a short and coherent summary with the target length. |
| Outcome: | The proposed model improves controllability and ROGUE scores and generalizes well. |
Logic: Long-form Outline Generation via Imitative and Critical Self-refinement (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for long-form outline generation have low knowledge density and lack detail . retrieval-augmented approaches struggle to maintain logical coherence across retrieved information . |
| Approach: | They propose a system that mimics human writers' refinement process by mimicking outlines through imitation and critical self-refinement. |
| Outcome: | The proposed system improves on the FreshWiki and WikiOutline datasets and establishes a coherent planning framework and structured knowledge base. |
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
| 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. |
AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)
Copied to clipboard
Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu, Wenqi Zhang, Yuchen Yan, Qiuying Peng, Jun Wang, Weiming Lu
| Challenge: | Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification. |
| Approach: | They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth. |
| Outcome: | The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation. |
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
| 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%. |
M3AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset (2024.acl-long)
Copied to clipboard
Zhe Chen, Heyang Liu, Wenyi Yu, Guangzhi Sun, Hongcheng Liu, Ji Wu, Chao Zhang, Yu Wang, Yanfeng Wang
| Challenge: | Publishing open-source academic video recordings is an emerging approach to sharing knowledge online. |
| Approach: | They propose a multimodal, multigenre, and multipurpose audio-visual academic lecture dataset with human annotations for multimodal content recognition and understanding tasks. |
| Outcome: | The proposed dataset can be used for multiple audio-visual recognition and understanding tasks. |
Mixture-of-Subspaces in Low-Rank Adaptation (2024.emnlp-main)
Copied to clipboard
| 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. |
Can Intelligent Agents Revolutionize Scale Generation? (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing measurement scales require extensive manual labor and require extensive validation and validation. |
| Approach: | They propose a multi-agent framework that automates scale development by leveraging collaborative AI agents. |
| Outcome: | The proposed framework automates scale development while maintaining rigorous quality standards. |
Enhancing Learning-Based Binary Code Similarity Detection Model through Adversarial Training with Multiple Function Variants (2024.findings-emnlp)
Copied to clipboard
Lichen Jia, Chenggang Wu, Bowen Tang, Peihua Zhang, Zihan Jiang, Yang Yang, Ning Liu, Jingfeng Zhang, Zhe Wang
| Challenge: | Existing Learning-Based Binary Code Similarity Detection (LB-BCSD) methods exhibit lower accuracy in recognizing functions with the same functionality but different implementations. |
| Approach: | They propose a gradient-guided adversarial attack method based on critical code called FuncFooler which perturbs critical code to generate multiple variants of the same function. |
| Outcome: | The proposed method increases the accuracy of the current Learning-Based Binary Code Similarity Detection (LB-BCSD) model by 5%-7%. |
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text generation still suffer from incoherence problems . Neural sequence-to-sequence (seq2sequ) models generate fluent results . |
| Approach: | They propose a novel generation framework that leverages autoregressive self-attention mechanism to conduct content planning and surface realization dynamically. |
| Outcome: | The proposed framework outperforms baseline models and generates more coherent texts with richer contents. |
Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models (2025.coling-main)
Copied to clipboard
| 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. |
Centrality-aware Product Retrieval and Ranking (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Ambiguity and complexity of user queries often lead to mismatch between user’s intent and retrieved product titles or documents. |
| Approach: | They propose a user-intent centrality optimization approach which optimizes for the user intent in semantic product search. |
| Outcome: | The proposed approach improves product ranking efficiency for ambiguous queries and lexical terms with alphanumeric characters. |
LLM as a metric critic for low resource relation identification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that small language models (SLMs) overfit in low resource situations . however, the gap between pre-training and fine-tuning leads to performance decay . |
| Approach: | They propose to combine large language models and LLM for relation identification by co-evolution . they propose to use a masked language model prompt to generate a relation identification task . |
| Outcome: | The proposed model can handle low resource relation identification tasks with minimal overfitting . the proposed model provides essential background knowledge to assist training process . |
GUITester: Enabling GUI Agents for Exploratory Defect Discovery (2026.findings-acl)
Copied to clipboard
| Challenge: | Exploratory GUI testing is essential for software quality but suffers from high manual costs. |
| Approach: | They propose a framework that decouples navigation from verification via two modules . they propose 143 tasks and a GUITestBench benchmark that features 26 defects . |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks in 143 tasks and 26 defects. |
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
| 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. |
Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs (2025.coling-main)
Copied to clipboard
| 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
| 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. |
QueryNER: Segmentation of E-commerce Queries (2024.lrec-main)
Copied to clipboard
| Challenge: | Prior work on aspect-value extraction has focused on extracting portions of a product title or query for narrowly defined aspects. |
| Approach: | They propose a manually-annotated dataset and model for e-commerce query segmentation. |
| Outcome: | The proposed model can recover from null and low recall queries with token and entity dropping. |