Papers by Yuanhe Zhang

Improving Chinese Word Segmentation with Wordhood Memory Networks (2020.acl-main)

Copied to clipboard

Yuanhe Tian, Yan Song, Fei Xia, Tong Zhang, Yonggang Wang

Challenge:	Contextual features are important in Chinese word segmentation (CWS) but it is difficult to integrate wordhood information into existing neural models.
Approach:	They propose a neural framework that integrates contextual wordhood information with several popular encoder-decoder combinations for Chinese word segmentation.
Outcome:	The proposed framework achieves state-of-the-art performance on five benchmark datasets.

ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences (2024.acl-long)

Copied to clipboard

Yuanhe Tian, Ruyi Gan, Yan Song, Jiaxing Zhang, Yongdong Zhang

Language Models

Challenge:	Current large language models (LLMs) are ineffective in learning domain knowledge and aligning with human preference.
Approach:	They propose a benchmark LLM for Chinese medical domain that uses pre-training, supervised fine-tuning and RLHF to train LLMs.
Outcome:	The proposed LLM performs better than existing LLMs in the Chinese medical domain.

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent (2025.findings-emnlp)

Copied to clipboard

Pengyu Zhu, Zhenhong Zhou, Yuanhe Zhang, Shilinlu Yan, Kun Wang, Sen Su

Robustness in NLP

Challenge:	a new method for detecting advanced backdoors is proposed to bypass safety audits.
Approach:	They propose a backdoor implantation strategy that introduces dynamic encryption to bypass safety audits.
Outcome:	The proposed method achieves an attack success rate approaching 100% while maintaining a detection rate of 0%.

SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models (2026.acl-long)

Copied to clipboard

Yuanhe Zhang, Jiayu Tian, Yibo Zhang, Shilinlu Yan, Liang Lin, Zhenhong Zhou, Li Sun, Sen Su

Semantic Text Processing

Challenge:	Existing studies on noise lack quantitative analysis and rely on intuition and empirical observation, thus failing to understand practical robustness.
Approach:	They propose a method for quantifying the impact of noise intensity on LALM inputs by using a structured activation subspace derived from the model's internal representations.
Outcome:	The proposed method outperforms existing denoising methods and demonstrates that noise is perceived more accurately than raw audio features.

PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models (2025.findings-emnlp)

Copied to clipboard

Yuanhe Zhang, Xinyue Wang, Haoran Gao, Zhenhong Zhou, Fanyu Meng, Yuyao Zhang, Sen Su

Language Models

Challenge:	Existing work lacks mitigation strategies against resource consumption attacks . existing work does not provide mitigation strategies for real-world LLM deployments .
Approach:	They propose a pluggable and dynamic doS-Defense framework which employs a two-stage approach to defend against resource consumption attacks from both the input and output sides.
Outcome:	The proposed framework significantly mitigates resource consumption attacks, improving users’ access capacity by up to 500% during adversarial load.

Improving Constituency Parsing with Span Attention (2020.findings-emnlp)

Copied to clipboard

Yuanhe Tian, Yan Song, Fei Xia, Tong Zhang

Challenge:	Constituency parsing is a fundamental task for natural language understanding . n-grams are a conventional type of feature for contextual information . experimental results show that neural parsers with no grammar rules outperform statistical ones .
Approach:	They propose to incorporate n-grams into span representations by weighting them according to their contributions to the parsing process.
Outcome:	The proposed approach outperforms existing statistical grammar-based models on Arabic, Chinese, and English datasets.

RESEMO: A Benchmark Chinese Dataset for Studying Responsive Emotion from Social Media Content (2024.findings-acl)

Copied to clipboard

Bo Hu, Meng Zhang, Chenfei Xie, Yuanhe Tian, Yan Song, Zhendong Mao

Information Extraction & Text Mining

Challenge:	Existing studies on social media text processing do not focus on responsive emotion analysis.
Approach:	They propose a Chinese dataset named ResEmo for responsive emotion analysis, including 3813 posts with 68,781 comments collected from Weibo, the largest social media platform in China.
Outcome:	The proposed dataset includes 3813 posts with 68,781 comments collected from weibo, the largest social media platform in China.

Aspect-based Sentiment Analysis with Context Denoising (2024.findings-naacl)

Copied to clipboard

Yuanhe Tian, Chang Liu, Yan Song, Fei Xia, Yongdong Zhang

Sentiment Analysis

Challenge:	Existing approaches to ABSA use text encoders to locate important context features or remove them from input.
Approach:	They propose to improve ABSA with context denoising to remove noise from text . they use diffusion networks to perform denoizing process to gradually eliminate noise . paper shows that aspect-based sentiment analysis is effective for fine-grained analysis .
Outcome:	The proposed approach improves ABSA on five widely used ABSA datasets.

CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models (2026.findings-acl)

Copied to clipboard

Zhenhong Zhou, Zherui Li, Jie Zhang, Yuanhe Zhang, Kun Wang, Yang Liu, Qing Guo

Robustness in NLP

Challenge:	Existing security models rely on open-ended communication, but the collaborative process itself can be exploited and disrupted.
Approach:	They propose a new threat class, called Denial-of-Collaboration, which corrupts collaborative structure and transforms communication topology into self-sabotage.
Outcome:	The proposed attacks bypass conventional safety alignments that are not designed to detect behavioral or systemic attacks.

Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge (2020.acl-main)

Copied to clipboard

Yuanhe Tian, Yan Song, Xiang Ao, Fei Xia, Xiaojun Quan, Tong Zhang, Yonggang Wang

Syntactic Text Processing

Challenge:	Chinese word segmentation and part-of-speech tagging are important fundamental tasks in natural language processing.
Approach:	They propose a neural model for Chinese word segmentation and part-of-speech tagging . they incorporate context features and syntactic knowledge for each input character .
Outcome:	The proposed model can learn and benefit from existing tools, but its quality may be poor.

Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings (2025.findings-acl)

Copied to clipboard

Yuanhe Zhang, Zhenhong Zhou, Wei Zhang, Xinyue Wang, Xiaojun Jia, Yang Liu, Sen Su

Robustness in NLP

Challenge:	Existing studies on white-box attacks focus on black-box LLMs, leaving black- box scenarios underexplored.
Approach:	They propose an automated algorithm designed for black-box LLMs that constructs the DoS Attack Tree and expands the node coverage to achieve effectiveness under black- box conditions.
Outcome:	The proposed algorithm can be used to build a DoS Attack Tree and expand the node coverage to achieve effectiveness under black-box conditions.