Papers by Yuan Zhuang
Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context (2026.acl-long)
Copied to clipboard
Yilun Zhu, Yuan Zhuang, Nikhita Vedula, Dushyanta Dhyani, Shaoyuan Xu, Mohsen Bayati, Bryan Wang, Shervin Malmasi
| Challenge: | Existing methods for text regression lack local grounding and rely on shared representations. |
| Approach: | They propose a distributional regression model with quantile tokens that insert dedicated quantiles into the input sequence. |
| Outcome: | The proposed method outperforms baseline models on the inside Airbnb and StackSample datasets. |
NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human (2025.findings-emnlp)
Copied to clipboard
Shuo Huang, William Maclean, Xiaoxi Kang, Qiongkai Xu, Zhuang Li, Xingliang Yuan, Gholamreza Haffari, Lizhen Qu
| Challenge: | a large number of large language models are being used to protect user privacy . sanitizing sensitive text using two common strategies is the answer . |
| Approach: | They propose sanitizing sensitive text using deleting expressions and abstracting them . they propose a tool for text rewriting that uses crowdsourcing and large language models . |
| Outcome: | The proposed approach protects privacy before sending sensitive data to large language models . it combines crowdsourcing and large language modeling to create a text rewrite tool . |
CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languages (2025.coling-main)
Copied to clipboard
| Challenge: | Existing multilingual models such as XLM-R support only approximately 100-200 languages, leaving nearly 7,000 low-resource languages untapped. |
| Approach: | They construct and open-source a dataset of four-language corpora obtained through machine translation into Chinese, Uyghur and Tibetan. |
| Outcome: | The proposed dataset includes two resource-rich languages and two low-resource languages. |
Rhetorical Questions in LLM Representations: A Linear Probing Study (2026.acl-long)
Copied to clipboard
| Challenge: | Rhetorical questions are asked not to seek information, but to persuade or signal stance . how large language models internally represent rhetorical questions remains unclear . |
| Approach: | They analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts. |
| Outcome: | The results show that rhetorical signals emerge early and are most stably captured by last-token representations. |
Eliciting Affective Events from Language Models by Multiple View Co-prompting (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to generate training data using weakly labeled data are costly and limited . |
| Approach: | They propose a method for acquiring and labeling affective events with multiple view co-prompting using pre-trained language models. |
| Outcome: | The proposed approach improves state-of-the-art affective event classifier on two datasets. |
Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration (2025.acl-long)
Copied to clipboard
Tianyi Bai, Ling Yang, Zhen Hao Wong, Fupeng Sun, Xinlin Zhuang, Jiahui Peng, Chi Zhang, Lijun Wu, Qiu Jiantao, Wentao Zhang, Binhang Yuan, Conghui He
| Challenge: | Efficient data selection is crucial to accelerate the pretraining of language models . limited research has addressed the inherent conflicts between data selection methods . |
| Approach: | They propose a multi-actor collaborative data selection mechanism that prioritizes data based on its specific criterion and updates prioritization rules using the current state of the model. |
| Outcome: | The proposed model accelerates convergence in LM pretraining and achieves an average relative performance gain of 10.5% across multiple language model benchmarks. |
SOLAR: Serendipity Optimized Language Model Aligned for Recommendation (2025.findings-emnlp)
Copied to clipboard
Zichen Yuan, Lifan Sun, Yucen Zhuang, Yue Wang, Xinyuan Song, Tianqi Xu, Siyuan Li, Junchen Fu, Youhua Li, Sirui Hong, Jiaqi Chen, Joemon M. Jose, Yongxin Ni
| Challenge: | Large Language Models have shown strong potential in recommendation tasks . however, their application to serendipity-oriented recommendations remains challenging . |
| Approach: | They propose a domain-adaptive instruction tuning method that aligns Large Language Models with recommendation tasks. |
| Outcome: | The proposed framework bridges the domain gap between LLMs and recommendation tasks. |
MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models (2026.acl-long)
Copied to clipboard
Jie Cao, Tianwei Lin, Bo Yuan, Rolan Yan, Hongyang He, Wenqiao Zhang, Juncheng Li, Dongping Zhang, Siliang Tang, Yueting Zhuang
| Challenge: | Existing methods for parameter-efficient fine-tuning (PEFT) are limited by computational costs and performance degradation. |
| Approach: | They propose a method that integrates Low-Rank Adaptation and Mixture-of-Experts (MoE) they propose combining expert load imbalance and representation collapse to improve LLM performance . |
| Outcome: | The proposed method outperforms homogeneous MoE-LoRA architectures in performance and parameter efficiency. |
Enhancing Cross-Lingual Transfer through Reversible Transliteration: A Huffman-Based Approach for Low-Resource Languages (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models demonstrate cross-lingual transfer capabilities, but these capabilities often fail to extend to low-resource languages, especially those utilizing non-Latin scripts. |
| Approach: | They propose to combine character transliteration with Huffman coding to create a complete transliterations framework that can be extended to other low-resource languages. |
| Outcome: | The proposed framework reduces storage requirements and improves accuracy and accuracy across multiple downstream tasks while maintaining performance on high-resource languages. |
Affective Event Classification with Discourse-enhanced Self-training (2020.emnlp-main)
Copied to clipboard
| Challenge: | Prior work on recognizing affective events focused on producing lexical resources of verbs or event phrases with corresponding affective polarity values. |
| Approach: | They propose a BERT-based model for affective event classification and a discourse-enhanced self-training method that iteratively improves the classifier with unlabeled data. |
| Outcome: | The proposed model outperforms existing models with unlabeled data and improves recall and precision. |
Recognizing Social Cues in Crisis Situations (2024.lrec-main)
Copied to clipboard
| Challenge: | During natural disasters, observations of other people's behavior can play an essential role in a person's decision-making. |
| Approach: | They propose a task to categorize social cues in tweets during crisis situations using an annotated dataset of 6,000 tweets. |
| Outcome: | The proposed task is challenging for existing systems and a manual task is based on a dataset of 6,000 tweets labeled with eight social cue categories. |
My Heart Skipped a Beat! Recognizing Expressions of Embodied Emotion in Natural Language (2024.naacl-long)
Copied to clipboard
| Challenge: | a new task is needed to recognize physical manifestations of emotions in natural language . physical manifestation of emotions affects not only our mental state but also our physical state . |
| Approach: | They propose a task to recognize expressions of embodied emotion in natural language . they use body part mentions with human annotations to extract emotional manner expressions . |
| Outcome: | The proposed model can train without gold data and improve performance with gold data. |
PLAtE: A Large-scale Dataset for List Page Web Extraction (2023.acl-industry)
Copied to clipboard
Aidan San, Yuan Zhuang, Jan Bakus, Colin Lockard, David Ciemiewicz, Sandeep Atluri, Kevin Small, Yangfeng Ji, Heba Elfardy
| Challenge: | Existing methods for web extraction are limited by the limited number of available large-scale datasets. |
| Approach: | They introduce a dataset that focuses on shopping data and a list page web extraction task. |
| Outcome: | The proposed dataset is the first large-scale list page web extraction dataset . it contains 52,898 items and 156,014 attributes, making it the first dataset based on this task . |
Exploring the Role of Context to Distinguish Rhetorical and Information-Seeking Questions (2020.acl-srw)
Copied to clipboard
| Challenge: | Social media posts often contain questions, but many of them are rhetorical and do not seek information. |
| Approach: | They propose a dataset containing questions in tweets paired with their prior tweets to provide context . they find that prior tweet and topic features can improve performance on this task . |
| Outcome: | The proposed dataset compares questions in tweets with their prior tweets to provide context . it shows that prior tweet and topic features can improve performance on this task . |