Wenxuan Zhang (张雯轩)

Contact: isakzhang [at] gmail.com
More about me: Google Scholar | LinkedIn | X (Twitter) | Zhihu

I will join SUTD as an Assistant Professor in early 2025. I am actively looking for highly motivated PhD students (2025 Fall) / Research Assistants / Visiting students, check out this page on how to get involved. (*: equal contribution, ☨: corresponding author / major supervision)

Recent Preprints

• [NEW] SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages
  Wenxuan Zhang*, Hou Pong Chan*, Yiran Zhao*, Mahani Aljunied*, Jianyu Wang*, Chaoqun Liu, Yue Deng, Zhiqiang Hu, Weiwen Xu, Yew Ken Chia, Xin Li, Lidong Bing
  arXiv:2407.19672 [paper] [project page]
• Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions
  Ruochen Zhao, Wenxuan Zhang☨, Yew Ken Chia, Deli Zhao, Lidong Bing
  arXiv:2405.20267 [paper] [project page]
• Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models
  Chaoqun Liu, Wenxuan Zhang☨, Yiran Zhao, Anh Tuan Luu, Lidong Bing
  arXiv:2403.10258 [paper] [code]

Selected Publications [Google Scholar]

• Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels
  Chaoqun Liu, Qin Chao, Wenxuan Zhang☨, Xiaobao Wu, Boyang Li, Anh Tuan Luu, Lidong Bing
  COLING 2025 [paper] [code]
• How do Large Language Models Handle Multilingualism?
  Yiran Zhao, Wenxuan Zhang☨, Guizhen Chen, Kenji Kawaguchi, Lidong Bing
  NeurIPS 2024 [paper] [data&code]
• On the Multi-turn Instruction Following for Conversational Web Agents
  Yang Deng*, Xuan Zhang*, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua
  ACL 2024 [paper] [code]
• SeaLLMs -- Large Language Models for Southeast Asia
  Xuan-Phi Nguyen*, Wenxuan Zhang*, Xin Li*, Mahani Aljunied*, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing
  ACL 2024 System Demostration [paper] [code] [demo]
• Multilingual Jailbreak Challenges in Large Language Models
  Yue Deng, Wenxuan Zhang☨, Sinno Jialin Pan, Lidong Bing
  ICLR 2024 [paper] [data&code]
  Top 3% cited papers at ICLR 2024 (as of Dec 2024)
• Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents
  Yang Deng, Wenxuan Zhang☨, Wai Lam, See-Kiong Ng, Tat-Seng Chua
  ICLR 2024 [paper] [data&code]
• Sentiment Analysis in the Era of Large Language Models: A Reality Check
  Wenxuan Zhang*, Yue Deng*, Bing Liu, Sinno Jialin Pan, Lidong Bing
  Findings of NAACL 2024 [paper] [data&code]
• M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models
  Wenxuan Zhang, Sharifah Mahani Aljunied, Chang Gao, Yew Ken Chia, Lidong Bing
  NeurIPS 2023 (Datasets and Benchmarks) [paper] [data&code]
• From Clozing to Comprehending: Retrofitting Pre-trained Language Model to Pre-trained Machine Reader
  Weiwen Xu, Xin Li, Wenxuan Zhang, Meng Zhou, Wai Lam, Luo Si, Lidong Bing.
  NeurIPS 2023 [paper] [data&code]
• SOUL: Towards Sentiment and Opinion Understanding of Language
  Yue Deng, Wenxuan Zhang☨, Sinno Jialin Pan, Lidong Bing.
  EMNLP 2023 [paper] [data&code]
• Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations
  Yang Deng, Wenxuan Zhang, Yifei Yuan, Wai Lam.
  ACL 2023 [paper] [data&code]
• Product Question Answering in E-Commerce: A Survey
  Yang Deng, Wenxuan Zhang, Qian Yu, Wai Lam.
  ACL 2023 [paper] [data&code]
• Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysis
  Yue Deng, Wenxuan Zhang☨, Sinno Jialin Pan, Lidong Bing.
  ACL 2023 [paper] [data&code]
• Easy-to-Hard Learning for Information Extraction
  Chang Gao, Wenxuan Zhang☨, Wai Lam, Lidong Bing.
  Findings of ACL 2023 [paper] [data&code]
• Zero-Shot Text Classification via Self-Supervised Tuning
  Chaoqun Liu, Wenxuan Zhang☨, Guizhen Chen, Xiaobao Wu, Anh Tuan Luu, Chip Hong Chang, Lidong Bing.
  Findings of ACL 2023 [paper] [data&code]
• A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems
  Yang Deng, Wenxuan Zhang☨, Weiwen Xu, Wenqiang Lei, Tat-Seng Chua, Wai Lam
  TOIS 2023 [paper] [data&code]
• A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges
  Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, Wai Lam
  TKDE 2022 [paper] [resources]
• PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance
  Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, Tat-Seng Chua.
  EMNLP 2022 [paper] [data&code]
• UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue
  Chang Gao, Wenxuan Zhang, Wai Lam
  ACL 2022 [paper] [data&code]
• User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational Systems
  Yang Deng, Wenxuan Zhang, Wai Lam, Hong Cheng, Helen Meng
  WWW 2022 [paper]
• Aspect Sentiment Quad Prediction as Paraphrase Generation
  Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, Wai Lam
  EMNLP 2021 [paper] [data&code]
  Top 2% cited papers at EMNLP 2021 (as of Dec 2024)
• Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-Switching
  Wenxuan Zhang, Ruidan He, Haiyun Peng, Lidong Bing, Wai Lam
  EMNLP 2021 [paper] [data&code]
• Aspect-based Sentiment Analysis in Question Answering Forums
  Wenxuan Zhang, Yang Deng, Xin Li, Lidong Bing, Wai Lam
  Findings of EMNLP 2021 [paper] [code]
• Towards Generative Aspect-Based Sentiment Analysis
  Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, Wai Lam.
  ACL 2021 [paper] [code]
Top 3% cited papers at ACL 2021 (as of Dec 2024)
• AnswerFact: Fact Checking in Product Question Answering
  Wenxuan Zhang, Yang Deng, Jing Ma, Wai Lam.
  EMNLP 2020 [paper] [data]
• Multi-hop Inference for Question-driven Summarization
  Yang Deng, Wenxuan Zhang, Wai Lam.
  EMNLP 2020 [paper] [code]
• Answer Ranking for Product-Related Questions via Multiple Semantic Relations Modeling
  Wenxuan Zhang, Yang Deng, Wai Lam.
  SIGIR 2020 [arXiv]
• Review-guided Helpful Answer Identification in E-commerce
  Wenxuan Zhang, Wai Lam, Yang Deng, Jing Ma.
  WWW 2020 [paper] [code]
• Exploiting BERT for End-to-End Aspect-Based Sentiment Analysis
  Xin Li, Lidong Bing, Wenxuan Zhang and Wai Lam.
  W-NUT@EMNLP 2019 [paper] [code]