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 LanguagesWenxuan 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 DiscussionsRuochen 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 ModelsChaoqun 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 LabelsChaoqun 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 AgentsYang Deng*, Xuan Zhang*, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua
ACL 2024 [paper] [code] -
SeaLLMs -- Large Language Models for Southeast AsiaXuan-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 ModelsYue 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 AgentsYang 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 CheckWenxuan 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 ModelsWenxuan 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 ReaderWeiwen 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 LanguageYue Deng, Wenxuan Zhang☨, Sinno Jialin Pan, Lidong Bing.
EMNLP 2023 [paper] [data&code] -
Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support ConversationsYang Deng, Wenxuan Zhang, Yifei Yuan, Wai Lam.
ACL 2023 [paper] [data&code] -
Product Question Answering in E-Commerce: A SurveyYang Deng, Wenxuan Zhang, Qian Yu, Wai Lam.
ACL 2023 [paper] [data&code] -
Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment AnalysisYue Deng, Wenxuan Zhang☨, Sinno Jialin Pan, Lidong Bing.
ACL 2023 [paper] [data&code] -
Easy-to-Hard Learning for Information ExtractionChang Gao, Wenxuan Zhang☨, Wai Lam, Lidong Bing.
Findings of ACL 2023 [paper] [data&code] -
Zero-Shot Text Classification via Self-Supervised TuningChaoqun 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 SystemsYang 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 ChallengesWenxuan 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 FinanceYang 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 DialogueChang Gao, Wenxuan Zhang, Wai Lam
ACL 2022 [paper] [data&code] -
User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational SystemsYang Deng, Wenxuan Zhang, Wai Lam, Hong Cheng, Helen Meng
WWW 2022 [paper] -
Aspect Sentiment Quad Prediction as Paraphrase GenerationWenxuan 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-SwitchingWenxuan Zhang, Ruidan He, Haiyun Peng, Lidong Bing, Wai Lam
EMNLP 2021 [paper] [data&code] -
Aspect-based Sentiment Analysis in Question Answering ForumsWenxuan Zhang, Yang Deng, Xin Li, Lidong Bing, Wai Lam
Findings of EMNLP 2021 [paper] [code] -
Towards Generative Aspect-Based Sentiment AnalysisWenxuan 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 AnsweringWenxuan Zhang, Yang Deng, Jing Ma, Wai Lam.
EMNLP 2020 [paper] [data] -
Multi-hop Inference for Question-driven SummarizationYang Deng, Wenxuan Zhang, Wai Lam.
EMNLP 2020 [paper] [code] -
Answer Ranking for Product-Related Questions via Multiple Semantic Relations ModelingWenxuan Zhang, Yang Deng, Wai Lam.
SIGIR 2020 [arXiv] -
Review-guided Helpful Answer Identification in E-commerceWenxuan Zhang, Wai Lam, Yang Deng, Jing Ma.
WWW 2020 [paper] [code] -
Exploiting BERT for End-to-End Aspect-Based Sentiment AnalysisXin Li, Lidong Bing, Wenxuan Zhang and Wai Lam.
W-NUT@EMNLP 2019 [paper] [code]