🧑‍🔬 Roy Ka-Wei Lee

🏛️ Affiliations

🎓Singapore University of Technology and DesignSingapore · Singapore2020–2026 · 77 papersEmployment 2020–2026 · Associate Professor, Design and Artificial Intelligencecurrent🎓Nanyang Technological UniversitySingapore · Singapore2026 · 1 papercurrent🎓University of SaskatchewanSaskatoon · Canada2019–2022 · 12 papersEmployment 2019–2020 · Assistant Professor, Computer Science🎓Singapore Management UniversitySingapore · Singapore2013–2019 · 12 papers🎓University of British Columbia, Okanagan CampusKelowna · Canada2026Employment since 2026 · Associate Professor, Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models (2024 · 86 citations)
   Open-source multimodal LLMs such as LLaVA-1.5 handle general VQA well but struggle with math problems that depend on diagrams, charts, or tables.
2. SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models (2026 · 6 citations)
   Large language models tend to produce long texts in one uninterrupted pass. The results often start well but lose coherence and contradict themselves as length grows. The authors address this by imitating how human authors work. Their SuperWriter-Agent pipeline splits writing into three stages:
3. BLEnD-Vis: Benchmarking Multimodal Cultural Understanding in Vision Language Models (2026 · 2 citations)
   Vision-language models (VLMs) are used worldwide, yet current cultural evaluations mostly test plain fact recall or single-image grounding.
4. Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages — A Singlish Case Study (2025 · 1 citation)
   LLMs are mostly safety-tuned on English data, so they behave worse in creoles and code-mixed varieties. Lim et al. address this for Singlish, the English creole of Singapore. They take SEA-Lion-v2.1-Instruct, a Llama 3-8B model adapted to Southeast Asian languages but without explicit safety tuning, and compare three…
5. Belief Is All You Need: Signed Belief Graph Neural Networks for Topic Modeling in Conspiratorial Discourse (2026)
   Topic models that rely only on semantic similarity often merge conspiratorial and ordinary posts, because both use the same vocabulary about health, politics or money.
6. Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment (2026)
   Most LLMs are aligned to a single, aggregated value profile that often leans Western. This paper asks whether models can instead reproduce the differing values of demographic subgroups within one society. Singapore serves as the testbed, using its World Values Survey (WVS) Wave 7 data. The authors define subgroups by…
7. Revisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty (2026)
   Self-play preference optimization aligns LLMs without human labels. A policy model samples several answers per prompt, a reward model scores them, and the top- and bottom-scored answers become a DPO training pair. Past work studied reward models and pair construction, but rarely asked which prompts belong in the…

All works

15 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetLei Wang et al.2023 · 666 citations
2. Graph-to-Tree Learning for Solving Math Word Problems ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetJipeng Zhang et al.2020 · 186 citations
3. Prompting for Multimodal Hateful Meme Classification ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetRui Cao et al.2022 · 123 citations
4. Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language ModelsFindings of the Association for Computational LinguisticsWenhao Shi, Zhiqiang Hu, Yi Bin, et al.2024 · 86 citations
5. Teacher-Student Networks with Multiple Decoders for Solving Math Word Problem ↗IJCAI 2020 · no summary yetJipeng Zhang et al.2020 · 76 citations
6. Text Style Transfer: A Review and Experimental Evaluation ↗arXiv:2010.12742 · KDD Explorations 24 (2022) 14-45 · no summary yetZhiqiang Hu et al.2020 · 71 citations
7. HateGAN: Adversarial Generative-Based Data Augmentation for Hate Speech Detection ↗Proceedings of the 28th International Conference on Computational Linguistics · no summary yetRui Cao, Roy Ka-Wei Lee2020 · 68 citations
8. On Orthogonality Constraints for Transformers ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) · no summary yetAston Zhang et al.2021 · 11 citations
9. Syntax Matters! Syntax-Controlled in Text Style Transfer ↗Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021) · no summary yetZhiqiang Hu, Roy Ka-Wei Lee, Charu C. Aggarwal2021 · 9 citations
10. SuperWriter: Reflection-Driven Long-Form Generation with Large Language ModelsFindings of the Association for Computational LinguisticsYuhao Wu, Yushi Bai, Zhiqiang Hu, et al.2026 · 6 citations
11. BLEnD-Vis: Benchmarking Multimodal Cultural Understanding in Vision Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Bryan Chen Zhengyu Tan, Weihua Zheng, Zhengyuan Liu, et al.2026 · 2 citations
12. Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages — A Singlish Case StudyarXiv:2502.12485Isaac Lim, Shaun Khoo, Roy Ka-Wei Lee, et al.2025 · 1 citation
13. Belief Is All You Need: Signed Belief Graph Neural Networks for Topic Modeling in Conspiratorial DiscourseWorkshop on Natural Language Processing and Computational Social ScienceSoorya Ram Shimgekar, Abhay Goyal, Roy Ka-Wei Lee, et al.2026
14. Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural AlignmentAnnual Meeting of the Association for Computational Linguistics (ACL)Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, et al.2026
15. Revisiting Self-Play Preference Optimization: On the Role of Prompt DifficultyFindings of the Association for Computational LinguisticsYao Xiao, Jung-jae Kim, Roy Ka-Wei Lee, et al.2026

🤝 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

• Bryan Chen Zhengyu Tan ×2
• Lidong Bing ×2
• Nancy Chen ×2
• Zhengyuan Liu ×2
• Zhiqiang Hu ×2
• Hwaran Lee
• Juanzi Li
• Jung-jae Kim
• See-Kiong Ng
• Xiaoyuan Yi
• Xing Xie
• Yang Yang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×3: ACL 2026
• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026 ×2, Findings of the Association for Computational Linguistics 2024
• Conference of the European Chapter of the Association for Computational Linguistics (EACL): EACL 2026
• Workshop on Natural Language Processing and Computational Social Science: Workshop on Natural Language Processing and Computational Social Science 2026
• IJCAI 2020
• Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
• Proceedings of the 28th International Conference on Computational Linguistics
• Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
• Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)

🔗 Cited by

Papers of our library cite their works 600 times (of the 149,439 papers whose bibliographies we read); 139 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/roy-ka-wei-lee/