Hi, Here is
Weizhi Tang
A Researcher in Neuro-Symbolic AI; A Founder in qianhu.ai; A Developer in Frontend, Flutter, Backend, and Cloud; A Songwriter in Pop and R&B.
NEWS
π°Paper Accepted at HAR 2025
Jul, 2025Knowledge-free and knowledge-based Theory of Mind reasoning in Large Language Models
PublicationPaper Accepted at HAR 2025
Jul, 2025Breaking the illusion: Revisiting LLM anthropomorphism
PublicationPaper Accepted at ACL Findings 2025
May, 2025HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation
Publication
EDUCATION
πUniversity of Edinburgh
2024 - Present
PhD in Computer Science
National University of Singapore
2021 - 2022
MSc in Data Science and Machine Learning
University of Colorado Boulder
2018 - 2020
BA in Computer Science & Psychology (Distinction)
PAPERS
πBreaking the illusion: Revisiting LLM anthropomorphism
C Sypherd, W Tang, V Belle
The 4th International Conference on Human and Artificial Rationalities, 1-19
As LLMs have demonstrated remarkable performance across diverse domains, researchers have often utilized human categories to describe and evaluate their behavior. Such anthropomorphism results in the application of expectations, benchmarks, and interpretations typically reserved for humans to LLMs. LLM anthropomorphism has a number of benefits, such as facilitating understanding of LLMs, but risks misrepresenting fundamental differences between humans and LLMs and the reality of the progress being made. With that dichotomy in mind, we explore practical taxonomies for the application of anthropomorphic terms and human benchmarks to LLMs that mitigate the risks of LLM anthropomorphism.
Published Jul 2025Knowledge-free and knowledge-based Theory of Mind reasoning in Large Language Models
W Tang, V Belle
The 4th International Conference on Human and Artificial Rationalities, 1-17
Large Language Models (LLMs) have recently shown promise and emergence of Theory of Mind (ToM) ability and even outperform humans in certain ToM tasks. To evaluate and extend the boundaries of the ToM reasoning ability of LLMs, we proposed a novel concept, taxonomy, and framework, that Knowledge-Free and Knowledge-Based ToM reasoning, and developed a multi-round text-based game, called Pick the Right Stuff, as a benchmark. We have evaluated seven LLMs with this game and found their performance on Knowledge-Free tasks is consistently better than on Knowledge-Based tasks. In addition, we found that one of the models with the small parameter size, mistral: 7b-instruct, shows similar performance to other evaluated models with large parameter sizes and even outperforms several of them. Furthermore, it even achieved a performance almost similar to gpt-4o on Knowledge-Based tasks. These results raise a thought-provoking question about whether increasing model parameter size may effectively enhance LLMs capabilities, at least discussed in the context of ToM reasoning ability. We expect this work to offer insights into the ToM reasoning ability of LLMs and to pave the way for the future development of ToM benchmarks and also for the promotion and development of more complex AI agents or systems that are required to be equipped with more complex ToM reasoning ability.
Published Jul 2025Lyria: A General LLM-Driven Genetic Algorithm Framework for Problem Solving
W Tang, K Nuamah, V Belle
While Large Language Models (LLMs) have demonstrated impressive abilities across various domains, they still struggle with complex problems characterized by multi-objective optimization, precise constraint satisfaction, immense solution spaces, etc. To address the limitation, drawing on the superior semantic understanding ability of LLMs and also the outstanding global search and optimization capability of genetic algorithms, we propose to capitalize on their respective strengths and introduce Lyria, a general LLM-driven genetic algorithm framework, comprising 7 essential components. Through conducting extensive experiments with 4 LLMs across 3 types of problems, we demonstrated the efficacy of Lyria. Additionally, with 7 additional ablation experiments, we further systematically analyzed and elucidated the factors that affect its performance.
Preprint Jul 2025
BLOGS
π¨π»βπ»Test Blog 1
Oct, 2025Lorem ipsum dolor sit amet, consectetur adipiscing elit. Praesent nec molestie nunc, et porttitor risus. Cras rutrum tortor id viverra sagittis. Nam rhoncus tincidunt dui non efficitur. Nullam at erat nunc. Morbi mollis cursus ligula, in vestibulum justo iaculis sed. Aliquam interdum erat tortor, ut egestas nisl tristique vel. Duis lectus enim, lobortis id dictum sed, tristique porta felis. Donec elementum, turpis sed congue suscipit, neque lorem gravida diam, quis consequat augue odio eu sem.
test1test2test3


