Zhun Yang
Papers
2
Total Citations
30
H-Index
2
About
Zhun Yang is a rising researcher at the intersection of artificial intelligence, natural language processing, and symbolic reasoning. Their work focuses on bridging the gap between the statistical power of large language models (LLMs) and the structured precision of logic programming—a critical challenge for achieving robust, generalizable machine reasoning. Yang’s most-cited paper, “Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text” (2023, with 28 citations), demonstrates a novel framework where LLMs act as highly effective natural language interfaces to logical inference engines. This approach addresses a key limitation of LLMs: their inability to perform reliable, multi-step reasoning without hallucination. By combining the flexibility of neural models with the rigor of symbolic systems, Yang’s work offers a path toward AI that can reason transparently and adapt across diverse text-based tasks. Their contributions are particularly significant for fields requiring verifiable reasoning, such as question answering and automated theorem proving. With growing recognition in the AI community, Zhun Yang is helping to define a hybrid paradigm that could make next-generation AI both more powerful and more trustworthy.
Research Focus
Key Achievements
Top Papers
- 1
- 2