Annie Wong
Papers
1
Total Citations
13
H-Index
1
About
Annie Wong is a leading researcher at the forefront of large language model (LLM) reasoning, with a primary focus on enhancing the logical and multi-step inference capabilities of modern AI systems. Her most-cited work, “Multi-Step Reasoning with Large Language Models, a Survey” (2025, 13 citations), provides a comprehensive analysis of how LLMs with billions of parameters leverage in-context learning for few-shot tasks, while critically identifying their persistent struggles with basic reasoning benchmarks. Wong’s major contribution lies in systematically mapping the gap between LLMs’ impressive language performance and their fundamental reasoning limitations, offering a roadmap for future improvements. Her survey has become an essential reference for researchers working to bridge this divide, influencing subsequent work on chain-of-thought prompting and structured reasoning frameworks. Wong’s insights are particularly valuable for students and practitioners seeking to understand why even the most powerful models can fail at simple logical deductions, and her work continues to shape the direction of LLM reasoning research.
Research Focus
Key Achievements
Top Papers
- 1Multi-Step Reasoning with Large Language Models, a Survey13 citations · 2025