Eric Zelikman

Papers

1

Total Citations

14

H-Index

1

About

Eric Zelikman is a leading researcher in the intersection of large language models (LLMs) and algorithmic reasoning, with a focus on enabling machines to tackle complex, hierarchical tasks. His most notable contribution is the development of **Parsel**, a framework that allows LLMs to decompose intricate problems—such as generating sophisticated computer programs—into manageable, high-level algorithmic designs before implementing each component step-by-step. This approach mirrors human problem-solving strategies and addresses a critical limitation of LLMs, which often struggle with multi-step reasoning. Although published in 2022, Parsel has already garnered **14 citations**, reflecting its growing influence in the AI community. Zelikman’s work is pivotal for advancing LLM capabilities in domains requiring structured reasoning, such as code generation and mathematical problem-solving. His research bridges the gap between natural language understanding and formal logic, offering a scalable path toward more reliable and interpretable AI systems. For students and researchers exploring the frontiers of machine reasoning, Zelikman’s contributions provide a foundational framework for designing models that think algorithmically, not just statistically.

Research Focus

Key Achievements

1
H-Index
1
Papers
14
Total Citations
14
Avg Citations/Paper
🏆 Most Cited Paper
Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions
14 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 4

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago