Program Aided Language Models

Program Aided Language Models turns out to be a useful lens for thinking about data in the real world. Aman Madaan and Shuyan Zhou. They are both PhD students at the Language Technology Institute at Carnegie Mellon University.

Guests

Aman Madaan: "Aman is a PhD candidate at Carnegie Mellon University. His current focus is improving the reasoning capabilities of large language models, focusing on leveraging feedback and the synergy between code generation and natural language reasoning. In the past, he has developed several techniques that are now part of standard few-shot reasoning workflows, including memory-augmented prompting [http://memprompt.com](http://memprompt.com), using code for improving structured generation and reasoning: [http://cocogen.structgen.com/](http://cocogen.structgen.com/), [http://reasonwithpal.com/](http://reasonwithpal.com/), and Self-refinement of language model outputs [http://selfrefine.info/](http://selfrefine.info/). Website: [https://madaan.github.io/](https://madaan.github.io/) "

Shuyan Zhou: "[Shuyan Zhou](https://shuyanzhou.com) is a final-year Ph.D. student from the Language Technologies Institute at Carnegie Mellon University, advised by Prof. Graham Neubig. She studies autonomous AI agents and she aims to create AI agents that could perform tedious tasks so that everyone can focus on more creative and interesting tasks. Before joining CMU, she received her B.S. degree from the Department of Computer Science and Technology at Harbin Institute of Technology. "