Sharing State Between Prompts and Programs
By: Ellie Y. Cheng , Logan Weber , Tian Jin and more
The rise of large language models (LLMs) has introduced a new type of programming: natural language programming. By writing prompts that direct LLMs to perform natural language processing, code generation, reasoning, etc., users are writing code in natural language -- natural language code -- for the LLM to execute. An emerging area of research enables interoperability between natural language code and formal languages such as Python. We present a novel programming abstraction, shared program state, that removes the manual work required to enable interoperability between natural language code and program state. With shared program state, programmers can write natural code that directly writes program variables, computes with program objects, and implements control flow in the program. We present a schema for specifying natural function interfaces that extend programming systems to support natural code and leverage this schema to specify shared program state as a natural function interface. We implement shared program state in the Nightjar programming system. Nightjar enables programmers to write Python programs that contain natural code that shares the Python program state. We show that Nightjar programs achieve comparable or higher task accuracy than manually written implementations (+4-19%), while decreasing the lines of code by 39.6% on average. The tradeoff to using Nightjar is that it may incur runtime overhead (0.4-4.3x runtime of manual implementations).
Similar Papers
HoarePrompt: Structural Reasoning About Program Correctness in Natural Language
Software Engineering
Checks if computer code follows instructions.
Evaluating Large Language Models for Code Translation: Effects of Prompt Language and Prompt Design
Software Engineering
Helps computers rewrite code between languages.
How Natural Language Proficiency Shapes GenAI Code for Software Engineering Tasks
Software Engineering
Better English prompts make AI write more correct code.