2.1k citations · 2.4k across the 15 of their papers we have counts for
8 papers · 1 filter
NExT: Teaching Large Language Models to Reason about Code Execution
Ansong Ni, Miltiadis Allamanis, Arman Cohan +4
A fundamental skill among human developers is the ability to understand and reason about program execution. As an example, a programmer can mentally simulate code execution in natu…
Grounding Data Science Code Generation with Input-Output Specifications
Yeming Wen, Pengcheng Yin, Kensen Shi +3
Large language models (LLMs) have recently demonstrated a remarkable ability to generate code from natural language (NL) prompts. However, in the real world, NL is often too ambigu…
ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
Kensen Shi, Joey Hong, Yinlin Deng +3
When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neur…
LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas
Kensen Shi, Hanjun Dai, Wen-Ding Li +2
Search is an important technique in program synthesis that allows for adaptive strategies such as focusing on particular search directions based on execution results. Several prior…
A Library for Representing Python Programs as Graphs for Machine Learning
David Bieber, Kensen Shi, Petros Maniatis +4
Graph representations of programs are commonly a central element of machine learning for code research. We introduce an open source Python library python_graphs that applies static…
Compositional Generalization and Decomposition in Neural Program Synthesis
Kensen Shi, Joey Hong, Manzil Zaheer +2
When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neur…
CrossBeam: Learning to Search in Bottom-Up Program Synthesis
Kensen Shi, Hanjun Dai, Kevin Ellis +1
Many approaches to program synthesis perform a search within an enormous space of programs to find one that satisfies a given specification. Prior works have used neural models to…
Incremental Sampling Without Replacement for Sequence Models
Kensen Shi, David Bieber, Charles Sutton
Sampling is a fundamental technique, and sampling without replacement is often desirable when duplicate samples are not beneficial. Within machine learning, sampling is useful for…