Sumit Gulwani

On the fly synthesis of edit suggestions

2019 · Conference on Object-Oriented Programming Systems, Languages, and Applications

When working with a document, users often perform context-specific repetitive edits – changes to the document that are similar but specific to the contexts at their locations. Programming by demonstration/examples (PBD/PBE) systems automate these tasks …

Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs

2023 · arXiv (Cornell University)

Large language models (LLMs) are increasingly applied for tabular tasks using in-context learning. The prompt representation for a table may play a role in the LLMs ability to process the table. Inspired by prior work, …

An empirical study of validating synthetic data for formula generation

2025

Large language models (LLMs) can be leveraged to help write formulas in spreadsheets, but formula data resources are scarce, impacting both the base performance of pre-trained models and limiting the ability to fine-tune them.Given a …

LLM-Guided Compositional Program Synthesis

2025 · arXiv (Cornell University)

Program synthesis from input-output examples, also called programming by example (PBE), has had tremendous impact on automating end-user tasks. Large language models (LLMs) have the ability to solve PBE tasks by generating code in different …

Program synthesis using natural language

2016

Interacting with computers is a ubiquitous activity for millions of people. Repetitive or specialized tasks often require creation of small, often one-off, programs. End-users struggle with learning and using the myriad of domain-specific languages (DSLs) …