Discovering the syntax and strategies of natural language programming with generative language models

E Jiang, E Toh, A Molina, K Olson, C Kayacik… - Proceedings of the …, 2022 - dl.acm.org
In this paper, we present a natural language code synthesis tool, GenLine, backed by 1) a
large generative language model and 2) a set of task-specific prompts that create or change …

Repairing bugs in python assignments using large language models

J Zhang, J Cambronero, S Gulwani, V Le… - arXiv preprint arXiv …, 2022 - arxiv.org
Students often make mistakes on their introductory programming assignments as part of
their learning process. Unfortunately, providing custom repairs for these mistakes can …

Flashfill++: Scaling programming by example by cutting to the chase

J Cambronero, S Gulwani, V Le, D Perelman… - Proceedings of the …, 2023 - dl.acm.org
Programming-by-Examples (PBE) involves synthesizing an" intended program" from a small
set of user-provided input-output examples. A key PBE strategy has been to restrict the …

Constitutionmaker: Interactively critiquing large language models by converting feedback into principles

S Petridis, BD Wedin, J Wexler, M Pushkarna… - Proceedings of the 29th …, 2024 - dl.acm.org
Large language model (LLM) prompting is a promising new approach for users to create
and customize their own chatbots. However, current methods for steering a chatbot's …

Scattershot: Interactive in-context example curation for text transformation

S Wu, H Shen, DS Weld, J Heer… - Proceedings of the 28th …, 2023 - dl.acm.org
The in-context learning capabilities of LLMs like GPT-3 allow annotators to customize an
LLM to their specific tasks with a small number of examples. However, users tend to include …

Data extraction via semantic regular expression synthesis

Q Chen, A Banerjee, Ç Demiralp, G Durrett… - Proceedings of the ACM …, 2023 - dl.acm.org
Many data extraction tasks of practical relevance require not only syntactic pattern matching
but also semantic reasoning about the content of the underlying text. While regular …

Using pre-trained language models to resolve textual and semantic merge conflicts (experience paper)

J Zhang, T Mytkowicz, M Kaufman, R Piskac… - Proceedings of the 31st …, 2022 - dl.acm.org
Program merging is standard practice when developers integrate their individual changes to
a common code base. When the merge algorithm fails, this is called a merge conflict. The …

Two birds with one stone: Boosting code generation and code search via a generative adversarial network

S Wang, B Lin, Z Sun, M Wen, Y Liu, Y Lei… - Proceedings of the ACM …, 2023 - dl.acm.org
Automatically transforming developers' natural language descriptions into source code has
been a longstanding goal in software engineering research. Two types of approaches have …

Neurosymbolic repair for low-code formula languages

R Bavishi, H Joshi, J Cambronero, A Fariha… - Proceedings of the …, 2022 - dl.acm.org
Most users of low-code platforms, such as Excel and PowerApps, write programs in domain-
specific formula languages to carry out nontrivial tasks. Often users can write most of the …

Pydex: Repairing bugs in introductory python assignments using llms

J Zhang, JP Cambronero, S Gulwani, V Le… - Proceedings of the …, 2024 - dl.acm.org
Students often make mistakes in their introductory programming assignments as part of their
learning process. Unfortunately, providing custom repairs for these mistakes can require a …