# Program Synthesis with Pragmatic Communication

arXiv: https://arxiv.org/abs/2007.05060 · HTML: https://mlsanity.com/paper/2007.05060/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2020.

## Built on by (most cited first, 15 of 15)

- [Communicating Natural Programs to Humans and Machines](https://mlsanity.com/paper/2106.07824/) (2021)
- [Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models](https://mlsanity.com/paper/2302.04662/) (2023)
- [I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons](https://mlsanity.com/paper/2212.10060/) (2022)
- [Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language](https://mlsanity.com/paper/2306.02797/) (2023)
- [Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches](https://mlsanity.com/paper/2211.08371/) (2022)
- [Toward Trustworthy Neural Program Synthesis](https://mlsanity.com/paper/2210.00848/) (2022)
- [Transcribing Natural Languages for The Deaf via Neural Editing Programs](https://mlsanity.com/paper/2112.09600/) (2021)
- [Generating Pragmatic Examples to Train Neural Program Synthesizers](https://mlsanity.com/paper/2311.05740/) (2023)
- [Efficient Pragmatic Program Synthesis with Informative Specifications](https://mlsanity.com/paper/2204.02495/) (2022)
- [Amortizing Pragmatic Program Synthesis with Rankings](https://mlsanity.com/paper/2407.02499/) (2024)
- [Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitation](https://mlsanity.com/paper/2409.13507/) (2024)
- [Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generation](https://mlsanity.com/paper/2510.09390/) (2025)
- [Online library learning in human visual puzzle solving](https://mlsanity.com/paper/2603.23244/) (2026)
- [Amortizing Pragmatic Program Synthesis with Rankings](https://mlsanity.com/paper/2309.03225/) (2023)
- [Natural Building Blocks for Structured World Models: Theory, Evidence, and Scaling](https://mlsanity.com/paper/2511.02091/) (2025)

## Abstract (arXiv)

Program synthesis techniques construct or infer programs from user-provided specifications, such as input-output examples. Yet most specifications, especially those given by end-users, leave the synthesis problem radically ill-posed, because many programs may simultaneously satisfy the specification. Prior work resolves this ambiguity by using various inductive biases, such as a preference for simpler programs. This work introduces a new inductive bias derived by modeling the program synthesis task as rational communication, drawing insights from recursive reasoning models of pragmatics. Given a specification, we score a candidate program both on its consistency with the specification, and also whether a rational speaker would chose this particular specification to communicate that program. We develop efficient algorithms for such an approach when learning from input-output examples, and build a pragmatic program synthesizer over a simple grid-like layout domain. A user study finds that end-user participants communicate more effectively with the pragmatic program synthesizer over a non-pragmatic one.