Papers › Natural Language to Code Translation with Execution

Natural Language to Code Translation with Execution

25 Apr 2022arXiv:2204.11454archive 2025-07-28

Freda Shi, Daniel Fried, Marjan Ghazvininejad, Luke Zettlemoyer, Sida I. Wang

Generative models of code, pretrained on large corpora of programs, have shown great success in translating natural language to code (Chen et al., 2021; Austin et al., 2021; Li et al., 2022, inter alia). While these models do not explicitly incorporate program semantics (i.e., execution results) during training, they are able to generate correct solutions for many problems. However, choosing a single correct program from a generated set for each problem remains challenging. In this work, we introduce execution result--based minimum Bayes risk decoding (MBR-EXEC) for program selection and show that it improves the few-shot performance of pretrained code models on natural-language-to-code tasks. We select output programs from a generated candidate set by marginalizing over program implementations that share the same semantics. Because exact equivalence is intractable, we execute each program on a small number of test inputs to approximate semantic equivalence. Across datasets, execution or simulated execution significantly outperforms the methods that do not involve program semantics. We find that MBR-EXEC consistently improves over all execution-unaware selection methods, suggesting it as an effective approach for natural language to code translation. We open-source our code at github.com/facebookresearch/mbr-exec and data at dl.fbaipublicfiles.com/mbr-exec/mbr-exec-release.zip

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2204.11454")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · violated contract; 2 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/mbr-exec officialmentioned in paperMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 6 ran; 1 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · violated contract
2ran
6unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from facebookresearch/mbr-exec. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

condition_has_like facebookresearch/mbr-exec/utils_sql.py official repository ran · violated contract MIT (permissive) · 8231e3fdffa9c8ee · report
condition_has_or facebookresearch/mbr-exec/utils_sql.py official repository ran · violated contract fingerprinted MIT (permissive) · f2d76234528d3b57 · report
condition_has_sql facebookresearch/mbr-exec/utils_sql.py official repository ran · violated contract MIT (permissive) · 954c76e256cc7220 · report
get_schema facebookresearch/mbr-exec/process_sql.py official repository ran fingerprinted MIT (permissive) · 0992d2a47ae733fa · report
get_schema_from_json facebookresearch/mbr-exec/process_sql.py official repository ran MIT (permissive) · c4dcaf29b663a364 · report
single_exec_result_matching facebookresearch/mbr-exec/sample_selectors.py official repository ran · honoured contract fingerprinted MIT (permissive) · e0d0a3c69f5ae939 · report
codex facebookresearch/mbr-exec/collectors.py official repository unverified MIT (permissive) · 92903e4e5086d7ec · report
codex_with_info facebookresearch/mbr-exec/collectors.py official repository unverified MIT (permissive) · 573e53ead6564561 · report
evaluate_spider facebookresearch/mbr-exec/evaluate.py official repository unverified MIT (permissive) · 684a636f41be9e03 · report
executability_selection_function facebookresearch/mbr-exec/sample_selectors.py official repository unverified MIT (permissive) · 6a5cb99badd4bfea · report
execution_selection_function facebookresearch/mbr-exec/sample_selectors.py official repository unverified MIT (permissive) · de850df14e9ba78e · report
tokenize facebookresearch/mbr-exec/process_sql.py official repository unverified MIT (permissive) · a906f5de1f5971b0 · report

Tasks

Code GenerationCode TranslationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation MBPP code-davinci-001 175B + MBR-Exec Accuracy 58.2 #50 of 99 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections