Papers › CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

25 Mar 2022arXiv:2203.13474archive 2025-07-28

Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong

Program synthesis strives to generate a computer program as a solution to a given problem specification, expressed with input-output examples or natural language descriptions. The prevalence of large language models advances the state-of-the-art for program synthesis, though limited training resources and data impede open access to such models. To democratize this, we train and release a family of large language models up to 16.1B parameters, called CODEGEN, on natural language and programming language data, and open source the training library JAXFORMER. We show the utility of the trained model by demonstrating that it is competitive with the previous state-of-the-art on zero-shot Python code generation on HumanEval. We further investigate the multi-step paradigm for program synthesis, where a single program is factorized into multiple prompts specifying subproblems. To this end, we construct an open benchmark, Multi-Turn Programming Benchmark (MTPB), consisting of 115 diverse problem sets that are factorized into multi-turn prompts. Our analysis on MTPB shows that the same intent provided to CODEGEN in multi-turn fashion significantly improves program synthesis over that provided as a single turn. We make the training library JAXFORMER and model checkpoints available as open source contribution: https://github.com/salesforce/CodeGen.

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="2203.13474")

Code

Syntology Ran 10 of 10 code samples harvested from 3 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · violated contract; 4 ran · our draft was wrong; 2 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran; community (archive-listed): 7 samples from 2 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

salesforce/CodeGen officialmentioned in papermentioned on GitHubjax report
salesforce/jaxformer officialmentioned in papermentioned on GitHubjaxBSD-3-Clause report
DIRECT-BIT/SRA-MCTS mentioned on GitHub report
eth-sri/sven mentioned on GitHub report
openlmlab/moss mentioned on GitHubpytorchApache-2.0 report
openmoss/moss mentioned on GitHubpytorchApache-2.0 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

10 samples harvested; 10 ran; 0 honoured the contract we drafted; 0 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 · violated contract
4ran · our draft was wrong
2ran · fixture could not drive it
3ran

Licence: 0 of the 10 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

apply_rotary_pos_emb salesforce/CodeGen/codegen1/jaxformer/hf/codegen/modeling_codegen.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 2f6618868885e7ca · report
fixed_pos_embedding salesforce/CodeGen/codegen1/jaxformer/hf/codegen/modeling_codegen.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 423269b3cef0af9c · report
rotate_every_two salesforce/CodeGen/codegen1/jaxformer/hf/codegen/modeling_codegen.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · c66149010337c505 · report
apply_rotary_pos_emb openlmlab/moss/models/modeling_moss.py community (archive-listed) ran Apache-2.0 (permissive) · d11e60ed4e63403d · report
create_sinusoidal_positions openlmlab/moss/models/modeling_moss.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · c2217cd556fe5607 · report
find_layers openlmlab/moss/models/quantization.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · a9e7f2cdf016b88b · report
get_pairs openlmlab/moss/models/tokenization_moss.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · c083e60f5001bd38 · report
parse_text openlmlab/moss/moss_web_demo_gradio.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 826ceb601fb31250 · report
rotate_every_two openlmlab/moss/models/modeling_moss.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 2e3bec9f0c9b1973 · report
trim_code eth-sri/sven/scripts/human_eval_gen.py community (archive-listed) ran · violated contract MIT (permissive) · f3ac5c7092505639 · report

Tasks

Code GenerationHumanEvalLanguage ModelingLanguage ModellingLarge Language ModelProgram Synthesis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: CodeGen

CodeGen

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