Papers › Learning Code Preference via Synthetic Evolution

Learning Code Preference via Synthetic Evolution

4 Oct 2024arXiv:2410.03837archive 2025-07-28

Jiawei Liu, Thanh Nguyen, Mingyue Shang, Hantian Ding, Xiaopeng Li, Yu Yu, Varun Kumar, Zijian Wang

Large Language Models (LLMs) have recently demonstrated remarkable coding capabilities. However, assessing code generation based on well-formed properties and aligning it with developer preferences remains challenging. In this paper, we explore two key questions under the new challenge of code preference learning: (i) How do we train models to predict meaningful preferences for code? and (ii) How do human and LLM preferences align with verifiable code properties and developer code tastes? To this end, we propose CodeFavor, a framework for training pairwise code preference models from synthetic evolution data, including code commits and code critiques. To evaluate code preferences, we introduce CodePrefBench, a benchmark comprising 1364 rigorously curated code preference tasks to cover three verifiable properties-correctness, efficiency, and security-along with human preference. Our evaluation shows that CodeFavor holistically improves the accuracy of model-based code preferences by up to 28.8%. Meanwhile, CodeFavor models can match the performance of models with 6-9x more parameters while being 34x more cost-effective. We also rigorously validate the design choices in CodeFavor via a comprehensive set of controlled experiments. Furthermore, we discover the prohibitive costs and limitations of human-based code preference: despite spending 23.4 person-minutes on each task, 15.1-40.3% of tasks remain unsolved. Compared to model-based preference, human preference tends to be more accurate under the objective of code correctness, while being sub-optimal for non-functional objectives.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (6 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

amazon-science/llm-code-preference officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 9 samples, 8 ran (2 instrument-failed) · 1 unverified 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

9 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
5ran
1unverified

Licence: 9 of the 9 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 amazon-science/llm-code-preference. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

amazon-science/llm-code-preference official repository 9 samples, 8 ran (2 instrument-failed) · 1 unverified
datagen_inference codefavor/prompt/critic_evol.py ran fingerprinted licence not identified · pointer only · 3a40321ab74c0bc2 · report fixture: signature instruction:str/0/str, attempt1:str/0/str · returned str · level recorded 2026-09-24
fewshot_template_improve codefavor/prompt/critic_evol.py ran licence not identified · pointer only · 898b72c5ee01636a · report fixture: signature instruction:str/0/str, attempt1:str/0/str, reflection:str/0/str, criteria:str/0/str, attempt2:str/0/str, feedback:str/0/str · returned str · level recorded 2026-09-24
fewshot_template_no_improve codefavor/prompt/critic_evol.py ran fingerprinted licence not identified · pointer only · fc13e41d350f62cb · report fixture: signature instruction:str/0/str, attempt1:str/0/str, reflection:str/0/str · returned str · level recorded 2026-09-24
hacky_assistant_stop_seq codefavor/provider/base.py ran · our draft was wrong licence not identified · pointer only · bfb3f9ec4b555806 · report fixture: signature tokenizer:MockTokenizer/0/? · returned str · level recorded 2026-09-24
pairwise_classification_template codefavor/template.py ran fingerprinted licence not identified · pointer only · 74e1c40ca345d7ce · report fixture: signature instruction:str/0/str, code1:str/0/str, code2:str/0/str, criteria:str/0/str · returned str · level recorded 2026-09-24
pairwise_cot_template codefavor/template.py ran fingerprinted licence not identified · pointer only · da043ad281c84014 · report fixture: signature instruction:str/0/str, code1:str/0/str, code2:str/0/str, criteria:str/0/str · returned str · level recorded 2026-09-24
response_parser codefavor/evaluate.py ran · honoured contract fingerprinted licence not identified · pointer only · 58badd651ef12b99 · report fixture: signature response:str/0/str · returned int · level recorded 2026-09-24
task_md5 codefavor/evaluate.py ran · our draft was wrong licence not identified · pointer only · 1238c597ba115abe · report fixture: signature task:dict/0/? · returned str · level recorded 2026-09-24
merge_models codefavor/merge_model.py unverified licence not identified · pointer only · 081407e2793ad7f0 · report

Tasks

Code Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNSET

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