Papers › CodeKGC: Code Language Model for Generative Knowledge Graph Construction

CodeKGC: Code Language Model for Generative Knowledge Graph Construction

18 Apr 2023arXiv:2304.09048archive 2025-07-28

Zhen Bi, Jing Chen, Yinuo Jiang, Feiyu Xiong, Wei Guo, Huajun Chen, Ningyu Zhang

Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model trained on structured data such as code has demonstrated impressive capability in understanding natural language for structural prediction and reasoning tasks. Intuitively, we address the task of generative knowledge graph construction with code language model: given a code-format natural language input, the target is to generate triples which can be represented as code completion tasks. Specifically, we develop schema-aware prompts that effectively utilize the semantic structure within the knowledge graph. As code inherently possesses structure, such as class and function definitions, it serves as a useful model for prior semantic structural knowledge. Furthermore, we employ a rationale-enhanced generation method to boost the performance. Rationales provide intermediate steps, thereby improving knowledge extraction abilities. Experimental results indicate that the proposed approach can obtain better performance on benchmark datasets compared with baselines. Code and datasets are available in https://github.com/zjunlp/DeepKE/tree/main/example/llm.

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 16 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 14 ran (13 with no instrument failure; 1 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zjunlp/deepke officialmentioned in paperpytorchMITSyntology: 16 samples, 14 ran (1 instrument-failed) · 2 unverified report
zjunlp/DeepKE officialpytorchSyntology: 16 samples, 14 ran (1 instrument-failed) · 2 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

16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
13ran
2unverified

Licence: 1 of the 16 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zjunlp/deepke. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zjunlp/deepke official repository 16 samples, 14 ran (1 instrument-failed) · 2 unverified
chunks in 16 papers src/deepke/relation_extraction/document/prepro.py ran fingerprinted MIT (permissive) · b6545335b7f399a2 · report fixture: signature l:list/1/int, n:int/0/int · returned list · level recorded 2026-09-26
collate_fn in 500 papers src/deepke/relation_extraction/document/utils.py ran MIT (permissive) · 20c8771d9d2aae90 · report fixture: signature batch:list/1/dict · returned tuple · level recorded 2026-09-26
collate_fn_sample src/deepke/relation_extraction/document/utils.py ran MIT (permissive) · 53be30fa2bb69d92 · report fixture: signature batch:list/1/dict · returned tuple · level recorded 2026-09-26
find_head_idx src/deepke/triple_extraction/PRGC/dataloader_utils.py ran fingerprinted MIT (permissive) · 6adefb5e4abb5be2 · report fixture: signature source:list/1/int, target:list/1/int · returned int · level recorded 2026-09-26
gen_train_facts src/deepke/relation_extraction/document/evaluation.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 705aa67db81dcc32 · report fixture: signature data_file_name:str/0/str, truth_dir:str/0/str · returned set · level recorded 2026-09-22
get_labels in 42 papers src/deepke/relation_extraction/few_shot/generate_k_shot.py ran MIT (permissive) · 0858952626966671 · report fixture: signature path:str/0/str, name:str/0/str, negative_label:str/0/str · returned list · level recorded 2026-09-25
get_metrics in 46 papers src/deepke/triple_extraction/PRGC/evaluate.py ran MIT (permissive) · 626bdc34ef9914c2 · report fixture: signature correct_num:int/0/int, predict_num:int/0/int, gold_num:int/0/int · returned dict · level recorded 2026-09-26
multilabel_categorical_crossentropy in 6 papers src/deepke/relation_extraction/document/losses.py ran fingerprinted MIT (permissive) · 9f47bb60899af064 · report fixture: signature y_true:Tensor/2/float, y_pred:Tensor/2/float · returned Tensor · level recorded 2026-09-25
official_evaluate src/deepke/relation_extraction/document/evaluation.py ran MIT (permissive) · fd5637cef4c93295 · report fixture: signature tmp:list/1/dict, path:str/0/str · returned tuple · level recorded 2026-09-25
process_long_input src/deepke/relation_extraction/document/prepro.py ran MIT (permissive) · 1caea7819d2e4841 · report fixture: signature model:callable/0/?, input_ids:Tensor/2/int, attention_mask:Tensor/2/float, start_tokens:list/1/int, end_tokens:list/1/int · returned tuple · level recorded 2026-09-25
read_examples in 23 papers src/deepke/triple_extraction/PRGC/dataloader_utils.py ran MIT (permissive) · 402533ae0c194b8a · report fixture: signature data_dir:str/0/str, data_sign:str/0/str, rel2idx:dict/0/? · returned list · level recorded 2026-09-25
span2str src/deepke/triple_extraction/PRGC/evaluate.py ran MIT (permissive) · 94ab66ec54e9046e · report fixture: signature triples:list/1/tuple, tokens:list/1/str · returned list · level recorded 2026-09-26
split_label_words src/deepke/relation_extraction/few_shot/get_label_word.py ran MIT (permissive) · 3e44103f6e52ca2f · report fixture: signature tokenizer:callable/0/?, label_list:list/1/str · returned Tensor · level recorded 2026-09-26
to_official src/deepke/relation_extraction/document/evaluation.py ran MIT (permissive) · 25620f5a71d51a9f · report fixture: signature args:Args/0/?, preds:ndarray/2/float, features:list/1/dict · returned list · level recorded 2026-09-25
convert in 76 papers src/deepke/triple_extraction/PRGC/dataloader_utils.py unverified MIT (permissive) · 859f514ce96f405e · report
evaluate in 514 papers src/deepke/triple_extraction/PRGC/evaluate.py unverified MIT (permissive) · 7b0a68af7010382a · report

Tasks

Code CompletionLanguage ModelingLanguage Modellinggraph construction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

fail

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