{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/codegen","slug":"codegen","name":"CodeGen","full_name":"CodeGen","full_name_withheld":false,"description_markdown":"**CodeGen** is an autoregressive transformers with next-token prediction language modeling as the learning objective trained on a natural language corpus and programming language data curated from GitHub.","description_state":"present","introduced_year":null,"introduced_by":{"title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","paper":"/paper/a-conversational-paradigm-for-program","first_author":"Erik Nijkamp","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/a-conversational-paradigm-for-program"},"source":{"url":"https://arxiv.org/abs/2203.13474v5","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":25,"archive_num_papers":25,"papers_newest_first":[{"paper":"/paper/how-to-select-pre-trained-code-models-for","slug":"how-to-select-pre-trained-code-models-for","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","date":"2025-01-07","arxiv_id":"2501.03783","n_code_links":1,"syntology":null},{"paper":"/paper/does-your-neural-code-completion-model-use-my","slug":"does-your-neural-code-completion-model-use-my","title":"Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach","date":"2024-04-22","arxiv_id":"2404.14296","n_code_links":1,"syntology":null},{"paper":null,"slug":"codefort-robust-training-for-code-generation","title":"CodeFort: Robust Training for Code Generation Models","date":"2024-04-11","arxiv_id":"2405.01567","n_code_links":0,"syntology":null},{"paper":"/paper/bugs-in-large-language-models-generated-code","slug":"bugs-in-large-language-models-generated-code","title":"Bugs in Large Language Models Generated Code: An Empirical Study","date":"2024-03-13","arxiv_id":"2403.08937","n_code_links":1,"syntology":null},{"paper":null,"slug":"llamoco-instruction-tuning-of-large-language","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","date":"2024-03-02","arxiv_id":"2403.01131","n_code_links":0,"syntology":null},{"paper":"/paper/humaneval-on-latest-gpt-models-2024","slug":"humaneval-on-latest-gpt-models-2024","title":"HumanEval on Latest GPT Models -- 2024","date":"2024-02-20","arxiv_id":"2402.14852","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["daniel442li/gpt-human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/crosscodeeval-a-diverse-and-multilingual","slug":"crosscodeeval-a-diverse-and-multilingual","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","date":"2023-10-17","arxiv_id":"2310.11248","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/neural-rankers-for-code-generation-via-inter","slug":"neural-rankers-for-code-generation-via-inter","title":"Functional Overlap Reranking for Neural Code Generation","date":"2023-10-16","arxiv_id":"2311.03366","n_code_links":2,"syntology":null},{"paper":null,"slug":"large-language-model-aware-in-context","title":"Large Language Model-Aware In-Context Learning for Code Generation","date":"2023-10-15","arxiv_id":"2310.09748","n_code_links":0,"syntology":null},{"paper":"/paper/biocoder-a-benchmark-for-bioinformatics-code","slug":"biocoder-a-benchmark-for-bioinformatics-code","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","date":"2023-08-31","arxiv_id":"2308.16458","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gersteinlab/biocoder"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/comex-a-tool-for-generating-customized-source","slug":"comex-a-tool-for-generating-customized-source","title":"COMEX: A Tool for Generating Customized Source Code Representations","date":"2023-07-10","arxiv_id":"2307.04693","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-robustness-of-large-language","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","date":"2023-06-26","arxiv_id":"2306.14583","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-large-language-models-for","slug":"fine-tuning-large-language-models-for","title":"Fine-Tuning Large Language Models for Answering Programming Questions with Code Snippets","date":"2023-06-26","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/how-effective-are-neural-networks-for-fixing","slug":"how-effective-are-neural-networks-for-fixing","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","date":"2023-05-29","arxiv_id":"2305.18607","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lin-tan/llm-vul"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/prompting-with-pseudo-code-instructions","slug":"prompting-with-pseudo-code-instructions","title":"Prompting with Pseudo-Code Instructions","date":"2023-05-19","arxiv_id":"2305.11790","n_code_links":2,"syntology":{"ran":6,"of":13,"n_ran_checked":6,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["mayank31398/pseudo-code-instructions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-the-effectiveness-of-large-language","slug":"exploring-the-effectiveness-of-large-language","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","date":"2023-04-30","arxiv_id":"2305.00418","n_code_links":1,"syntology":null},{"paper":"/paper/learning-performance-improving-code-edits","slug":"learning-performance-improving-code-edits","title":"Learning Performance-Improving Code Edits","date":"2023-02-15","arxiv_id":"2302.07867","n_code_links":2,"syntology":{"ran":8,"of":19,"n_ran_checked":3,"n_instrument":5,"unverified":11,"pointer_only":19,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","official":{"repos":["madaan/pie-perf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":"/paper/controlling-large-language-models-to-generate","slug":"controlling-large-language-models-to-generate","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","date":"2023-02-10","arxiv_id":"2302.05319","n_code_links":1,"syntology":null},{"paper":"/paper/execution-based-evaluation-for-open-domain","slug":"execution-based-evaluation-for-open-domain","title":"Execution-Based Evaluation for Open-Domain Code Generation","date":"2022-12-20","arxiv_id":"2212.10481","n_code_links":1,"syntology":null},{"paper":"/paper/recode-robustness-evaluation-of-code","slug":"recode-robustness-evaluation-of-code","title":"ReCode: Robustness Evaluation of Code Generation Models","date":"2022-12-20","arxiv_id":"2212.10264","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["amazon-science/recode"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/benchmarking-large-language-models-for","slug":"benchmarking-large-language-models-for","title":"Benchmarking Large Language Models for Automated Verilog RTL Code Generation","date":"2022-12-13","arxiv_id":"2212.11140","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shailja-thakur/vgen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-the-compositional-generalization-gap-of-in","title":"On the Compositional Generalization Gap of In-Context Learning","date":"2022-11-15","arxiv_id":"2211.08473","n_code_links":0,"syntology":null},{"paper":"/paper/extracting-meaningful-attention-on-source","slug":"extracting-meaningful-attention-on-source","title":"Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration","date":"2022-10-11","arxiv_id":"2210.05506","n_code_links":1,"syntology":null},{"paper":"/paper/a-scalable-and-extensible-approach-to","slug":"a-scalable-and-extensible-approach-to","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","date":"2022-08-17","arxiv_id":"2208.08227","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nuprl/multipl-e"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-conversational-paradigm-for-program","slug":"a-conversational-paradigm-for-program","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","date":"2022-03-25","arxiv_id":"2203.13474","n_code_links":8,"syntology":{"ran":10,"of":10,"n_ran_checked":3,"n_instrument":7,"unverified":0,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","official":{"repos":["salesforce/CodeGen","salesforce/jaxformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"papers_shown":25,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":25,"with_a_code_link":19,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":25,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":10,"papers_where_code_ran_first_page":"/method/codegen/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/codegen/papers/ran/1","json":"/method/codegen/papers/ran/1.json","rows":10}],"tasks":[{"task":"/task/code-generation","name":"Code Generation","papers":19},{"task":"/task/humaneval","name":"HumanEval","papers":6},{"task":"/task/language-modelling","name":"Language Modelling","papers":5},{"task":"/task/program-synthesis","name":"Program Synthesis","papers":4},{"task":null,"name":"mbpp","papers":4},{"task":"/task/code-completion","name":"Code Completion","papers":3},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":3},{"task":"/task/language-modeling","name":"Language Modeling","papers":3},{"task":"/task/benchmarking","name":"Benchmarking","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":2},{"task":"/task/large-language-model","name":"Large Language Model","papers":2},{"task":"/task/memorization","name":"Memorization","papers":2},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/code-repair","name":"Code Repair","papers":1},{"task":"/task/code-summarization-1","name":"Code Summarization","papers":1},{"task":"/task/model-selection","name":"Model Selection","papers":1},{"task":"/task/program-repair","name":"Program Repair","papers":1},{"task":"/task/prompt-engineering","name":"Prompt Engineering","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1}],"tasks_shown":20,"n_tasks":25,"usage_by_year":[{"year":"2022","papers":7},{"year":"2023","papers":12},{"year":"2024","papers":5},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/codegen"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=CodeGen","read_at":"2026-10-05T00:53:49+00:00","query":"CodeGen","kind":"paper","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2203.13474","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"unresolved_bearers","may_be_wrong_sense":true,"bearers_found":2,"served":null,"leading_other_bearer":{"arxiv_id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","citations":1576,"named_by":["title_prefix"],"bearer_name":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","ask_with":"have('2203.13474')"},"n_other_bearers_listed":2,"note":"Nothing resolved to 'CodeGen' by name, but 2 thing(s) here DECLARE that name -- most cited: the paper 'CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis' (arXiv:2203.13474, 1,576 citations). That is a RESOLUTION miss, not a coverage gap: the corpus holds the name under a spelling the lookup did not reach. Ask again with an entry of `also_named`."},"name_competition_text":"Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis” (arXiv:2203.13474, 1,576 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach.","near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"c1a138787de3dc15a79b3774c58357d7b7f3134349d9c7652ea55489f3cbf93a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}