{"url":"/task/text-to-code-generation","name":"Text-to-Code Generation","slug":"text-to-code-generation","description_markdown":"**Text-to-Code Generation** is a task where we can generate code based on the natural language description.\r\n\r\nSource: [Text-to-code Generation with TensorFlow, 🤗 & MBPP](https://www.kaggle.com/code/rhtsingh/text-to-code-generation-with-tensorflow-mbpp)","categories":[{"name":"Computer Code","url":"/area/computer-code"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":20,"papers_with_code":12,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":10,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-to-code-generation-on-codexglue-concode","slug":"text-to-code-generation-on-codexglue-concode","dataset":"CodeXGLUE - CONCODE","dataset_url":"/dataset/codexglue","rows_in_archive":2,"metrics":["BLEU","CodeBLEU","EM"],"first_row_in_archive_order":{"model":"CodeT5","paper_title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","paper_url":"/paper/codet5-identifier-aware-unified-pre-trained","paper_date":"2021-09-02","arxiv_id":"2109.00859","code_links":[{"title":"salesforce/codet5","url":"https://github.com/salesforce/codet5"},{"title":"salesforce/coderl","url":"https://github.com/salesforce/coderl"},{"title":"awsm-research/vulrepair","url":"https://github.com/awsm-research/vulrepair"},{"title":"jetbrains-research/commit_message_generation","url":"https://github.com/jetbrains-research/commit_message_generation"},{"title":"fewshotcdcs/cdcs","url":"https://github.com/fewshotcdcs/cdcs"}],"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/codexglue","name":"CodeXGLUE","full_name":"","num_papers_in_archive":205},{"url":"/dataset/codecontests","name":"CodeContests","full_name":"","num_papers_in_archive":84},{"url":"/dataset/pytorrent","name":"PyTorrent","full_name":"PyTorrent","num_papers_in_archive":5},{"url":"/dataset/safim","name":"SAFIM","full_name":"Syntax-Aware Fill-In-the-Middle","num_papers_in_archive":5},{"url":"/dataset/blendnet","name":"BlendNet","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cadbench","name":"CADBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/micro25","name":"MICRO25","full_name":"","num_papers_in_archive":1},{"url":"/dataset/res-q","name":"RES-Q","full_name":"RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository Scale","num_papers_in_archive":1},{"url":"/dataset/verireason-rtl-coder-7b-reasoning-tb","name":"Verireason-RTL-Coder_7b_reasoning_tb","full_name":"VeriReason Verilog Dataset with Reasoning, Testbench, and Simulation Results","num_papers_in_archive":1},{"url":"/dataset/verireason-rtl-coder-7b-reasoning-tb-simple","name":"Verireason-RTL-Coder_7b_reasoning_tb_simple","full_name":"Simple Problems of VeriReason Verilog Dataset with Reasoning, Testbench, and Simulation Results","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":12,"of":12,"tagged_in_all":20,"items":[{"url":"/paper/codexglue-a-machine-learning-benchmark","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","date":"2021-02-09","arxiv_id":"2102.04664","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","arxiv_id":"2109.00859","repositories_listed":5,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/magicoder-source-code-is-all-you-need","title":"Magicoder: Empowering Code Generation with OSS-Instruct","date":"2023-12-04","arxiv_id":"2312.02120","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/bridging-the-gap-between-open-source-and","title":"Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA","date":"2025-06-11","arxiv_id":"2506.09657","repositories_listed":1,"syntology":null},{"url":"/paper/planning-driven-programming-a-large-language","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","date":"2024-11-21","arxiv_id":"2411.14503","repositories_listed":1,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/inversecoder-unleashing-the-power-of","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","date":"2024-07-08","arxiv_id":"2407.05700","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_unverified":0,"n_pointer_only":11}},{"url":"/paper/from-words-to-routes-applying-large-language","title":"Can Large Language Models Solve Robot Routing?","date":"2024-03-16","arxiv_id":"2403.10795","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-language-models-of-code-with-global","title":"Guiding Language Models of Code with Global Context using Monitors","date":"2023-06-19","arxiv_id":"2306.10763","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/code-execution-with-pre-trained-language","title":"Code Execution with Pre-trained Language Models","date":"2023-05-08","arxiv_id":"2305.05383","repositories_listed":1,"syntology":null},{"url":"/paper/c3po-a-lightweight-copying-mechanism-for","title":"C3PO: A Lightweight Copying Mechanism for Translating Pseudocode to Code","date":"2022-11-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pangu-coder-program-synthesis-with-function","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","date":"2022-07-22","arxiv_id":"2207.11280","repositories_listed":1,"syntology":null},{"url":"/paper/structcoder-structure-aware-transformer-for","title":"StructCoder: Structure-Aware Transformer for Code Generation","date":"2022-06-10","arxiv_id":"2206.05239","repositories_listed":1,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}