{ "metadata": { "version": "1.3.0", "updated_at": "2026-11-14", "search_refreshed_at": "2026-10-19", "topic_id": "training-compilation", "name": "Compilation through training", "definition": "Generate examples from a function specification and train a reusable neural program.", "record_count": 1, "topic_url": "https://programasweights.com/reading-list/guides/compilation/#training-compilation", "source_url": "https://programasweights.com/reading-list/data/papers.json" }, "comparisons": [ { "title": "Fast prediction and training", "text": "PAW’s fast compiler predicts a program. Compile by Training starts from that prediction, generates examples, and trains an adapter. Both use the same runtime interface; the extra training improves semantic accuracy on FuzzyBench-Hard at a higher compilation cost.", "source_ids": [ "2607.02512", "2609.04199" ], "source_urls": [ "https://arxiv.org/html/2607.02512v1#S3", "https://arxiv.org/html/2609.04199v1#S3", "https://arxiv.org/html/2609.04199v1#S5" ], "source_labels": [ "PAW compiler implementations", "Compile by Training method", "Compile by Training evaluation" ] } ], "demos": [ ], "papers": [ { "id": "2609.04199", "title": "Compile by Training: Turning Natural-Language Specifications into Local Neural Functions", "authors": "Yuntian Deng, Pengyu Nie, Stuart Shieber", "first_public": "2026-09-03", "first_public_source": "https://arxiv.org/abs/2609.04199", "arxiv_first_submission": "2026-09-03", "date_label": "arXiv v1", "arxiv": "2609.04199", "paper_url": "https://arxiv.org/abs/2609.04199", "original_url": "https://arxiv.org/html/2609.04199v1", "venue": "EMNLP 2026 System Demonstrations", "venue_source": "https://aclanthology.org/2026.emnlp-demos.78/", "lens": [ "neural-programs", "training-compilation" ], "related_terms": [ "compile by training", "training-based compilation", "specification-specific optimization", "synthetic supervision", "local neural function", "FuzzyBench-Hard", "ProgramAsWeights" ], "summary": "Compiles a function description into a reusable local program by generating training examples and optimizing an adapter.", "contribution": "Makes task-specific training a software build step. Raises FuzzyBench-Hard semantic accuracy (LEM) from 22.4% to 83.6% and demonstrates composition in a website helper, avatar control, and English–Claudish translation.", "program_form": "A LoRA adapter, runtime prompt, specification, and interpreter metadata in a PAW program.", "conditioning": "The specification guides teacher synthesis. PAW’s fast compiler supplies the initial adapter and runtime prompt.", "execution": "A frozen Qwen3-0.6B interpreter runs the saved function locally without further teacher calls.", "relationship": "Extends PAW with training at compile time while keeping its program format and runtime interface.", "relationship_source": "https://arxiv.org/html/2609.04199v1#S1", "project_url": "https://programasweights.com/playground?compiler=paw-ft-bs48", "demo_url": "https://programasweights.com/playground?compiler=paw-ft-bs48", "code_url": "https://github.com/programasweights/compile-by-training", "provenance": "September 2026 arXiv paper; published in EMNLP 2026 System Demonstrations, pages 830–839.", "first_public_note": "The paper reports public-service measurements from May 2026.", "author_names": [ "Yuntian Deng", "Pengyu Nie", "Stuart Shieber" ], "record_url": "https://programasweights.com/reading-list/papers/2609.04199/", "legacy_record_url": "https://programasweights.com/reading-list/papers/#paper-2609-04199", "citation_date": "2026", "json_url": "https://programasweights.com/reading-list/papers/2609.04199/record.json", "markdown_url": "https://programasweights.com/reading-list/papers/2609.04199/index.md", "bibtex_url": "https://programasweights.com/reading-list/papers/2609.04199/citation.bib", "csl_url": "https://programasweights.com/reading-list/papers/2609.04199/citation.csl.json", "publication": { "title": "Compile by Training: Turning Natural-Language Specifications into Local Neural Functions", "author_names": [ "Yuntian Deng", "Pengyu Nie", "Stuart Shieber" ], "year": 2026, "type": "paper-conference", "container_title": "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", "editor_names": [ "Sweta Agrawal", "Alberto Abad" ], "month": 10, "month_name": "October", "address": "Budapest, Hungary", "publisher": "Association for Computational Linguistics", "pages": "830-839", "bibtex_pages": "830--839", "doi": "10.18653/2026.emnlp-demos.78", "isbn": "979-8-89176-461-3", "url": "https://aclanthology.org/2026.emnlp-demos.78/", "source_url": "https://aclanthology.org/2026.emnlp-demos.78/", "verified_at": "2026-11-06", "preferred_citation": true, "citation_key": "deng-etal-2026-compile" }, "publication_bibtex_url": "https://programasweights.com/reading-list/papers/2609.04199/publication.bib", "publication_csl_url": "https://programasweights.com/reading-list/papers/2609.04199/publication.csl.json", "preferred_citation": { "title": "Compile by Training: Turning Natural-Language Specifications into Local Neural Functions", "author_names": [ "Yuntian Deng", "Pengyu Nie", "Stuart Shieber" ], "year": 2026, "type": "paper-conference", "container_title": "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", "editor_names": [ "Sweta Agrawal", "Alberto Abad" ], "month": 10, "month_name": "October", "address": "Budapest, Hungary", "publisher": "Association for Computational Linguistics", "pages": "830-839", "bibtex_pages": "830--839", "doi": "10.18653/2026.emnlp-demos.78", "isbn": "979-8-89176-461-3", "url": "https://aclanthology.org/2026.emnlp-demos.78/", "source_url": "https://aclanthology.org/2026.emnlp-demos.78/", "verified_at": "2026-11-06", "preferred_citation": true, "citation_key": "deng-etal-2026-compile" }, "citation_url": "https://aclanthology.org/2026.emnlp-demos.78/", "preprint_citation_date": "2026-09-03", "preprint_bibtex_url": "https://programasweights.com/reading-list/papers/2609.04199/preprint.bib", "preprint_csl_url": "https://programasweights.com/reading-list/papers/2609.04199/preprint.csl.json", "method_comparisons": [ { "title": "Fast prediction and training", "text": "PAW’s fast compiler predicts a program. Compile by Training starts from that prediction, generates examples, and trains an adapter. Both use the same runtime interface; the extra training improves semantic accuracy on FuzzyBench-Hard at a higher compilation cost.", "source_ids": [ "2607.02512", "2609.04199" ], "source_urls": [ "https://arxiv.org/html/2607.02512v1#S3", "https://arxiv.org/html/2609.04199v1#S3", "https://arxiv.org/html/2609.04199v1#S5" ], "source_labels": [ "PAW compiler implementations", "Compile by Training method", "Compile by Training evaluation" ], "topic_id": "training-compilation", "topic_label": "Compilation through training", "topic_url": "https://programasweights.com/reading-list/guides/compilation/#training-compilation" } ], "summary_zh": "根据函数说明生成训练样本，再训练 LoRA 适配器，将一次函数定义构建成可复用的本地神经程序。", "translations": { "zh-CN": { "summary": "根据函数说明生成训练样本，再训练 LoRA 适配器，将一次函数定义构建成可复用的本地神经程序。", "relationship": "在 PAW 的快速编译结果上增加针对当前函数的训练，保留 PAW 的程序格式和解释器接口。", "program_form": "包含 LoRA 适配器、运行提示词、函数说明和解释器元数据的 PAW 程序。", "conditioning": "函数说明指导教师模型生成样本，PAW 快速编译器提供初始适配器与运行提示词。", "execution": "冻结的 Qwen3-0.6B 解释器执行保存的函数，不再调用教师模型。" } } } ] }