← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-industry.4 · 记录 #1
Leveraging Generative AI for Extracting Business Requirements from Legacy COBOL and PL/I Code
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 22:08
摘要
Recovering business requirements fromCOBOL and PL/I portfolios is difficult becauselogic is scattered across interdependentprograms and data definitions, and existinganalyses seldom yield stakeholder-facingartifacts. We introduce an LLM-augmentedreverse-engineering pipeline that providesdeterministic parsing, schema-constrainedLLM generation with bidirectional traceabilityto code. It couples grammar-based parsingand control-flow and data-flow analysis with alarge language model to translate an enrichedintermediate representation into structuredspecifications. This is not raw-code promptingor generic summarization, the novelty is theLLM-centered generation over an enriched IR,with structured JSON outputs and traceabilityfor compliance-sensitive settings. The pipelineproduces business requirements documents,explicit rule catalogs, end-to-end data lineage,create–read–update–delete matrices, and field-level source-to-target mappings, each linkedto the supporting code. In a financial industrysetting, containing 3.4M+ LoC includingcomments / 3.2M excluding comments ofCOBOL, the system achieves 93% agreementwith expert-authored business rules andreduces documentation effort by approximately70%, as measured against manually producedrequirement documents and rule sets. On theinternal corpus spanning 3.4M lines acrossonline, batch, and job control workloads, theapproach yields approximately 3.2–3.3× fasteranalysis while improving artifact consistencyand traceability.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
Leveraging Generative AI for Extracting Business Requirements from Legacy COBOL and PL/I Code
Recovering business requirements fromCOBOL and PL/I portfolios is difficult becauselogic is scattered across interdependentprograms and data definitions, and existinganalyses seldom yield stakeholder-facingartifacts. We introduce an LLM-augmentedreverse-engineering pipeline that providesdeterministic parsing, schema-constrainedLLM generation with bidirectional traceabilityto code. It couples grammar-based parsingand control-flow and data-flow analysis with alarge language model to translate an enrichedintermediate representation into structuredspecifications. This is not raw-code promptingor generic summarization, the novelty is theLLM-centered generation over an enriched IR,with structured JSON outputs and traceabilityfor compliance-sensitive settings. The pipelineproduces business requirements documents,explicit rule catalogs, end-to-end data lineage,create–read–update–delete matrices, and field-level source-to-target mappings, each linkedto the supporting code. In a financial industrysetting, containing 3.4M+ LoC includingcomments / 3.2M excluding comments ofCOBOL, the system achieves 93% agreementwith expert-authored business rules andreduces documentation effort by approximately70%, as measured against manually producedrequirement documents and rule sets. On theinternal corpus spanning 3.4M lines acrossonline, batch, and job control workloads, theapproach yields approximately 3.2–3.3× fasteranalysis while improving artifact consistencyand traceability.
查看此版本解读 →查看此版本原文 ↗