面向热带植物、水生生物和外来宠物的证据驱动性状提取的注册约束LLM流水线
A Registry-Bound LLM Pipeline for Evidence-Grounded Trait Extraction across Tropical Plants, Aquatic Species, and Exotic Pets
AI总结：
提出一种注册约束的大语言模型流水线，通过四种机制（受控词汇注册表、逐行证据引用、置信度标签、多版本保存）从热带物种百科全书中大规模提取证据驱动的结构化性状记录，在409,820个物种上实现99.985%的覆盖率和高置信度。
摘要：
我们描述了一种注册约束的大语言模型提取流水线，能够在栽培热带植物、水生和宠物物种上大规模生成证据驱动的结构化性状记录。四种机制使LLM导出的行可审计：一个版本化的39键闭词汇性状注册表，将每个接受的值约束到类型化模式；每行逐字证据引用，将每个值绑定到源文本；每行置信度标签（高或中；低置信度在持久化前丢弃）；以及多版本保存。应用于热带物种百科全书中409,880个可发表物种，该流水线执行了706,220次运行，并在409,820个物种（99.985%）中持久化了5,489,881条性状记录，其中81.57%为高置信度。我们报告了三个验证层级，按证据强度递减：在全种群中，5,427,588条含证据的行中有90.12%的引用是源文本的逐字子串（排除一个合规性元性状后为93.49%）；在n=100的分层非红区行上进行的引用支持值审计结果为100/100（下限96.30%）；在n=50的红区行上进行的表面有效性审计结果为50/50接受（下限92.86%）。我们不声称每条记录的正确性；100%有待人工审核。贡献在于四种机制框架。
英文摘要：
We describe a registry-bound large-language-model extraction pipeline producing evidence-grounded structured trait records at scale, on cultivated tropical plant, aquatic, and pet species. Four mechanisms render LLM-derived rows auditable: a versioned 39-key closed-vocabulary trait registry constraining every admitted value to a typed schema; a per-row verbatim evidence quote tying each value to source text; a per-row confidence label (high or medium; low dropped pre-persist); and multi-version preservation. Applied to 409,880 publishable species from the Tropical Species Encyclopedia, the pipeline executed 706,220 runs and persisted 5,489,881 trait records across 409,820 species (99.985%), 81.57% at high confidence. We report three validation layers in descending evidentiary strength: at full population, 90.12% of 5,427,588 evidence-bearing rows have their quote as a verbatim source substring (93.49% excluding one compliance meta-trait); a quote-supports-value audit on n=100 stratified non-red-zone rows yielded 100/100 (lower bound 96.30%); face-validity on n=50 red-zone rows yielded 50/50 Accept (lower bound 92.86%). Per-record correctness is not claimed; 100% pending human curation. The contribution is the four-mechanism framework.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
