中国畜禽种业2026，Vol.22Issue(7)：17-27,11.DOI:10.19543/j.cnki.1673-4556.20260507.001
GBNP-2026:面向畜禽遗传、育种、营养与生产的大语言模型专业问答能力评测基准
GBNP-2026:A benchmark for evaluating large language models'professional question-answering capabilities in animal genetics,breeding,nutrition,and production
摘要
Abstract
[Objective]Livestock-related QA is terminology-heavy and often involves indicators,parameters,and trade-offs in breeding and production plans.This study evaluates LLM professional usability using subjective responses and explicit scoring rubrics.[Methods]We built a Chinese vertical benchmark,the Genetics,Breeding,Nutrition,and Production Benchmark(GBNP-2026),with 510 subjective items(363 short-answer and 147 essay)spanning the same four domains,each with a reference answer,checkable scoring points,and domain tags.Nine open-and closed-source models were tested under a unified zero-shot,context-free protocol,scored by coverage and quality,followed by error attribution on low-score cases.[Results]Mean scores ranged from 64.03 to 83.99 and coverage from 70.6%to 91.9%.Essay items scored higher than short-answer items on average;breeding was the weakest domain for most models.Among 628 low-score samples,missing knowledge(37.3%)and hallucinations(25.0%)dominated.Missing-knowledge rates differed across domains(x²=8.42,P=0.038),highest in breeding(47.1%).[Conclusion]Compared with multiple-choice accuracy alone,coverage-plus-quality scoring helps separate capability gaps in this setting;strictly numerical or proof-style tasks still need a dedicated sub-benchmark.GBNP-2026 and the pipeline support reproducible comparison,error diagnosis,and data planning for SFT/RAG.关键词
大语言模型/题库评估/遗传育种/自动评分/领域评测Key words
Large language model/Question bank assessment/Genetic breeding/Automatic scoring/Domain evaluation分类
农业科技引用本文复制引用
肖成朋,金炜炜,孙桂荣,罗艳,顾兴健,陆明洲,康相涛,李文婷,李成林,雷艳茹,蔡钊,谢伯斐,王克君,郭玉洁,宫玉杰,李东华..GBNP-2026:面向畜禽遗传、育种、营养与生产的大语言模型专业问答能力评测基准[J].中国畜禽种业,2026,22(7):17-27,11.基金项目
国家自然科学基金(32422081) （32422081）
中原英才计划(育才系列):青年拔尖人才. （育才系列）
