ai-labeling: Prompt 1 v0.3(80%) + Prompt 3 v0.2(90%) + GT v0.4.2
Prompt 1 迭代 v0.1→v0.3: - 多选字段加显著篇幅门槛+从属零件反例教学 - 前沿科技vs横切类比拆清(技术主角测试) - 装备深解加同类体系/窄类别测试 - 跨域改为传播分类框(≥3域即标,非军事术语) - 全对率 40%→80% Prompt 3 开篇钩子 v0.1→v0.2: - 阅读范围扩至3段(导视+主持人+首段解说) - 强判定从紧迫感硬门槛改为6条独立路径 - 弱判定区分信息性提问vs悬念式提问 - 命中率 50%→90% ground-truth v0.4.2:ep008补标跨域 + 20期opening_hook全标注 脚本:run_labeling/summarize 支持 opening_hook,summarize改从源GT读取 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -44,6 +44,7 @@ ALL_EPISODES = list(range(1, 21))
|
||||
FIELD_PROMPT_MAP = {
|
||||
"narrative": "prompt2_narrative.md",
|
||||
"classification": "prompt1_classification.md",
|
||||
"opening_hook": "prompt3_opening_hook.md",
|
||||
}
|
||||
|
||||
|
||||
@@ -145,8 +146,8 @@ def main():
|
||||
parser.add_argument("--ep", type=int, help="单期编号")
|
||||
parser.add_argument("--all", action="store_true", help="跑全部")
|
||||
parser.add_argument("--model", default="mimo-v2.5-pro", help="模型键名")
|
||||
parser.add_argument("--field", default="narrative", choices=["narrative", "classification"],
|
||||
help="打标字段: narrative(叙事结构) / classification(4分类)")
|
||||
parser.add_argument("--field", default="narrative", choices=["narrative", "classification", "opening_hook"],
|
||||
help="打标字段: narrative(叙事结构) / classification(4分类) / opening_hook(开篇钩子)")
|
||||
args = parser.parse_args()
|
||||
if args.all:
|
||||
for ep in ALL_EPISODES:
|
||||
|
||||
Reference in New Issue
Block a user