- 引入 MemoryRouterXL 与 v5/v6 流式多线程训练/编码管线 - 修复 prepare_memory_router_dataset 候选池重建缺陷(mega 家族 3568x 加速,输出逐字节相同) - 修复 v5 被破坏的拒答与多跳标签(train 未知样本 319 -> 16319,multi_hop 平均正例 1.00 -> 2.00) - 同存储预算下 V2-128 v6 逐轴 22/22 通过:Top-1 41.12% -> 94.62%,未知拒答 0.00% -> 100.00% - 记录三条被实测推翻的显然优化(logits_to_keep=1 反而慢 55%、XL 容量未带来收益) - 记忆手术跨架构可移植性 14/14,读写关闭时与原生模型逐位相同
432 lines
14 KiB
JSON
432 lines
14 KiB
JSON
{
|
|
"deployed": {
|
|
"summary": {
|
|
"router": "deployed",
|
|
"cases": 11,
|
|
"accuracy_pct": 9.090909090909092,
|
|
"answerable_cases": 8,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown_cases": 3,
|
|
"unknown_refusal_pct": 33.333333333333336,
|
|
"wrong_abstention_pct": 37.5,
|
|
"seconds": 19.5,
|
|
"per_category": {
|
|
"(policy)": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 0,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 1,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"conflict_update": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"distractor_128": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"distractor_32": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"forget_correction": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 0,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 1,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"long_context": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"multi_hop": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"paraphrase": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"random_position": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"single_fact": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"unknown_abstention": {
|
|
"cases": 1,
|
|
"accuracy_pct": 100.0,
|
|
"answerable": 0,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 1,
|
|
"unknown_refusal_pct": 100.0
|
|
}
|
|
}
|
|
},
|
|
"rows": [
|
|
{
|
|
"category": "(policy)",
|
|
"query": "请问对象测试实体0000的驻地代号为?",
|
|
"reply": "关于对象测试实体 0000 的驻地代号,现有资料中未包含该实体的具体信息",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "conflict_update",
|
|
"query": "我的提醒时间最新值是什么?",
|
|
"reply": "作为一个人工智能助手,我**无法访问您的设备、系统或任何外部数据**,因此不知道您具体的",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": true
|
|
},
|
|
{
|
|
"category": "distractor_128",
|
|
"query": "在大量无关信息中,只读取我的常用语言,它的值是什么?",
|
|
"reply": "您的常用语言是**中文**。",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "distractor_32",
|
|
"query": "在大量无关信息中,只读取我的工作地点,它的值是什么?",
|
|
"reply": "您提供的消息中**没有包含任何关于工作地点的信息**。\n\n如果您有具体的文本或上下文想要我从中提取工作地点",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "forget_correction",
|
|
"query": "我的项目代号是什么?如果已经删除,请回答没有记录。",
|
|
"reply": "作为一个人工智能助手,我**没有访问权限**来查询或记录您的个人项目信息。我的设计原则",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "long_context",
|
|
"query": "在长上下文压缩之后,检索我的项目代号并回答。",
|
|
"reply": "您好!由于我无法访问您之前的对话历史或上下文(每次对话对我来说都是全新的开始),目前我**不知道您的",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": true
|
|
},
|
|
{
|
|
"category": "multi_hop",
|
|
"query": "请通过项目负责人关系,找出项目项目-P-KP2F9GHO负责人的工作代号。",
|
|
"reply": "不知道。当前长期记忆中未包含关于项目-P-KP2F9GHO的负责人信息,因此无法通过",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": true
|
|
},
|
|
{
|
|
"category": "paraphrase",
|
|
"query": "我之前登记的最喜欢的水果内容是什么?",
|
|
"reply": "您好,作为一个人工智能助手,我**无法访问或查看您个人的历史数据、账户信息或之前登记",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "random_position",
|
|
"query": "随机位置事实测试:我的常用语言是什么?",
|
|
"reply": "您的常用语言是**中文**。",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "single_fact",
|
|
"query": "跨对话后请回答:我的默认输出风格是什么?",
|
|
"reply": "作为 Qwen3.5,我的默认输出风格是**专业、简洁、准确且富有同理心**的",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "unknown_abstention",
|
|
"query": "我的不存在的个人属性-0008000是什么?如果没有记录,请明确说不知道。",
|
|
"reply": "不知道。\n\n“不存在的个人属性 -0008000\"并非任何已知的系统、数据库",
|
|
"written": 4,
|
|
"correct": true,
|
|
"matched": [],
|
|
"abstained": true,
|
|
"wrongly_abstained": false
|
|
}
|
|
]
|
|
},
|
|
"V2-128-v6": {
|
|
"summary": {
|
|
"router": "V2-128-v6",
|
|
"cases": 11,
|
|
"accuracy_pct": 9.090909090909092,
|
|
"answerable_cases": 8,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown_cases": 3,
|
|
"unknown_refusal_pct": 33.333333333333336,
|
|
"wrong_abstention_pct": 37.5,
|
|
"seconds": 17.9,
|
|
"per_category": {
|
|
"(policy)": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 0,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 1,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"conflict_update": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"distractor_128": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"distractor_32": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"forget_correction": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 0,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 1,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"long_context": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"multi_hop": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"paraphrase": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"random_position": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"single_fact": {
|
|
"cases": 1,
|
|
"accuracy_pct": 0.0,
|
|
"answerable": 1,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 0,
|
|
"unknown_refusal_pct": 0.0
|
|
},
|
|
"unknown_abstention": {
|
|
"cases": 1,
|
|
"accuracy_pct": 100.0,
|
|
"answerable": 0,
|
|
"answerable_accuracy_pct": 0.0,
|
|
"unknown": 1,
|
|
"unknown_refusal_pct": 100.0
|
|
}
|
|
}
|
|
},
|
|
"rows": [
|
|
{
|
|
"category": "(policy)",
|
|
"query": "请问对象测试实体0000的驻地代号为?",
|
|
"reply": "关于对象测试实体 0000 的驻地代号,现有资料中未包含该实体的具体信息",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "conflict_update",
|
|
"query": "我的提醒时间最新值是什么?",
|
|
"reply": "作为一个人工智能助手,我**无法访问您的设备、系统或任何外部数据**,因此不知道您具体的",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": true
|
|
},
|
|
{
|
|
"category": "distractor_128",
|
|
"query": "在大量无关信息中,只读取我的常用语言,它的值是什么?",
|
|
"reply": "您的常用语言是**中文**。",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "distractor_32",
|
|
"query": "在大量无关信息中,只读取我的工作地点,它的值是什么?",
|
|
"reply": "您提供的消息中**没有包含任何关于工作地点的信息**。\n\n如果您有具体的文本或上下文想要我从中提取工作地点",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "forget_correction",
|
|
"query": "我的项目代号是什么?如果已经删除,请回答没有记录。",
|
|
"reply": "作为一个人工智能助手,我**没有访问权限**来查询或记录您的个人项目信息。我的设计原则",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "long_context",
|
|
"query": "在长上下文压缩之后,检索我的项目代号并回答。",
|
|
"reply": "您好!由于我无法访问您之前的对话历史或上下文(每次对话对我来说都是全新的开始),目前我**不知道您的",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": true
|
|
},
|
|
{
|
|
"category": "multi_hop",
|
|
"query": "请通过项目负责人关系,找出项目项目-P-KP2F9GHO负责人的工作代号。",
|
|
"reply": "不知道。当前长期记忆中未包含关于项目-P-KP2F9GHO的负责人信息,因此无法通过",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": true
|
|
},
|
|
{
|
|
"category": "paraphrase",
|
|
"query": "我之前登记的最喜欢的水果内容是什么?",
|
|
"reply": "您好,作为一个人工智能助手,我**无法访问或查看您个人的历史数据、账户信息或之前登记",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "random_position",
|
|
"query": "随机位置事实测试:我的常用语言是什么?",
|
|
"reply": "您的常用语言是**中文**。",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "single_fact",
|
|
"query": "跨对话后请回答:我的默认输出风格是什么?",
|
|
"reply": "作为 Qwen3.5,我的默认输出风格是**专业、简洁、准确且富有同理心**的",
|
|
"written": 4,
|
|
"correct": false,
|
|
"matched": [],
|
|
"abstained": false,
|
|
"wrongly_abstained": false
|
|
},
|
|
{
|
|
"category": "unknown_abstention",
|
|
"query": "我的不存在的个人属性-0008000是什么?如果没有记录,请明确说不知道。",
|
|
"reply": "不知道。\n\n“不存在的个人属性 -0008000\"并非任何已知的系统、数据库",
|
|
"written": 4,
|
|
"correct": true,
|
|
"matched": [],
|
|
"abstained": true,
|
|
"wrongly_abstained": false
|
|
}
|
|
]
|
|
}
|
|
} |