Files
natural-memory-nm21/answerability_cosine.json
WpyQwq 643e22ecb9 Natural Memory NM2.1: 记忆路由器分叉、数据集缺陷修复与全轴评测证据
- 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
2026-09-19 11:11:31 +08:00

63 lines
1.2 KiB
JSON

{
"overall_auc": 0.6741,
"per_category": {
"alias_paraphrase": {
"n": 25,
"auc": null,
"mean_pos": 0.8255,
"mean_neg": null
},
"long_fact": {
"n": 25,
"auc": null,
"mean_pos": 0.7631,
"mean_neg": null
},
"multi_entity": {
"n": 25,
"auc": null,
"mean_pos": 0.7077,
"mean_neg": null
},
"multi_hop": {
"n": 25,
"auc": null,
"mean_pos": 0.7697,
"mean_neg": null
},
"near_miss": {
"n": 25,
"auc": null,
"mean_pos": 0.7452,
"mean_neg": null
},
"noise_context": {
"n": 25,
"auc": null,
"mean_pos": 0.6853,
"mean_neg": null
},
"unknown_attribute": {
"n": 25,
"auc": null,
"mean_pos": null,
"mean_neg": 0.7149
},
"update_conflict": {
"n": 25,
"auc": null,
"mean_pos": 0.7203,
"mean_neg": null
}
},
"best_threshold": {
"margin": 0.02,
"refused_unknown_pct": 40.0,
"false_refusal_pct": 3.43
},
"auc": {
"max": 0.6741,
"margin": 0.9413,
"zscore": 0.1767
}
}