20260601
This commit is contained in:
40
concepts/capability-degradation.md
Normal file
40
concepts/capability-degradation.md
Normal file
@@ -0,0 +1,40 @@
|
||||
---
|
||||
title: "能力退化 (Capability Degradation)"
|
||||
created: 2026-05-21
|
||||
type: concept
|
||||
tags: ["continual-learning", "catastrophic-forgetting"]
|
||||
sources: ["[[when-large-multimodal-models-confront-evolving-knowledge]]"]
|
||||
---
|
||||
|
||||
# 能力退化 (Capability Degradation)
|
||||
|
||||
## 定义
|
||||
|
||||
能力退化是指 LMM 在注入新知识后,在**通用能力测试**(综合评估、OCR、多学科、指令遵循、数学推理、幻觉检测)上出现显著性能下降的现象。
|
||||
|
||||
## 量化数据(LLaVA-v1.5)
|
||||
|
||||
| 方法 | 平均退化 | 最严重退化项 |
|
||||
|------|---------|------------|
|
||||
| Full-FT | -25.89% | MIA-Bench (-61.93%), HallusionBench (-57.40%) |
|
||||
| LoRA | -25.74% | HallusionBench (-59.65%), MIA-Bench (-55.28%) |
|
||||
|
||||
## 测试维度(12 个基准,7 个维度)
|
||||
|
||||
1. 综合评估:MME, MMBench
|
||||
2. OCR:SEEDBench2 Plus, OCRBench
|
||||
3. 多学科:ScienceQA, MMMU
|
||||
4. 指令遵循:MIA-Bench
|
||||
5. 多轮对话:MMDU
|
||||
6. 数学推理:MathVista, MathVision
|
||||
7. 幻觉检测:POPE, HallusionBench
|
||||
|
||||
## 与灾难性遗忘的关系
|
||||
|
||||
能力退化是[[catastrophic-forgetting|灾难性遗忘]]在多模态知识注入场景下的具体表现。但本研究发现**部分退化可以通过知识感知增强缓解**,这是此前未被注意的现象。
|
||||
|
||||
## 参见
|
||||
|
||||
- [[knowledge-retention|知识保留]]
|
||||
- [[data-replay|数据回放]]
|
||||
- [[moe-lora|MoELoRA]]
|
||||
Reference in New Issue
Block a user