Unverified80% confidenceFactTime unknown
阿里团队发现强化学习训练不会导致模型其他能力下降，反而会带来全面协同提升，与传统微调中的灾难性遗忘问题形成对比
1
Sources
80%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Unverified专项优化的AI模型在特定领域可能表现不及通用基础模型，这与深度学习中的灾难性遗忘现象有关77% similarUnverified样例学习效应表明对初学者而言学习已解决的例题比自主解题更有效71% similarUnverifiedThe root cause of rising hallucination rates in reasoning models is misaligned incentives: reinforcement learning training causes models to tend to generate detailed and persuasive chains of thought, and human evaluators give higher scores to more elaborately argued answers, even when they contain factual errors.70% similarUnverifiedThe teacher model outputs in distillation training rarely include self-correction examples, causing student models to form an implicit belief that "strong models don't make mistakes," leading them to repeat rather than correct when verification fails.70% similarVerifiedThe core challenge of internalizing knowledge into model parameters is the Catastrophic Forgetting problem, which is a difficulty not yet fully resolved in the field of continual learning.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/23199API
curl https://kongchang.com/api/v1/knowledge/claims/23199MCP
get_claim(id=23199)