Unverified50% confidenceFactExact time
When fine-tuning large language models sequentially, full-parameter fine-tuning almost inevitably leads to significant degradation of existing capabilities.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe emergent capability of large language models refers to the complex reasoning ability that suddenly manifests after the parameter scale surpasses a certain threshold.76% similarVerifiedThe inference speed of large language models is constrained by the nature of autoregressive generation, which can only produce one token at a time and depends on all preceding tokens, making true parallelization impossible.75% similarVerifiedWhen language models are repeatedly trained on data generated by themselves or similar models, systematic degradation occurs, with the diversity of model outputs decreasing with each generation and the tail information of the distribution gradually being lost.74% similarUnverifiedA language model's understanding of sequence features is statistical rather than based on explicit biochemical rules, which may simultaneously produce both creative and obviously erroneous predictions.73% similarUnverified扩散语言模型在复杂推理、指令遵循和思维链等方面面临结构性挑战，可控性弱于自回归模型72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1109276API
curl https://kongchang.com/api/v1/knowledge/claims/1109276MCP
get_claim(id=1109276)