Unverified50% confidenceFactExact time
Prefix Tuning learns a trainable virtual prefix that serves as additional key-value pairs in attention computation; Prompt Tuning is its simplified variant, learning only soft prompt vectors at the input side.
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMiniMind covers the complete pipeline including Tokenizer training, pre-training, supervised fine-tuning (SFT), LoRA fine-tuning, DPO reinforcement learning, and model distillation.71% similarUnverifiedFine-tuning methods include supervised fine-tuning and reinforcement with a grader.68% similarUnverifiedA common approach is to first train a lightweight conditioning module (such as a conditioning head or adapter) on a small amount of data, then at inference time superimpose its output as a logits bias, thereby balancing learning capability and real-time controllability.67% similarUnverifiedConverting vocabulary from passive recognition to active use requires repeated practice and output in authentic contexts; mere vocabulary exposure needs to be paired with active recall testing to achieve deep learning.66% similarUnverifiedThe learnable routing function differs from fixed sparse attention (such as local windows and fixed-stride jumps) by allowing the model to learn during training where it should attend.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1093833API
curl https://kongchang.com/api/v1/knowledge/claims/1093833MCP
get_claim(id=1093833)