Unverified50% confidenceFactExact time
Adding the same constant to every similarity score in the softmax does not change the loss, so the model can arbitrarily choose the score range for unrelated texts, and the training process pays no attention to absolute scores whatsoever.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
Unverified用Minimax生成的训练数据具有确定性和完备性，理论上可覆盖井字棋所有合法局面，几乎不存在分布外问题65% similarUnverifiedThe frequency-aware training schedule adds no model parameters and does not change inference-time computation, making it a purely training-side improvement.65% similarUnverifiedDuring fine-tuning, the prompt format in the training phase must strictly match the inference phase; otherwise, performance degradation will occur without any error being reported.65% similarUnverifiedBoth adjustments—merging confused classes and calibrating the observation window—can recover accuracy without retraining the model.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/998012API
curl https://kongchang.com/api/v1/knowledge/claims/998012MCP
get_claim(id=998012)