Unverified50% confidenceFactExact time
Large language models default to optimizing for plausibility rather than discriminability when generating options, because the training objective is to predict plausible words.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified大语言模型的训练目标是最大化下一个Token的预测概率而非最大化代码安全性，这两个目标在数学上不等价80% similarVerifiedLarge language models are optimized to make code look correct rather than to meet current-stage requirements; they are fundamentally probability-statistical machines that predict the next most likely token and excel at reproducing high-frequency patterns from training data.79% similarVerifiedLarge language models rely solely on parameter weights fixed during training for autoregressive generation at inference time, and have two inherent limitations: a knowledge cutoff and capability boundaries77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003498API
curl https://kongchang.com/api/v1/knowledge/claims/1003498MCP
get_claim(id=1003498)