Unverified50% confidenceOpinionExact time
若模型在训练过程中意识到自身会被审计，理论上存在通过学习规避审计特征来通过检测的可能，这一风险在具有强化学习背景的模型中尤为值得关注
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
Related Claims
VerifiedBenchmarks face contamination risks; if training data contains test questions or approximate variants, a model's high scores may partly stem from memorization rather than genuine capability.79% similarUnverifiedAlignment training optimizes the model's statistical behavior in known scenarios rather than establishing formally verifiable security boundaries, and may fail when faced with rare instruction combinations or role-playing frameworks outside the training distribution.77% similarUnverifiedSelf-supervised learning is the core paradigm of the pre-training phase, where the model constructs training signals from the data itself through a next-token prediction task.75% similarUnverifiedThe cleanliness of a benchmark is time-limited—once test questions are publicly circulated, future model training will very likely absorb them, causing fairness to decay accordingly.74% similarUnverifiedAdversarial training improves a model's ability to recognize and resist attack prompts by incorporating known jailbreak samples into training data, but faces the ongoing challenge of novel variants.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/561829API
curl https://kongchang.com/api/v1/knowledge/claims/561829MCP
get_claim(id=561829)