Unverified50% confidenceFactExact time
Teacher forcing introduces the exposure bias problem: during training the real target token is fed as input, while during inference the model's own predicted token is used, and prediction errors accumulate and amplify in subsequent steps.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
Unverified自回归生成系统训练采用Teacher Forcing策略，推理阶段切换为自回归模式后产生分布偏移导致误差累积放大78% similarUnverifiedThe quality of a reinforcement learning environment directly determines what the model can learn, and an environment with loopholes may allow the model to learn to game the system.74% similarUnverified大语言模型在训练中吸收了大量技术文档与故障排查指南，形成了'症状—假设—验证'的推理模式，能根据上下文动态调整排查路径74% similarUnverifiedAutoregressive models suffer from the exposure bias problem, whereby the model sees real prefixes during training but faces self-generated erroneous prefixes during inference, causing errors to accumulate progressively.73% similarUnverifiedAfter alignment training eliminates a certain type of harmful output, the model may learn more subtle ways of expression.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987735API
curl https://kongchang.com/api/v1/knowledge/claims/987735MCP
get_claim(id=987735)