Expired50% confidenceFactExact time
The industry has identified four most commonly used prompt roles: System, User, Tool, and Assistant, and large models undergo dedicated optimization training for these four roles during the base training phase.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
From Tokens to Agents: A Deep Dive into the Core Logic Behind AI's Key Concepts
bilibili人工智能AI大模型课程6/8/2026
Related Claims
UnverifiedThe 'role assignment' principle in prompts can activate specific domain knowledge distributions that the model learned during pretraining, making outputs more professional and focused.70% similarUnverified实现角色一致性通常依赖角色系统提示词工程、长上下文窗口管理以及专项微调训练三重技术保障69% similarVerified提示词工程已发展出思维链（Chain-of-Thought）、少样本学习（Few-Shot Learning）、角色扮演（Role Prompting）等多种成熟范式69% similarUnverifiedTALM and Toolformer are training-side tool-calling approaches that modify model weights; the currently more mainstream approach in industry is the prompt-side solution, which does not modify the model and instead relies on prompts to guide the model in deciding when to use tools.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/50205API
curl https://kongchang.com/api/v1/knowledge/claims/50205MCP
get_claim(id=50205)