Unverified50% confidenceFactExact time
The safety capabilities of Manacá-1B-Instruct-2 come from a dedicated safety-SFT, whose style is close to the construction method of the LLM-jp AnswerCarefully dataset, with three iterations.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSafety alignment is typically achieved through stages such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF); more recent and efficient methods such as direct preference optimization (DPO) have emerged, with alignment goals summarized as the 3H principle: helpful, honest, and harmless.64% similarUnverifiedTW3Cast uses a three-guard mechanism to prevent selection bias: dual criteria of accuracy and calibration, targeted asymmetric margins, and conservative per-window gating.62% similarUnverifiedSAST discovers potential vulnerabilities by analyzing source code, while DAST discovers security issues through runtime probing; these methods are built around deterministic assumptions.61% similarUnverified针对提示词注入的业界推荐多层防御体系包括输入沙箱化、输出格式校验和关键操作人工审批61% similarUnverified指令跟随能力依赖于监督微调（SFT）阶段和RLHF阶段的偏好对齐优化61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032790API
curl https://kongchang.com/api/v1/knowledge/claims/1032790MCP
get_claim(id=1032790)