凡自治之物 · LGD 治理学 · 创造术家族 | 评测协议:见平台质量门禁规范
English
When to use
- When the user questions the truthfulness of generated content, or voices worries like "the AI talks nonsense" or "I'm afraid of errors before this goes out".
- When factual claims in the model's answer must be verified, and concrete sources / citation tracing are required.
- When agent-generated articles, reports or replies are about to be published externally and must be verifiable and traceable.
Usage
- Run:
python fact_guard.py --input <text-to-check> - Enable strict-mode checking:
fact_guard check --mode strict --rules lgd_three_laws - Read a file and analyze its provenance:
fact_guard analyze --file <report-path> --cache __pycache__Parameters:--inputis the text to verify;--modeacceptsnormal/strict, orlgd_three_lawsto engage the theoretical root.
Workflow
- Extract claims: identify the key statements in the input and mark them as "claims to be proven".
- Retrieve evidence: run the script to search retrieved sources, looking for matching external knowledge bases or documents.
- Compare & label: per the results, tag each claim as "supported / unsourced / dubious".
- Gate: content tagged "unsourced" is forbidden from going out as fact.
- Report: emit a verdict with confidence levels and citation links for decision-making.
Evidence & safety statement
- Evidence: TBD (no evaluation / badge link yet; update here once it is produced)
- Version: 1.1.1
- Security: no independent security scan has been performed (TBD); the conclusion is pending and no endorsement is given until it is completed.
中文
何时用
- 当用户质疑生成内容的真实性,或表达「AI 胡说八道」、「内容发出去怕有错」等担忧时。
- 需要验证模型回答中的事实主张,并要求提供具体出处、出处校验或引用溯源证据时。
- 在将 Agent 生成的文章、报告或回复准备对外发布、需确保内容可证及可追溯时使用。
用法
- 调用命令:
python fact_guard.py --input <待核查文本> - 启用严格模式校验:
fact_guard check --mode strict --rules lgd_three_laws - 读取文件分析溯源:
fact_guard analyze --file <报告路径> --cache __pycache__参数说明:--input为待验证文本;--mode可选normal/strict或lgd_three_laws启用理论根基。
流程
- 提取主张:识别输入中的关键陈述并标记为「待证主张」。
- 检索证据:执行脚本对照检索来源,查找匹配的外部知识库或文档。
- 比对标注:依据结果将每条声明标注为「已支撑/无来源/存疑」。
- 门禁控制:对标记为「无来源」的内容禁止作为事实对外输出。
- 生成报告:输出含置信度等级与引用链接的核查结论供决策参考。
证据与安全声明
- 证据:TBD(暂无评测/徽章链接;产生后在此更新实际链接)
- 版本:1.1.1
- 安全:未做独立安全扫描(TBD),结论待补;补全前不作推荐背书。
