凡自治之物 · LGD 治理学 · 创造术家族 | 评测协议:skill-quality-gate
English
When to use
- When users question the truthfulness of RAG answers, or the input contains suspected hallucination keywords such as "fabricated" or "nonsense".
- When concrete conclusions drawn from retrieval results must be fact-checked, in line with the LGD registered/evidenced principles.
- In high-risk decision scenarios or when producing traceable reports, answers must carry supporting source citations.
Usage
Call the core script grounding_check.py and specify the check target and sources via command-line arguments:
python grounding_check.py --target <claim-to-check> --source <retrieval-store ID or URL> --mode lgd_grounding
--target: the specific factual statement or answer segment to verify.--source: the retrieved knowledge index, URL or related context data.--mode: validation mode;lgd_groundingrecommended (LGD Three-Law grounding).
Workflow
- Extract the key factual claims from the current RAG answer into a list of statements to check.
- Semantically match claims against retrieved sources and compute the grounding coverage.
- Run
grounding_check.pyto produce the internal verification result per LGD rules. - The script flags unsupported claims as high risk, warning "hallucination risk" in red.
- The system automatically requires unsupported conclusions to carry source links, ensuring every answer is traceable.
- Aggregate the analysis into a final credibility assessment with evidence-based correction suggestions.
Evidence & safety statement
- Evidence: TBD (no evaluation / badge link yet; update here once produced)
- Version: 1.1.1
- Safety: 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 RAG 回答内容的真实性,或输入包含“编造”、“胡说八道”等疑似幻觉关键词时。
- 需要对检索结果中的具体结论进行事实核验,确保符合 LGD 三律之“有籍”与“有证”。
- 在涉及高风险决策或需要生成可追溯报告的场景中,要求答案附带出处链接支撑。
用法
调用核心脚本文件 grounding_check.py,通过命令行参数指定校验对象与来源:
python grounding_check.py --target <待校验的文本声明> --source <检索库 ID 或 URL> --mode lgd_grounding
--target: 输入需要核查的具体事实陈述或回答片段。--source: 提供检索到的知识文档索引、URL 或相关上下文数据。--mode: 指定验证模式,推荐使用lgd_grounding(LGD 三律 grounding)。
流程
- 提取当前 RAG 回答中的关键事实声明,形成待校验文本列表。
- 将待校验声明与检索来源进行语义匹配,计算接地覆盖率(Grounding Coverage)。
- 执行
grounding_check.py脚本,依据 LGD 三律规则生成内部校验结果。 - 脚本输出中标记未覆盖的声明为高风险,并以红色文本警示“幻觉风险”。
- 系统自动要求未支撑结论附带来源链接,确保每一条回答“有籍可查”。
- 汇总分析结果,输出最终的可信度评估报告及基于证据的修正建议。
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。
