groundlens_dgi
Rank LLM responses by grounding quality when no source document is available. Provides a DGI score to prioritize reviews of open-ended chat or general Q&A outputs.
Instructions
Coarse context-free grounding signal, for when no source is available (DGI).
DGI (Directional Grounding Index) compares the question-to-response displacement against the direction typical of answers written from a source. No context is needed, so it works for open-ended chat and general Q&A.
IMPORTANT: this is the weakest signal here and it has a measured ceiling. With
authorship held constant it reaches AUROC 0.606, and the ceiling of the entire
embedding-similarity class is about 0.68. It is a ranking signal for triage,
not a detector, and it is not a risk verdict. Prefer groundlens_sgi
whenever a source is available. Never report a DGI score as evidence that an
answer is true or false.
Args: params (DGIInput): The question and LLM response.
Returns:
str: JSON with a plain-language CHECK, the DGI score, the magnitude,
escalate and handoff.
Examples: - Ranking a batch of chat answers so a reviewer starts with the worst - Screening outputs when no source document exists
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |