api-list-negative-filters-hallucinated-ids
IN premise
`list_negative()` discards any node IDs returned by the LLM that don't exist in the database, preventing hallucinated IDs from appearing in results.
Summary
When the system asks an LLM to identify nodes that contradict a query, the LLM might return IDs that don't actually exist in the database. The list_negative function guards against this by filtering out any such phantom IDs before returning results, so downstream code never has to deal with references to nonexistent nodes.
Dependents
These beliefs depend on this one:
- list-negative-is-defensively-bounded — The negative belief listing pipeline applies defense-in-depth: keyword pre-filtering narrows candidates before LLM classification, hallucinated node IDs are discarded against the actual network, and malformed LLM output falls back gracefully to zero count rather than raising.
- reference-validation-is-defense-in-depth — Every system boundary that accepts node ID references validates them against the actual network: import normalization drops unknown antecedent/outlist refs, nogood recording skips invalid node IDs, and LLM-returned negative-list IDs are filtered against existing nodes.
Details
| Source | entries/2026/04/29/tests-test_api.md |