Skip to content

v0.7.0 — Phase 8: faithfulness verifier (NLI)

Choose a tag to compare

@cattolatte cattolatte released this 17 Jul 01:13

The system's conscience — no unverified sentence reaches the user.

  • NLI verifier: Polaris SentencePairClassifier (num_classes=3, entail/neutral/contradict) from the Stage-0 trunk; 3-class training; artifact.
  • verify_grounded_answer: per-sentence NLI(cited span → sentence) with citation precision, citation recall, and hallucination-rate metrics; grounded iff every content sentence is cited and entailed.
  • Fail-safe ladder (answer_with_verification): generate → verify → extractive fallback → abstain.