すべてのプロジェクト

関連プロジェクト

  • no-hallucination

    Three measured experiments on RAG hallucination: quote-checking, TypeSafe's Jev, and IBM's STAIR. 850+ graded questions, raw responses included.

    共通トピック: benchmark, rag

  • jev-sinhala-review

    Empirical zero-shot benchmark of TypeSafe Jev (v1.13.0) on low-resource Sinhala and Singlish NLP benchmarks (SOLD, SinhalaMMLU, NSINA)

    共通トピック: benchmark, decision-model

  • jev-test

    Pre-registered benchmark: can a 2B local model (Gemma 4 E2B) answer web questions without making things up when a decision model (TypeSafe Jev) makes every call? SearXNG for search, MemPalace for verbatim memory, seven arms including open local judges. Spec and thresholds fixed before any run.

    共通トピック: benchmark, rag