全部项目

no-hallucination

aryanchauhanoffical/no-hallucination

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

Python
星标
4
派生
0

收录依据

一组 RAG 实验比较引文核验、Jev 护栏与路由策略;README 报告 Jev 在一项测试中未能阻止剩余的无依据回答。

相关项目

  • 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.

    共同主题: benchmark, hallucination, rag

  • jev-access-day

    A learning scaffold for TypeSafe AI's System One models: eval harness plus a measured, plain-language comparison of the Jev decision model vs an LLM stand-in on 24 real operational decisions. All numbers reproducible from committed run files.

    共同主题: benchmark, evaluation

  • jev-rag-benchmark

    Free English RAG benchmark for TypeSafe Jev 1.13 — frozen candidate pools, calibration, paired bootstrap CIs, $0 runs. Compared with OpenJev and NVIDIA cross-encoders.

    共同主题: benchmark, rag