Wiki Search Re-Ranker
Anis Marrouchi put Jev in front of his wiki search as a re-ranker, raising the rate of correct answers from 33% to 50% across 12 queries.
ِAnis Marrouchi@anis_marrouchi𝕏
My wiki search was picking the right answer 1 time in 3. I put Jev in front of it as a re-ranker — a typed decision, not another prompt. from 33% to 50%, at about $0.0005 and 550 ms per query. 12 queries. Small sample. Still the cheapest accuracy I've bought all week. https://t.co/Ny8qjl3X6w
He describes the re-ranking step as “a typed decision, not another prompt” and notes that the sample was small.
Also filed under Research & data
- Visualizes French Wikipedia Elites
The project is a data visualization of French elites on Wikipedia. Its crawl is ongoing, with new biographies arriving.
- GraphRAG with Swappable Laya and Jev Models
This project is an agentic GraphRAG pipeline with swappable local Laya or cloud Jev decision models.
- Jev Probability Calibration Experiments
The repository presents reproducible experiments on Jev probability calibration, uncertainty, and forecast preservation.
- Benchmarks Jev for Malicious Skill Detection
jev-skillbench benchmarks Jev as a malicious agent-skill detector on MalSkillBench with verify-and-escalate evaluation.