judge-jev
carlaiau/judge-jev
Reproducible experiments evaluating Jev as an automated judge across benchmarks and tasks.
TypeScript
- 星标
- 0
- 派生
- 0
收录依据
研究用 Jev Choice/Score/Noul 做段落相关性评估,与人工标签及公开 LLMJudge 结果对比;属于公开标签的回顾性比较,不是盲测挑战。
carlaiau/judge-jev
Reproducible experiments evaluating Jev as an automated judge across benchmarks and tasks.
研究用 Jev Choice/Score/Noul 做段落相关性评估,与人工标签及公开 LLMJudge 结果对比;属于公开标签的回顾性比较,不是盲测挑战。
Find where an API router confuses look-alike operations, rewrite the wording, and rerun. Runs offline in mock mode; live mode uses TypeSafe's Jev.
共同主题: evals
Does a System One model actually beat keyword matching? A reproducible benchmark on catching disguised duplicate thesis titles. 24 cases, real production baseline, raw data and charts included.
共同主题: information-retrieval
Evidence-gated registry of Jev question packs — curated questions, golden cases and measured evidence for Jev-compatible decision endpoints
共同主题: evals