[KongchangAI]
Concept

QSRG

A synthetic rubric generation method used as a baseline for comparison with Rubricon.

Timeline (last 90 days)

Oct 30

The alignment of scores that Rubricon-generated rubrics assign to frontier LLM responses with expert-written rubrics is 9% higher than that of the best alternative synthesis method, with compared methods including RRD, QSRG, OpenRubrics, and agent-based generation methods such as Codex.

Unverified50%

All Facts (1)

Unverified

The alignment of scores that Rubricon-generated rubrics assign to frontier LLM responses with expert-written rubrics is 9% higher than that of the best alternative synthesis method, with compared methods including RRD, QSRG, OpenRubrics, and agent-based generation methods such as Codex.

50%

Source Articles

Rubricon: Automatically Generating Rubrics to Boost LLM Evaluation and Training EfficiencyOct 30