Metraipolis › archive › dc_f91dbc629e25
RubricWorld: World Model-Guided Rubric Optimization for LLM Graders — arXiv:2611.01986
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01986
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:52:48.030Z
- SHA-256 of the archived text
a4afd62bbffc93b3bfa561e1a9958fc27f64cf5317e699494939c8ad91a8942f- Stable URL of this page
https://metraipolis.com/documento/dc_f91dbc629e25
How to cite
RubricWorld: World Model-Guided Rubric Optimization for LLM Graders — arXiv:2611.01986 — arXiv (en), https://arxiv.org/abs/2611.01986 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f91dbc629e25 (Metraipolis archive dc_f91dbc629e25, sha256 a4afd62bbffc93b3bfa561e1a9958fc27f64cf5317e699494939c8ad91a8942f)
BibTeX
@misc{dcf91dbc629e25,
title = {RubricWorld: World Model-Guided Rubric Optimization for LLM Graders — arXiv:2611.01986},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01986},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f91dbc629e25; sha256 a4afd62bbffc93b3bfa561e1a9958fc27f64cf5317e699494939c8ad91a8942f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01986. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Rubric optimization improves LLM grading by revising scoring instructions while keeping the grader's parameters fixed. Existing optimizers often judge edits by aggregate validation performance, limiting the supervision they retain about which errors an edit corrects or introduces. Testing each candidate also requires rescoring validation answers, which limits how many edits can be explored within a fixed budget. We propose RubricWorld, a framework that learns from previous edit evaluations to guide further search. Its world model predicts an edit's correction and degradation rates at score boundaries, conditioned on the current rubric state. The training signal comes from paired grading results: scores for the same answers before and after an edit. Predictions select one candidate for direct evaluation, and held-out confidence bounds determine whether it corrects enough target errors while keeping new errors within prespecified limits. Measured effects update the model even when the edit is rejected. Across EIR (National), ASAP2.0, and ASAP-SAS with three frozen LLM graders, RubricWorld achieves the highest score in 20 of 27 metric comparisons. On ASAP2.0, it raises gpt-5-mini accuracy from 18.20% with the original rubric to 46.70%, exceeding the strongest baseline, APO, by 22.60 percentage points. code will be released upon acceptance. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.01986 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:49:38.327Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).