Metraipolis › archive › dc_4edea2d7f9f9

Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring — arXiv:2610.09660

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09660
License (as archived)
CC0-1.0
Archived
2026-10-08T11:26:10.077Z
SHA-256 of the archived text
31697cd73218cbd663accce82d85780cca4e93a5a74ec4d16f6c51d995ad09c7
Stable URL of this page
https://metraipolis.com/documento/dc_4edea2d7f9f9

How to cite

Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring — arXiv:2610.09660 — arXiv (en), https://arxiv.org/abs/2610.09660 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4edea2d7f9f9 (Metraipolis archive dc_4edea2d7f9f9, sha256 31697cd73218cbd663accce82d85780cca4e93a5a74ec4d16f6c51d995ad09c7)
BibTeX
@misc{dc4edea2d7f9f9,
  title = {Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring — arXiv:2610.09660},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09660},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4edea2d7f9f9; sha256 31697cd73218cbd663accce82d85780cca4e93a5a74ec4d16f6c51d995ad09c7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09660. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automatic Short Answer Scoring (ASAS) requires models that can score student responses against question-specific criteria while remaining efficient and transferable across rubric sets. We propose RUSPAN, a rubric-conditioned ASAS framework that treats rubric descriptions as semantic label representations. RUSPAN serialises the question context, student answer, and all candidate rubric levels into a single sequence, then scores the levels listwise from the rubric-span and whole-sequence representations produced in a single LM pass. We further introduce RUSPAN-RIM, in which a Rubric-Independent Mask prevents rubric spans from attending to one another, making rubric representations depend only on the answer and question context and preventing overfitting to rubric patterns during training for zero-shot transfer. On six ASAS benchmarks spanning English, German, and Portuguese, RUSPAN improves mono-benchmark scoring over discriminative and generative baselines, while RIM with position reindexing delivers consistent and substantial gains on PT-ASAG, the held-out benchmark with the strongest combined language and rubric-structure shift.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.09660 — 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 2026-10-08T10:24:06.326Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).