English

Pair2Score: Pairwise-to-Absolute Transfer for LLM-Based Essay Scoring

Computation and Language 2026-05-05 v1 Artificial Intelligence Machine Learning

Abstract

Many scoring applications require absolute predictions, while pairwise comparisons can provide a simpler learning objective. We present Pair2Score, a two-stage learning framework that transfers pairwise comparisons into absolute scoring with parameter-efficient LLaMA adaptation. Stage 1 trains a directional Siamese ranker on pairwise comparisons derived from absolute trait labels; Stage 2 trains an absolute predictor using configurable transfer strategies (warm-start and embedding-fusion variants). We evaluate on rubric-aligned Automated Essay Scoring (AES) traits (grammar, vocabulary, syntax) under a five-fold protocol that co-rotates held-out fold and random seed. At the trait level, the best-performing transfer variant improves quadratic weighted kappa (QWK) over an absolute-only baseline for all three traits. However, not all transfer configurations help: a one-epoch pairwise stage transfers more reliably than extended pairwise training, and transfer configuration -- not just the inclusion of a pairwise stage -- determines whether downstream scoring benefits.

Cite

@article{arxiv.2605.02069,
  title  = {Pair2Score: Pairwise-to-Absolute Transfer for LLM-Based Essay Scoring},
  author = {İbrahim Rıza Hallaç and Hasan Oğul},
  journal= {arXiv preprint arXiv:2605.02069},
  year   = {2026}
}

Comments

11 pages, 2 figures

R2 v1 2026-07-01T12:47:44.845Z