CLAILGMay 3

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

arXiv:2605.020697.0
AI Analysis

For automated essay scoring, Pair2Score offers a method to leverage pairwise comparisons for absolute scoring, but the benefit is configuration-dependent and incremental.

Pair2Score transfers pairwise comparisons into absolute scoring for LLM-based essay scoring, improving quadratic weighted kappa over an absolute-only baseline for grammar, vocabulary, and syntax traits.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes