用配对比较训练模型，再转为绝对评分，提升作文自动打分准确率。
Pair2Score: Pairwise-to-Absolute Transfer for LLM-Based Essay Scoring
- 先用配对比较学方向判断，再转为绝对分数预测。
- 在语法、词汇、句法三项上均优于纯绝对评分基线。
- 配对训练时长和转移策略影响效果，非越多越好。
许多评分任务需要绝对分数，而配对比较能提供更简单的学习目标。我们提出 Pair2Score，一种两阶段学习框架，通过参数高效适配 LLaMA 将配对比较转化为绝对评分。第一阶段在基于绝对评分标签生成的配对数据上训练方向性孪生排序器；第二阶段采用可配置的迁移策略（热启动与嵌入融合变体）训练绝对预测器。在五折交叉验证协议下评估了与评分量表对齐的自动作文评分（AES）特质（语法、词汇、句法）。在特质层面，最优迁移变体在所有三项上均提升二次加权卡帕系数（QWK）相较于仅使用绝对标签的基线。但并非所有迁移配置都有效：一阶段配对训练比延长训练更可靠，迁移配置本身（而非仅是否包含配对阶段）决定了下游评分性能是否提升。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。