← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-long.648 · 记录 #1
Iterative Dual-Model Alignment for Story Evaluation
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 22:00
摘要
Large language models (LLMs) can both evaluate and explain text quality; however, most existing evaluators operate as static classifiers and lack the ability to refine their reasoning through interaction. We propose an Iterative Alpha–Beta Learning framework that jointly trains two complementary 8B models: an Alpha (\alpha) classifier that assesses pairwise story engagement, and a Beta (\beta) generator that produces structured, rubric-guided comparative explanations. The two models co-evolve within a closed feedback loop: \alpha provides probabilistic preference signals to guide \beta’s Direct Preference Optimization (DPO), while \beta’s improved explanations are reintegrated to retrain \alpha via a KL-based contrastive objective. This dual optimization enables mutual learning: \alpha gains interpretability and robustness from \beta’s textual rationales, while \beta acquires stronger alignment and discriminative precision from \alpha’s confidence deltas. Experiments on human-annotated story-pair datasets HANNA show that the proposed system consistently outperforms strong single-model baselines in both accuracy and explanation quality across multiple iterative rounds.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
Iterative Dual-Model Alignment for Story Evaluation
Large language models (LLMs) can both evaluate and explain text quality; however, most existing evaluators operate as static classifiers and lack the ability to refine their reasoning through interaction. We propose an Iterative Alpha–Beta Learning framework that jointly trains two complementary 8B models: an Alpha (\alpha) classifier that assesses pairwise story engagement, and a Beta (\beta) generator that produces structured, rubric-guided comparative explanations. The two models co-evolve within a closed feedback loop: \alpha provides probabilistic preference signals to guide \beta’s Direct Preference Optimization (DPO), while \beta’s improved explanations are reintegrated to retrain \alpha via a KL-based contrastive objective. This dual optimization enables mutual learning: \alpha gains interpretability and robustness from \beta’s textual rationales, while \beta acquires stronger alignment and discriminative precision from \alpha’s confidence deltas. Experiments on human-annotated story-pair datasets HANNA show that the proposed system consistently outperforms strong single-model baselines in both accuracy and explanation quality across multiple iterative rounds.
查看此版本解读 →查看此版本原文 ↗