EMNLP

SEFORA: Student Essays with Feedback Corpus and LLM Feedback Evaluation Framework

SEFORA：学生论文反馈语料库及LLM反馈评估框架

Shayan Peyghambari Oskoui, Norah Almousa, Zhaoyi Joey Hou, Carolina Gustafson, Gayle Rogers, Raquel Coelho, Diane Litman, Xiang Lorraine Li

机构 * University of Pittsburgh（匹兹堡大学） 纠错

AI总结 为解决大规模写作反馈中缺乏真实课堂反馈语料和评估方法的问题，构建了SEFORA语料库和UniMatch评估框架，实验表明LLM生成的反馈与教师反馈一致性低（F1≤0.4）。

Comments Under review for EMNLP 2026

Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning

Middo: 通过闭环学习提升LLM微调的模型感知动态数据优化

Zinan Tang, Xin Gao, Qizhi Pei, Zhuoshi Pan, Mengzhang Cai, Jiang Wu, Conghui He, Lijun Wu

AI总结 本文提出Middo框架，通过闭环学习动态优化数据，提升LLM微调效果，实验显示在多个基准上平均提升7.15%的准确率。

Comments Accepted by EMNLP 2025 (Main)

Journal ref EMNLP Main (2025) 6871-6891