The Impact of LLM Self-Consistency and Reasoning Effort on Automated Scoring Accuracy and Cost
大型语言模型自我一致性与推理努力对自动化评分准确性和成本的影响
机构 * Khan Academy(可汗学院)
专题命中 推理与问题求解 :LLM(title,summary_cn);large language model(abstract);language model(abstract);分类 cs.AI
AI总结 研究探讨了LLM自我一致性和推理努力对自动化评分准确性和成本的影响,发现策略性模型选择和推理设置比集成更有效,且推理努力与评分准确性呈正相关。
Comments 14 pages, 10 tables, 2 figures. Presented at the 2026 National Council on Measurement in Education (NCME) Annual Meeting, April 11, 2026, Los Angeles, CA