Research Papers 论文研究 4h ago Updated 22m ago 更新于 22分钟前 45

Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring 高效评分学习:基于多臂老虎机的低成本LLM论文评分提示选择框架

Proposes a multi-armed bandit (MAB) framework for adaptive prompt selection in automated essay scoring, treating each prompt type as a bandit arm Achieves comparable scoring accuracy to exhaustive grid search while reducing LLM calls by 78.4% during prompt optimization Identifies multi-step grading with calibration examples as the highest-accuracy recipe among four tested configurations Introduces the first cost-reliability learning curves for essay scoring, tracking token usage, latency, and ag 提出多臂老虎机(MAB)框架实现自适应提示选择,将每种提示类型视为"臂"进行在线学习 在IELTS写作Task 2论文评分任务上,相比穷举网格搜索减少78.4%的LLM调用,同时保持可比准确率 多步评分方法配合校准示例达到最高准确率,四种评分配方中表现最优 首次生成作文评分的成本-可靠性学习曲线,量化token消耗、延迟与评分一致性之间的关系 将提示选择从离线超参数优化问题转化为高效在线学习任务,开创AES领域新范式

62
Hot 热度
72
Quality 质量
60
Impact 影响力

Analysis 深度分析

TL;DR

  • Proposes a multi-armed bandit (MAB) framework for adaptive prompt selection in automated essay scoring, treating each prompt type as a bandit arm
  • Achieves comparable scoring accuracy to exhaustive grid search while reducing LLM calls by 78.4% during prompt optimization
  • Identifies multi-step grading with calibration examples as the highest-accuracy recipe among four tested configurations
  • Introduces the first cost-reliability learning curves for essay scoring, tracking token usage, latency, and agreement metrics
  • Transforms prompt selection from an offline hyperparameter optimization problem into an efficient online learning task

Why It Matters

This work addresses a critical bottleneck in deploying LLMs for educational assessment: the high operational cost of finding optimal prompting strategies. By reframing prompt selection as an online learning problem, it offers a scalable path for EdTech platforms to balance cost efficiency against assessment validity without exhaustive trial-and-error.

Technical Details

  • Multi-Armed Bandit Controller: Each prompt type (grading recipe) is treated as an arm in a MAB framework, enabling adaptive selection during inference rather than relying on fixed prompt configurations.
  • Four Grading Recipes Evaluated: Multi-step vs. single-step assessment, crossed with with vs. without calibration examples, yielding four distinct prompt configurations tested on IELTS Writing Task 2 essays.
  • 78.4% Reduction in LLM Calls: The MAB framework achieves accuracy comparable to exhaustive grid search while dramatically reducing the number of LLM calls needed to identify the best grading approach.
  • Cost-Reliability Learning Curves: First framework to jointly track token usage, latency, and agreement metrics, producing learning curves that visualize the cost-accuracy tradeoff for essay scoring systems.
  • Dataset: Experiments conducted on IELTS Writing Task 2 essays, a standardized benchmark for automated essay scoring.

Industry Insight

  • EdTech platforms can adopt bandit-driven prompt selection to significantly reduce inference costs while maintaining scoring quality, making large-scale automated assessment more economically viable.
  • The cost-reliability learning curves provide a practical decision-making tool for practitioners to determine the minimum cost required to achieve target agreement levels with human raters.
  • This online control paradigm generalizes beyond essay scoring and could be applied to any domain where prompt selection critically impacts both accuracy and operational cost.

TL;DR

  • 提出多臂老虎机(MAB)框架实现自适应提示选择,将每种提示类型视为"臂"进行在线学习
  • 在IELTS写作Task 2论文评分任务上,相比穷举网格搜索减少78.4%的LLM调用,同时保持可比准确率
  • 多步评分方法配合校准示例达到最高准确率,四种评分配方中表现最优
  • 首次生成作文评分的成本-可靠性学习曲线,量化token消耗、延迟与评分一致性之间的关系
  • 将提示选择从离线超参数优化问题转化为高效在线学习任务,开创AES领域新范式

为什么值得看

该研究首次将在线控制机制应用于自动作文评分(AES)的提示策略选择,为教育技术平台提供了可量化的成本-效度权衡方案。通过MAB框架实现自适应提示选择,在保持评分质量的同时大幅降低LLM调用成本,对大规模教育应用具有重要实践价值。

技术解析

  • 核心架构:将多臂老虎机(MAB)控制器应用于提示选择,每个提示类型作为独立"臂",在推理过程中动态调整策略,实现成本感知的自适应选择
  • 实验设计:在IELTS Writing Task 2论文数据集上实现四种评分配方(多步vs单步评估 × 有/无校准示例),通过token使用量、延迟和一致性指标进行综合评估
  • 关键结果:MAB框架达到与穷举网格搜索相当的评分准确率,但LLM调用减少78.4%;多步方法配合校准示例取得最高准确率
  • 创新产出:首次生成作文评分的成本-可靠性学习曲线(cost-reliability learning curves),提供可操作的优化洞察

行业启示

  • 教育技术平台可将MAB框架集成到自动化评分系统中,在预算约束下实现成本与评分质量的最优平衡
  • 成本-可靠性学习曲线为产品决策提供量化依据,帮助团队识别不同应用场景下的最佳提示策略
  • 提示选择从离线调优转向在线学习,为其他需要动态调整提示的工程场景(如客服、内容审核)提供可复用的方法论框架

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

LLM 大模型 Evaluation 评测 Research 科学研究 Education AI 教育AI