发表机构
Amazon Web Services（亚马逊网络服务公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究文本分类的提示优化方法，提出错误引导优化（ERGO）方法，通过诊断-规定-重写反馈循环迭代训练集。该方法在特定任务上准确率最高，能生成可解释规则，还提供了任务特征与最优范式选择的互补框架。
AI 中文摘要
文本分类的提示优化有多种方法，各有优缺点。我们通过对不同分类基准进行全面实证研究，比较了这些范式。在此基础上提出了错误引导优化（ERGO）方法，它通过诊断-规定-重写反馈循环来迭代训练集、诊断分类失败并生成目标决策规则。ERGO在错误集中于特定混淆标签对的任务上准确率最高，如TREC达90.0%，CLINC150达94.4%，3至5次迭代收敛且生成可解释决策规则。我们还提供了将任务特征与最优范式选择相联系的互补框架。
英文摘要
Prompt optimization for text classification spans diverse approaches, from demonstration selection to exploration-based search to error-driven diagnosis, each with known but incompletely characterized strengths and limitations. We conduct a comprehensive empirical study across diverse classification benchmarks (2 to 150 classes) comparing these paradigms through both quantitative evaluation and qualitative analysis of optimization traces, revealing that each paradigm excels on structurally different task types and that no single method dominates. Guided by these insights, we propose Error-Guided Optimization (ERGO), an error-driven method that iterates over the full training set in non-overlapping batches, diagnoses classification failures, and generates targeted decision rules through a diagnose-prescribe-rewrite feedback loop. ERGO achieves the best accuracy on tasks where errors concentrate in specific confused label pairs (which we term boundary-learnable tasks): TREC: 90.0%, CLINC150: 94.4%, converges in 3-5 iterations, and produces interpretable decision rules. While ERGO does not achieve the highest overall average, it fills a complementary role: demonstration-based ICL wins on coverage-dependent tasks, exploration-based search wins on many-class intent, and ERGO wins where decision boundaries are learnable from error patterns. We provide a complementarity framework linking task characteristics to optimal paradigm selection, offering practical guidance for practitioners.
