# 从示例中提炼任务指令：面向真实世界B2B对话的增强上下文学习

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-14 08:00
- AIHOT 分数：45
- AIHOT 链接：https://aihot.virxact.com/items/cmqotg8pm046oslx6w4iwctxj
- 原文链接：https://arxiv.org/abs/2606.15641

## AI 摘要

Call Playbook数据集包含五个分类任务，源自真实世界B2B对话。提出的知识提取方法将冗长示例蒸馏为紧凑的结构化分类标准和任务描述，使token使用减少99%，宏平均AUC比传统上下文学习（ICL）提升最多7%。与先进的token压缩基线（在上下文增长时F1下降超过9点）不同，该方法保持稳健。框架还支持直接优化分类逻辑，满足透明性、效率和用户交互需求。

## 正文

In-context learning (ICL) is the standard method for low-resource classification, yet its efficacy in specialized domains remains largely unexplored. We address the challenge of classifying semantically complex, multi-party B2B conversations, where traditional ICL encounters significant limitations, especially as context length increases due to the concatenation of multiple few-shot examples. We introduce the Call Playbook dataset, featuring five classification tasks derived from real-world B2B conversations targeting core sales concepts. To bridge the gap between performance and practical utility, we propose novel knowledge extraction methods that distill verbose examples into compact, interpretable representations of structured classification criteria and precise task descriptions. Our approach achieves a 99\% reduction in token usage and improves macro-averaged AUC by up to 7\% over traditional ICL. Notably, it remains robust as context grows, unlike advanced token compression baselines which degrade by over 9 F1 points. Importantly, our framework enables direct refinement of classification logic, addressing critical needs for transparency, efficiency, and user interaction in real-world NLP applications.