MMODELYST
Papers/Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations
PAP

Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations

Jun 14, 2026

arXiv
Abstract

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.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Guy Rotman, Adi Kopilov, Danit Berger Zalmanson, Omri Allouche
Your notes (browser-local)
saved
Cross-links
No linked entities.
arXiv:2606.15641