# From High Recall to High Utility: Dataset-Adaptive Post-Processing of LLM-Generated Customer Intents

> Полный текст доступен на английском

**Published:** 8 октября 2026 г.
**Author:** Mahesh Viswanathan, Joan Rossello, Leticia Fernandes, Paul Mutawe
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/from-high-recall-to-high-utility-dataset-adaptive-post-processing-of-llm

Large language models can extract useful signals from heterogeneous enterprise data, but high-recall extraction often produces outputs that are duplicated, uneven in granularity, semantically overlapping, or too numerous for downstream systems and human reviewers to use…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2610.09039)

**Теги:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*