# Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale

arXiv: https://arxiv.org/abs/2610.10758 · HTML: https://mlsanity.com/paper/2610.10758/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 5 of its 32 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 5 of 5)

- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.10720/) (2025)
- [Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting](https://mlsanity.com/paper/2605.04426/) (2026)
- [Context Compression Is Not One Thing: Readable Symbolic Re-expression vs. Coherent Summary at Matched Budget](https://mlsanity.com/paper/2606.14875/) (2026)

## Abstract (arXiv)

Enterprise conversation analytics asks many questions of millions of interactions. Each question can require reconstructing what people mean and identifying which information matters, repeating costly interpretive work across the same transcripts. We propose a simple principle: clarify the text, then focus the reader. Statement normalization transforms dialogue into short, speaker-attributed statements with source references and semantic tags. The statements make meaning more explicit; the tags support selecting evidence for a particular question. Downstream models can use the full representation or a relevant subset, depending on what helps them make the decision. In an offer-suppression task on customer-service calls, normalization improves a supervised classifier without selection, while weaker prompted readers benefit from both normalization and selection. A small model can learn the normalization contract, while lightweight encoders handle tagging and downstream decisions. Sharing this preparation across questions supports an inference pipeline built entirely from small models, making analytics over millions of conversations substantially less expensive.