# A Chat About Boring Problems: Studying GPT-based text normalization

arXiv: https://arxiv.org/abs/2309.13426 · HTML: https://mlsanity.com/paper/2309.13426/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 23 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [NeMo Inverse Text Normalization: From Development To Production](https://mlsanity.com/paper/2104.05055/) (2021)
- [Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems](https://mlsanity.com/paper/2104.07777/) (2021)

## Built on by (most cited first, 10 of 10)

- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction](https://mlsanity.com/paper/2502.17239/) (2025)
- [Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction](https://mlsanity.com/paper/2507.18863/) (2025)
- [PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech](https://mlsanity.com/paper/2511.03080/) (2025)
- [Comprehensive Evaluation on Lexical Normalization: Boundary-Aware Approaches for Unsegmented Languages](https://mlsanity.com/paper/2505.22273/) (2025)
- [Positional Description for Numerical Normalization](https://mlsanity.com/paper/2408.12430/) (2024)
- [Ethic-BERT: An Enhanced Deep Learning Model for Ethical and Non-Ethical Content Classification](https://mlsanity.com/paper/2510.12850/) (2025)
- [Head-Pose-Aware Visual Speech Recognition with FiLM Modulation](https://mlsanity.com/paper/2606.00751/) (2026)
- [Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation](https://mlsanity.com/paper/2609.01246/) (2026)
- [Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition](https://mlsanity.com/paper/2609.20839/) (2026)

## Abstract (arXiv)

Text normalization - the conversion of text from written to spoken form - is traditionally assumed to be an ill-formed task for language models. In this work, we argue otherwise. We empirically show the capacity of Large-Language Models (LLM) for text normalization in few-shot scenarios. Combining self-consistency reasoning with linguistic-informed prompt engineering, we find LLM based text normalization to achieve error rates around 40% lower than top normalization systems. Further, upon error analysis, we note key limitations in the conventional design of text normalization tasks. We create a new taxonomy of text normalization errors and apply it to results from GPT-3.5-Turbo and GPT-4.0. Through this new framework, we can identify strengths and weaknesses of GPT-based TN, opening opportunities for future work.