# Discourse-Aware In-Context Learning for Temporal Expression Normalization

arXiv: https://arxiv.org/abs/2404.07775 · HTML: https://mlsanity.com/paper/2404.07775/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 11 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [Exploring the Feasibility of ChatGPT for Event Extraction](https://mlsanity.com/paper/2303.03836/) (2023)
- [Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning](https://mlsanity.com/paper/2010.00117/) (2020)
- [Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text](https://mlsanity.com/paper/2005.09392/) (2020)
- [Multilingual Normalization of Temporal Expressions with Masked Language Models](https://mlsanity.com/paper/2205.10399/) (2022)

## Built on by (most cited first, 2 of 2)

- [A Vision for Geo-Temporal Deep Research Systems: Towards Comprehensive, Transparent, and Reproducible Geo-Temporal Information Synthesis](https://mlsanity.com/paper/2506.14345/) (2025)
- [Disco-RAG: Discourse-Aware Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.04377/) (2026)

## Abstract (arXiv)

Temporal expression (TE) normalization is a well-studied problem. However, the predominately used rule-based systems are highly restricted to specific settings, and upcoming machine learning approaches suffer from a lack of labeled data. In this work, we explore the feasibility of proprietary and open-source large language models (LLMs) for TE normalization using in-context learning to inject task, document, and example information into the model. We explore various sample selection strategies to retrieve the most relevant set of examples. By using a window-based prompt design approach, we can perform TE normalization across sentences, while leveraging the LLM knowledge without training the model. Our experiments show competitive results to models designed for this task. In particular, our method achieves large performance improvements for non-standard settings by dynamically including relevant examples during inference.