# DACE For Railway Acronym Disambiguation

arXiv: https://arxiv.org/abs/2512.18357 · HTML: https://mlsanity.com/paper/2512.18357/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 20 Dec 2025.

## Builds on (most cited first, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Acronym Identification and Disambiguation Shared Tasks for Scientific Document Understanding](https://mlsanity.com/paper/2012.11760/) (2020)
- [What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories](https://mlsanity.com/paper/2302.03353/) (2023)
- [MadDog: A Web-based System for Acronym Identification and Disambiguation](https://mlsanity.com/paper/2101.09893/) (2021)
- [BERT-based Acronym Disambiguation with Multiple Training Strategies](https://mlsanity.com/paper/2103.00488/) (2021)
- [GLADIS: A General and Large Acronym Disambiguation Benchmark](https://mlsanity.com/paper/2302.01860/) (2023)
- [Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs](https://mlsanity.com/paper/2510.03762/) (2025)

## Abstract (arXiv)

Acronym Disambiguation (AD) is a fundamental challenge in technical text processing, particularly in specialized sectors where high ambiguity complicates automated analysis. This paper addresses AD within the context of the TextMine'26 competition on French railway documentation. We present DACE (Dynamic Prompting, Retrieval Augmented Generation, Contextual Selection, and Ensemble Aggregation), a framework that enhances Large Language Models through adaptive in-context learning and external domain knowledge injection. By dynamically tailoring prompts to acronym ambiguity and aggregating ensemble predictions, DACE mitigates hallucination and effectively handles low-resource scenarios. Our approach secured the top rank in the competition with an F1 score of 0.9069.