mlsanityData to 14 Oct 2026

DACE For Railway Acronym Disambiguation

arXiv 2512.18357 ↗First posted 20 Dec 2025cs.CLcited by 0

Not on the map. Why?

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.

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

15 of 27 references.

References · 15

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  5. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  6. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  7. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  8. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  9. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  10. 2020Acronym Identification and Disambiguation Shared Tasks for Scientific Document Understandingcited by 12
  11. 2023What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventoriescited by 9
  12. 2021MadDog: A Web-based System for Acronym Identification and Disambiguationcited by 8
3 more
  1. 2021BERT-based Acronym Disambiguation with Multiple Training Strategiescited by 8
  2. 2023GLADIS: A General and Large Acronym Disambiguation Benchmarkcited by 5
  3. 2025Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Aligning the Pretraining and Finetuning Objectives of Language Models
  2. 2024Retrieval-Augmented Generation for Natural Language Processing: A Survey
  3. 2025Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey
  4. 2022FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction
  5. 2026An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
  6. 2026Association Is Not Similarity: Learning Corpus-Specific Associations for Multi-Hop Retrieval
  7. 2024Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation
  8. 2025Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models