Skip to content
conftrace_
2025 EMNLP EMNLP 2025

taskGen at TSAR 2025 Shared Task Exploring prompt strategies with linguistic knowledge

Abstract

AbstractTaskGen ranked as 6th best team in the TSAR 2025 shared task for English text adaptation to a target CEFR level. Our experiments consisted of prompting a Llama-3.1-8B-Instruct model with linguistic descriptors of the target level, examples of adaptations and multi-step approaches. Our best run, 13th in the overall ranking, applied an ensemble strategy using a voting mechanism to find the most adequate among 10 texts, each produced by a different prompting strategy.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Juan Cruz Oviedo, Elisabet Comelles Pujadas, Laura Alonso Alemany, Jordi Atserias Batalla

Topics

Natural Language Processing > Generation > Text Generation Natural Language Processing > Resources & Methods > Large Language Models Artificial Intelligence > Core AI > Large Language Models Machine Learning > Learning Types > Prompt Engineering

Keywords

prompt engineering linguistic knowledge text simplification ensemble method ensemble voting text adaptation large language model cefr level prompt strategy linguistic descriptor
Download PDF

More from EMNLP 2025

All EMNLP 2025 papers →
GRIPF at TSAR 2025 Shared Task Towards controlled CEFR level simplification with the help of inter-model interactions
ITU NLP at TSAR 2025 Shared Task A Three-Stage Prompting Approach for CEFR-Oriented Text Simplification
STARLING at TSAR 2025 Shared Task Leveraging Alternative Generations for Readability Level Adjustment in Text Simplification
EasyJon at TSAR 2025 Shared Task Evaluation of Automated Text Simplification with LLM-as-a-Judge
HULAT-UC3M at TSAR 2025 Shared Task A Prompt-Based Approach using Lightweight Language Models for Readability-Controlled Text Simplification
UoL-UPF at TSAR 2025 Shared Task A Generate-and-Select Approach for Readability-Controlled Text Simplification