DA-Pred: Performance Prediction for Text Summarization under Domain-Shift and Instruct-Tuning

Anum Afzal, Florian Matthes, Alexander Fabbri


Abstract
Large Language Models (LLMs) often don’t perform as expected under Domain Shift or after Instruct-tuning. A reliable indicator of LLM performance in these settings could assist in decision-making. We present a method that uses the known performance in high-resource domains and fine-tuning settings to predict performance in low-resource domains or base models, respectively. In our paper, we formulate the task of performance prediction, construct a dataset for it, and train regression models to predict the said change in performance. Our proposed methodology is lightweight and, in practice, can help researchers & practitioners decide if resources should be allocated for data labeling and LLM Instruct-tuning.
Anthology ID:
2025.emnlp-main.387
Volume:
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7632–7643
Language:
URL:
https://aclanthology.org/2025.emnlp-main.387/
DOI:
Bibkey:
Cite (ACL):
Anum Afzal, Florian Matthes, and Alexander Fabbri. 2025. DA-Pred: Performance Prediction for Text Summarization under Domain-Shift and Instruct-Tuning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 7632–7643, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
DA-Pred: Performance Prediction for Text Summarization under Domain-Shift and Instruct-Tuning (Afzal et al., EMNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.emnlp-main.387.pdf
Checklist:
 2025.emnlp-main.387.checklist.pdf