MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing
Vlad Andrei Negru, Robert Vacareanu, Camelia Lemnaru, Mihai Surdeanu, Rodica Potolea
Abstract
We introduce MorphNLI, a modular step-by-step approach to natural language inference (NLI). When classifying the premise-hypothesis pairs into entailment, contradiction, neutral, we use a language model to generate the necessary edits to incrementally transform (i.e., morph) the premise into the hypothesis. Then, using an off-the-shelf NLI model we track how the entailment progresses with these atomic changes, aggregating these intermediate labels into a final output. We demonstrate the advantages of our proposed method particularly in realistic cross-domain settings, where our method always outperforms strong baselines with improvements up to 12.6% (relative). Further, our proposed approach is explainable as the atomic edits can be used to understand the overall NLI label.
BibTeX
@inproceedings{negru-etal-2025-morphnli,
title = "{M}orph{NLI}: A Stepwise Approach to Natural Language Inference Using Text Morphing",
author = "Negru, Vlad Andrei and
Vacareanu, Robert and
Lemnaru, Camelia and
Surdeanu, Mihai and
Potolea, Rodica",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.385/",
pages = "6938--6953",
ISBN = "979-8-89176-195-7"
}