Fine-Tuning Sample Order Matters in Propositional Logical Question-Answering (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41166-41168
DOI: 10.1609/aaai.v40i48.42201 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Fengxiang Cheng und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Large language models (LLMs) have achieved impressive progress in natural language processing tasks but still struggle with complex logical reasoning. We observe that in propositional logic question-answering (QA), LLMs' performance varies with the order of training samples during fine-tuning. Motivated by this, we propose a data-driven approach to automatically determine the fine-tuning sample order, enhancing the logical QA performance of LLMs. Specifically, we first quantify the logical reasoning complexity of propositional reasoning samples and then stratify the training data into several subsets of ascending complexity. Subsequently, we fine-tune the LLMs on these subsets, progressing from low to high reasoning complexity. Experimental results demonstrate that our approach outperforms single-stage fine-tuning baselines across diverse reasoning benchmarks.
Zitieren
APA
Cheng, F., Zhou, C., Liu, F., & Rooij, R. V. (2026). Fine-Tuning Sample Order Matters in Propositional Logical Question-Answering (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41166-41168. https://doi.org/10.1609/aaai.v40i48.42201
Vancouver
Cheng F, Zhou C, Liu F, Rooij RV. Fine-Tuning Sample Order Matters in Propositional Logical Question-Answering (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41166-41168. doi:10.1609/aaai.v40i48.42201
BibTeX
@article{Cheng2026,
author = {Cheng, Fengxiang and Zhou, Chuan and Liu, Fenrong and Rooij, Robert Van},
title = {Fine-Tuning Sample Order Matters in Propositional Logical Question-Answering (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41166--41168},
doi = {10.1609/aaai.v40i48.42201}
}
EUVIMED