Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning

Yanda Chen, Chandan Singh, Xiaodong Liu, Simiao Zuo, Bin Yu, He He, Jianfeng Gao


Abstract
Large language models (LLMs) often generate convincing, fluent explanations. However, different from humans, they often generate inconsistent explanations on different inputs. For example, an LLM may explain “all birds can fly” when answering the question “Can sparrows fly?” but meanwhile answer “no” to the related question “Can penguins fly?”. Explanations should be consistent across related examples so that they allow humans to simulate the LLM’s decision process on multiple examples. We propose explanation-consistency finetuning (EC-finetuning), a method that adapts LLMs to generate more consistent natural-language explanations on related examples. EC-finetuning involves finetuning LLMs on synthetic data that is carefully constructed to contain consistent explanations. Across a variety of question-answering datasets in various domains, EC-finetuning yields a 10.0% relative explanation consistency improvement on 4 finetuning datasets, and generalizes to 7 out-of-distribution datasets not seen during finetuning (+4.5% relative). We will make our code available for reproducibility.
Anthology ID:
2025.coling-main.505
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7558–7568
Language:
URL:
https://aclanthology.org/2025.coling-main.505/
DOI:
Bibkey:
Cite (ACL):
Yanda Chen, Chandan Singh, Xiaodong Liu, Simiao Zuo, Bin Yu, He He, and Jianfeng Gao. 2025. Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7558–7568, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning (Chen et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.505.pdf