{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T18:43:55Z","timestamp":1769625835607,"version":"3.49.0"},"reference-count":34,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["NSFC.62276231"],"award-info":[{"award-number":["NSFC.62276231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>In the field of Natural Language Inference (NLI), model interpretability remains an urgent and unresolved challenge. Existing interpretability-oriented annotated datasets are highly limited, and manually constructing natural language explanations is both costly and inconsistent, making it difficult to balance model performance and interpretability. To address this issue, this paper proposes an interpretable NLI framework based on active learning, Explanation Generation Model-Prediction Model (EGM-PM), and designs an active learning sampling algorithm, Explanation-aware Transition from Clustering to Margin (ETCM), that incorporates natural-language explanation information. In this framework, Large Language Models (LLMs) are employed to automate explanation annotation, reducing dependence on human experts in traditional active learning. A small number of high-value samples obtained via ETCM sampling are used to train the EGM, whose generated natural-language explanations are then used to guide the PM in label inference. Experimental results show that data sampled by ETCM substantially enhance the model\u2019s ability to learn relational and logical structures between premise\u2013hypothesis pairs. Compared with other active learning algorithms, ETCM approaches full-data performance more rapidly while using significantly fewer labeled samples. This finding confirms the value of natural language explanation semantics in improving both model performance and interpretability. Furthermore, this paper employs prompt engineering to construct an interpretability-oriented NLI dataset, Explainable Natural Language Inference (ExNLI), which augments traditional premise\u2013hypothesis pairs with natural-language explanations. Human and automated evaluations confirm the consistency and faithfulness of these explanations. The dataset has been publicly released, offering a low-cost and scalable data construction approach for future research on explainable NLI.<\/jats:p>","DOI":"10.3390\/info17020119","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T16:13:48Z","timestamp":1769444028000},"page":"119","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing the Interpretability of NLI Models Using LLMs and Active Learning Algorithms"],"prefix":"10.3390","volume":"17","author":[{"given":"Qi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou 310018, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou 310018, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Saarela, M., and Podgorelec, V. (2024). Recent applications of Explainable AI (XAI): A systematic literature review. Appl. Sci., 14.","DOI":"10.3390\/app14198884"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1145\/3236386.3241340","article-title":"The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery","volume":"16","author":"Lipton","year":"2018","journal-title":"Queue"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Bowman, S., Angeli, G., Potts, C., and Manning, C.D. (2015, January 17\u201321). A large annotated corpus for learning natural language inference. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal.","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., and Bowman, S. (2018, January 1\u20136). A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), Orleans, LA, USA.","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Conneau, A., Rinott, R., Lample, G., Schwenk, H., Stoyanov, V., Williams, A., and Bowman, S.R. (November, January 31). XNLI: Evaluating cross-lingual sentence representations. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-1269"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hu, H., Richardson, K., Xu, L., Li, L., K\u00fcbler, S., and Moss, L.S. (2020, January 16\u201320). OCNLI: Original Chinese Natural Language Inference. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event.","DOI":"10.18653\/v1\/2020.findings-emnlp.314"},{"key":"ref_7","unstructured":"Camburu, O.M., Rockt\u00e4schel, T., Lukasiewicz, T., and Blunsom, P. (2018, January 3\u20138). e-snli: Natural language inference with natural language explanations. Proceedings of the Advances in Neural Information Processing Systems 31, Montr\u00e9al, QC, Canada."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhang, S., Gong, C., Liu, X., He, P., Chen, W., and Zhou, M. (2022, January 10\u201315). ALLSH: Active Learning Guided by Local Sensitivity and Hardness. Proceedings of the 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Washington, DC, USA.","DOI":"10.18653\/v1\/2022.findings-naacl.99"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Bennetot","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"106392","DOI":"10.1016\/j.neunet.2024.106392","article-title":"Human attention guided explainable artificial intelligence for computer vision models","volume":"177","author":"Liu","year":"2024","journal-title":"Neural Netw."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Quan, X., Valentino, M., Dennis, L., and Freitas, A. (2024, January 12\u201316). Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, FL, USA.","DOI":"10.18653\/v1\/2024.emnlp-main.172"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Gurrapu, S., Kulkarni, A., Huang, L., Lourentzou, I., and Batarseh, F.A. (2023). Rationalization for explainable NLP: A survey. Front. Artif. Intell., 6.","DOI":"10.3389\/frai.2023.1225093"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Popovi\u010d, N., and F\u00e4rber, M. (2025, January 4\u20139). Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China.","DOI":"10.18653\/v1\/2025.emnlp-main.1615"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hong, P., Chen, B., Peng, S., de Marneffe, M.C., and Plank, B. (2025, January 4\u20139). LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China.","DOI":"10.18653\/v1\/2025.emnlp-main.1728"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zong, C.C., Wang, Y.W., Ning, K.P., Ye, H.B., and Huang, S.J. (October, January 29). Bidirectional Uncertainty-Based Active Learning for Open-Set Annotation. Proceedings of the European Conference on Computer Vision (ECCV 2024), Milan, Italy. Part XXVIII.","DOI":"10.1007\/978-3-031-73390-1_8"},{"key":"ref_16","unstructured":"Sener, O., and Savarese, S. (2017). Active Learning for Convolutional Neural Networks: A Core-Set Approach. arXiv."},{"key":"ref_17","first-page":"8175","article-title":"Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets","volume":"Volume 162","author":"Chaudhuri","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning (ICML 2022)"},{"key":"ref_18","unstructured":"Doucet, P., Estermann, B., Aczel, T., and Wattenhofer, R. (2024, January 11). Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Training. Proceedings of the 5th Workshop on Practical ML for Limited\/Low Resource Settings (PML4LRS) @ ICLR 2024, Vienna, Austria."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Yao, B., Jindal, I., Popa, L., Katsis, Y., Ghosh, S., He, L., Lu, Y., Srivastava, S., Hendler, J.A., and Wang, D. (2023, January 6\u201310). Beyond labels: Empowering human with natural language explanations through a novel active-learning architecture. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore.","DOI":"10.18653\/v1\/2023.findings-emnlp.778"},{"key":"ref_20","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_21","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E.H., Le, Q.V., and Zhou, D. (December, January 28). Chain-of-thought prompting elicits reasoning in large language models. Proceedings of the Advances in Neural Information Processing Systems 35 (NIPS \u201922), Red Hook, NY, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1007\/978-3-032-04549-2_16","article-title":"Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study","volume":"Volume 16070","author":"Senn","year":"2026","journal-title":"Proceedings of the Artificial Neural Networks and Machine Learning\u2014ICANN 2025"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"109517","DOI":"10.1016\/j.compeleceng.2024.109517","article-title":"How rationals boost textual entailment modeling: Insights from large language models","volume":"119","author":"Pham","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Heredia, M., Etxaniz, J., Zulaika, M., Saralegi, X., Barnes, J., and Soroa, A. (2024, January 16\u201321). XNLIeu: A dataset for cross-lingual NLI in Basque. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Mexico City, Mexico.","DOI":"10.18653\/v1\/2024.naacl-long.234"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3267","DOI":"10.1007\/s10579-025-09844-1","article-title":"Myanmar XNLI: Building a dataset and exploring low-resource approaches to natural language inference with Myanmar","volume":"59","author":"Htet","year":"2025","journal-title":"Lang. Resour. Eval."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2019, January 3\u20137). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref_27","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_28","first-page":"3381","article-title":"Scaling Instruction-Finetuned Language Models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref_29","unstructured":"Hui, B., Yang, J., Cui, Z., Yang, J., Liu, D., Zhang, L., Liu, T., Zhang, J., Yu, B., and Lu, K. (2024). Qwen2.5-coder technical report. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Feng, F., Yang, Y., Cer, D., Arivazhagan, N., and Wang, W. (2022, January 22\u201327). Language-agnostic BERT Sentence Embedding. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics  (Volume 1: Long Papers), Dublin, Ireland.","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., and Liang, P. (2016, January 1\u20134). SQuAD: 100,000+ Questions for Machine Comprehension of Text. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA.","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref_33","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Hsieh, C.Y., Li, C.L., Yeh, C.K., Nakhost, H., Fujii, Y., Ratner, A.J., Krishna, R., Lee, C.Y., and Pfister, T. (2023, January 9\u201314). Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes. Proceedings of the the 61st Annual Meeting of the Association for Computational Linguistics, Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.findings-acl.507"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/2\/119\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T05:15:15Z","timestamp":1769577315000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/2\/119"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["info17020119"],"URL":"https:\/\/doi.org\/10.3390\/info17020119","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]}}}