{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T12:33:54Z","timestamp":1769517234183,"version":"3.49.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045485","type":"print"},{"value":"9783032045492","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04549-2_16","type":"book-chapter","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T13:47:33Z","timestamp":1757425653000},"page":"192-204","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7831-3141","authenticated-orcid":false,"given":"Mahdi","family":"Dhaini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4941-9166","authenticated-orcid":false,"given":"Juraj","family":"Vladika","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6170-3541","authenticated-orcid":false,"given":"Ege","family":"Erdogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3990-9588","authenticated-orcid":false,"given":"Zineb","family":"Attaoui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3123-7268","authenticated-orcid":false,"given":"Gjergji","family":"Kasneci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"key":"16_CR1","unstructured":"Brown, T.B., et\u00a0al.: Language Models are Few-Shot Learners (2020). arXiv preprint arXiv:2005.14165"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"S\u00f8gaard, A.: Explainable Natural Language Processing (Springer, 2022)","DOI":"10.1007\/978-3-031-02180-0"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Lei, T., et\u00a0al.: Rationalizing neural predictions. In: Proc. EMNLP, pp. 107\u2013117 (2016)","DOI":"10.18653\/v1\/D16-1011"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"DeYoung, Z., et\u00a0al.: ERASER: a benchmark to evaluate rationalized NLP models. In: Proc. EMNLP, pp. 4443\u20134458 (2020)","DOI":"10.18653\/v1\/2020.acl-main.408"},{"key":"16_CR5","unstructured":"Wiegreffe, S., et\u00a0al.: A survey of annotated datasets for explainable natural language processing. arXiv preprint arXiv:2006.02366 (2020)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Rajani, N.F., et\u00a0al.: Explain yourself! leveraging language models for commonsense reasoning. arXiv preprint arXiv:1906.02361 (2019)","DOI":"10.18653\/v1\/P19-1487"},{"key":"16_CR7","unstructured":"Wei, J., et\u00a0al.: Chain-of-thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903 (2022)"},{"key":"16_CR8","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s10849-023-09410-4","volume":"33","author":"R Gubelmann","year":"2024","unstructured":"Gubelmann, R., et al.: Capturing the varieties of natural language inference: a systematic survey of existing datasets and two novel benchmarks. J. Logic Lang. Inform. 33, 21\u201348 (2024)","journal-title":"J. Logic Lang. Inform."},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Bowman, S.R., et\u00a0al.: A large annotated corpus for learning natural language inference. In: Proc. EMNLP, pp. 632\u2013642 (2015)","DOI":"10.18653\/v1\/D15-1075"},{"key":"16_CR10","unstructured":"Devlin, J., et\u00a0al.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proc. NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"16_CR11","unstructured":"Liu, Y., Ott, M., et\u00a0al. Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Madsen, A., et\u00a0al.: Post-hoc interpretability for neural NLP: A Survey. ACM Comput. Surv. 55 (2022)","DOI":"10.1145\/3546577"},{"key":"16_CR13","unstructured":"Wiegreffe, S., Marasovi\u0107, A.: Teach me to explain: a review of datasets for explainable NLP. In: Proc. NeurIPS Datasets and Benchmarks (2021)"},{"key":"16_CR14","unstructured":"Mardaoui, D., Garreau, D.: An analysis of LIME for text data. In: Proc. AISTATS, pp. 3493\u20133501 (2021)"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Mathew, B., et\u00a0al.: HateXplain: a benchmark dataset for explainable hate speech detection. In: Proc. AAAI, pp. 14867\u201314875 (2021)","DOI":"10.1609\/aaai.v35i17.17745"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Vladika, J., et\u00a0al.: Step-by-step fact verification system for medical claims with explainable reasoning. In: Proc. 2025 NAACL-HLT (Association for Computational Linguistics, Albuquerque, New Mexico, 2025), pp. 805\u2013816","DOI":"10.18653\/v1\/2025.naacl-short.68"},{"key":"16_CR17","unstructured":"Hartmann, J., et\u00a0al.: Survey on how human explanations improve model learning. In: Proc. EMNLP, pp. 1000\u20131010 (2022)"},{"key":"16_CR18","unstructured":"Tan, C., et\u00a0al.: The diversity of explanation types in natural language processing: implications and challenges. In: Proc. NAACL, pp. 3456\u20133465 (2021)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Mishra, A., et\u00a0al.: Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks in Findings of ACL (2024), 8117\u20138139","DOI":"10.18653\/v1\/2024.findings-acl.484"},{"key":"16_CR20","unstructured":"Wang, Q., et\u00a0al.: Cross-Refine: improving natural language explanation generation by learning in tandem. In: Proc. COLING, pp. 1150\u20131167 (2025)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Wei Jie, Y., et\u00a0al.: How interpretable are reasoning explanations from prompting large language models? In: Findings of NAACL, pp. 2148\u20132164 (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.138"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Schmidtova, P., et\u00a0al.: Automatic metrics in natural language generation: a survey of current evaluation practices. In: Proc. INLG, pp. 557\u2013583 (2024)","DOI":"10.18653\/v1\/2024.inlg-main.44"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Papineni, K., et\u00a0al.: Bleu: a method for automatic evaluation of machine translation In: Proc. ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"16_CR24","unstructured":"Lin, C.-Y.: ROUGE: A Package for Automatic Evaluation of Summaries in Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"16_CR25","unstructured":"Zhang, T., et\u00a0al.: BERTScore: evaluating text generation with BERT. In: Proc. ICLR (2020)"},{"key":"16_CR26","unstructured":"Pillutla, K., et\u00a0al.: MAUVE: measuring the gap between neural text and human text using divergence frontiers. In: Proc. NeurIPS (2021)"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment. In: Proc. EMNLP, pp. 2511\u20132522 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Yao, B., et\u00a0al.: Are human explanations always helpful? Towards objective evaluation of human natural language explanations. In: Proc. ACL, pp. 14698\u201314713 (2023)","DOI":"10.18653\/v1\/2023.acl-long.821"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Hartmann, M., Sonntag, D.: A survey on improving NLP models with human explanations. In: Proc. Workshop on Learning with Natural Language Supervision, pp. 40\u201347 (2022)","DOI":"10.18653\/v1\/2022.lnls-1.5"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Warner, B., Chaffin, A., et\u00a0al.: Smarter, better, faster, longer: a modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference. arXiv preprint arXiv:2412.13663 (2024)","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"16_CR31","unstructured":"Camburu, O.-M., et\u00a0al.: e-SNLI: Natural Language Inference with Natural Language Explanations. In: Proc. NeurIPS, pp. 9539\u20139549 (2018)"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Bowman, S. R. et\u00a0al.: A large annotated corpus for learning natural language inference. arXiv preprint arXiv:1508.05326 (2015)","DOI":"10.18653\/v1\/D15-1075"},{"key":"16_CR33","unstructured":"Vladika, J. et\u00a0al.: HealthFC: verifying health claims with evidence-based medical fact-checking. In: Proc. LREC-COLING, pp. 8095\u20138107 (2024)"},{"key":"16_CR34","unstructured":"He, P. et\u00a0al.: Deberta: decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 (2020)"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Quan, X., et\u00a0al.: Verification and refinement of natural language explanations through LLM-symbolic theorem proving. In: Proc. EMNLP, pp. 2933\u20132958 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.172"},{"key":"16_CR36","unstructured":"Chen, Y., et\u00a0al.: Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning. In: Proc. COLING (2025), pp. 7558\u20137568"},{"key":"16_CR37","volume-title":"TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks","author":"D Jiang","year":"2024","unstructured":"Jiang, D., et al.: TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks. Trans, Machine Learning Research (2024)"},{"key":"16_CR38","unstructured":"Kim, S. et\u00a0al.: Prometheus: inducing fine-grained evaluation capability in language models. In: Proc. ICLR (2024)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Parcalabescu, L., Frank, A.: On measuring faithfulness or self-consistency of natural language explanations. arXiv preprint arXiv:2311.07466 (2023)","DOI":"10.18653\/v1\/2024.acl-long.329"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04549-2_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T13:47:48Z","timestamp":1757425668000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04549-2_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"ISBN":["9783032045485","9783032045492"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04549-2_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"assertion":[{"value":"10 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}