Abstract
Commonsense reasoning is a difficult task for a computer, but a critical skill for an artificial intelligence (AI). It can enhance the explainability of AI models by enabling them to provide intuitive and human-like explanations for their decisions. This is necessary in many areas but especially in the field of question answering (QA), which is one of the most important tasks of natural language processing (NLP). Over time, a multitude of methods have emerged for solving commonsense reasoning problems such as knowledge-based approaches using formal logic or linguistic analysis.
In this paper, we investigate the effectiveness of large language models (LLMs) on different QA tasks with focus on their abilities on reasoning and producing explanations. For this, we study the recent and very prominent LLM ChatGPT and evaluate the results by means of a questionnaire. We demonstrate ChatGPT’s ability to reason with common sense, and although ChatGPT’s accuracy ranges from 56% to 93% on various QA benchmarks, it outperforms human accuracy. Furthermore we can appraise that, in the sense of explainable artificial intelligence (XAI), ChatGPT gives good explanations for its decisions. In our questionnaire we found that 68% of the participants quantify ChatGPT’s explanations as “good” or “excellent”. Taken together, these findings enrich our understanding of current LLMs and pave the way for future investigations of reasoning and explainability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Álvez, J., Lucio, P., Rigau, G.: Adimen-SUMO: Reengineering an ontology for first-order reasoning. Int. J. Semant. Web Int. Syst. (IJSWIS) 8(4), 80–116 (2012), https://ideas.repec.org/a/igg/jswis0/v8y2012i4p80-116.html
Barredo Arrieta, A., et al.: Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020). https://doi.org/10.1016/j.inffus.2019.12.012
Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems 33 (NeurIPS 2020), pp. 1877–1901 (2020). https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
Burkart, N., Huber, M.F.: A survey on the explainability of supervised machine learning. J. Artif. Intell. Res. 70, 245–317 (2021). https://doi.org/10.1613/jair.1.12228
Chen, M., D’arcy, M., Liu, A., Fernandez, J., Downey, D.: CODAH: An adversarially-authored question answering dataset for common sense. In: Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP, pp. 63–69 (2019). https://www.jaredfern.com/publication/codah/
Clark, P., et al.: Think you have solved question answering? Try ARC, the AI2 reasoning challenge. CoRR - Computing Research Repository abs/1803.05457, Cornell University Library (2018), https://arxiv.org/abs/1803.05457
Davis, E.: Logical formalizations of commonsense reasoning: a survey. J. Artif. Intell. Res. 59, 651–723 (2017). https://doi.org/10.1613/jair.5339
Davis, E., Marcus, G.: Commonsense reasoning and commonsense knowledge in artificial intelligence. Commun. ACM 58(9), 92–103 (2015). https://doi.org/10.1145/2701413
Deng, J., Lin, Y.: The benefits and challenges of ChatGPT: An overview. Front. Comput. Intell. Syst. 2(2), 81–83 (2023). https://doi.org/10.54097/fcis.v2i2.4465
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. https://arxiv.org/pdf/1810.04805
Du, L., Ding, X., Xiong, K., Liu, T., Qin, B.: e-CARE: a new dataset for exploring explainable causal reasoning. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 432–446. Association for Computational Linguistics (2022). https://aclanthology.org/2022.acl-long.33/
Forbus, K.D.: Qualitative process theory. Artif. Intell. 24(1–3), 85–168 (1984). https://doi.org/10.1016/0004-3702(84)90038-9
Furbach, U., Hölldobler, S., Ragni, M., Schon, C., Stolzenburg, F.: Cognitive reasoning: A personal view. KI 33(3), 209–217 (2019). https://link.springer.com/article/10.1007/s13218-019-00603-3
d’Avila Garcez, A.S., Broda, K., Gabbay, D.M.: Symbolic knowledge extraction from trained neural networks: A sound approach. Artificial Intelligence 125(1–2), 155–207 (2001). https://doi.org/10.1016/S0004-3702(00)00077-1
d’Avila Garcez, A., Lamb, L., Gabbay, D.: Neural-Symbolic Cognitive Reasoning. Springer, Berlin, Heidelberg (2009). https://doi.org/10.1007/978-3-540-73246-4
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
Huang, L., Le Bras, R., Bhagavatula, C., Choi, Y.: Cosmos QA: Machine reading comprehension with contextual commonsense reasoning. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 2391–2401. Association for Computational Linguistics (2019). https://aclanthology.org/D19-1243/
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., Müller, K.R.: Unmasking clever hans predictors and assessing what machines really learn. Nature Communications 10(1), 1096 (2019). https://www.nature.com/articles/s41467-019-08987-4
Lenat, D.B.: CYC: a large-scale investment in knowledge infrastructure. Commun. ACM 38(11), 33–38 (1995). https://doi.org/10.1145/219717.219745
Lewis, M., et al.: BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension (2019). arXiv:1910.13461
Liu, Hugo, Singh, Push: Commonsense Reasoning in and Over Natural Language. In: Negoita, Mircea Gh., Howlett, Robert J.., Jain, Lakhmi C.. (eds.) KES 2004. LNCS (LNAI), vol. 3215, pp. 293–306. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-30134-9_40
Liu, Y., et al: RoBERTa: A robustly optimized BERT pretraining approach. https://arxiv.org/pdf/1907.11692
McCarthy, J.: Programs with common sense (1959). https://www.cs.rit.edu/~rlaz/is2014/files/McCarthyProgramsWithCommonSense.pdf
McCarthy, J.: Artificial intelligence, logic and formalizing common sense. In: Thomason, R.H. (ed.) Philosophical Logic and Artificial Intelligence, pp. 161–190. Springer, Netherlands, Dordrecht (1989). https://doi.org/10.1007/978-94-009-2448-2_6
Mostafazadeh, N., Roth, M., Louis, A., Chambers, N., Allen, J.: LSDSem 2017 shared task: The Story Cloze Test. In: Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, pp. 46–51 (2017). https://aclanthology.org/W17-0906.pdf
Onoe, Y., Zhang, M.J.Q., Choi, E., Durrett, G.: CREAK: A dataset for commonsense reasoning over entity knowledge. https://arxiv.org/pdf/2109.01653
Pal, A., Umapathi, L.K., Sankarasubbu, M.: MedMCQA: A large-scale multi-subject multi-choice dataset for medical domain question answering. ACM Conference on Health (2022). https://arxiv.org/pdf/2203.14371
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. Tech. rep., OpenAI (2019). https://paperswithcode.com/paper/language-models-are-unsupervised-multitask
Roemmele, M., Bejan, C.A., Gordon, A.S.: Choice of plausible alternatives: An evaluation of commonsense causal reasoning. In: AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning, pp. 90–95 (2011), https://aaai.org/papers/02418-choice-of-plausible-alternatives-an-evaluation-of-commonsense-causal-reasoning/
Sap, M., et al.: ATOMIC: an atlas of machine commonsense for if-then reasoning. Proc. AAAI Conf. Artif. Intell. 33(01), 3027–3035 (2019). https://doi.org/10.1609/aaai.v33i01.33013027
Sap, M., Rashkin, H., Chen, D., LeBras, R., Choi, Y.: Social IQa: Commonsense reasoning about social interactions. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 4463–4473. Association for Computational Linguistics (2019). https://aclanthology.org/D19-1454/
Siebert, S., Schon, C., Stolzenburg, F.: Commonsense reasoning using theorem proving and machine learning. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) Machine Learning and Knowledge Extraction - 3rd IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2019, pp. 395–413. LNCS 11713, Springer Nature Switzerland, Canterbury, UK (2019). https://doi.org/10.1007/978-3-030-29726-8_25
Singh, S., et al.: COM2SENSE: A commonsense reasoning benchmark with complementary sentences. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 883–898. Association for Computational Linguistics (2021). https://aclanthology.org/2021.findings-acl.78
Speer, R., Chin, J., Havasi, C.: ConceptNet 5.5: An open multilingual graph of general knowledge. Proceedings of the AAAI Conference on Artificial Intelligence 31(1) (2017). https://doi.org/10.1609/aaai.v31i1.11164
Talmor, A., Herzig, J., Lourie, N., Berant, J.: CommonsenseQA: A question answering challenge targeting commonsense knowledge. https://arxiv.org/pdf/1811.00937
Taylor, J.E.T., Taylor, G.W.: Artificial cognition: how experimental psychology can help generate explainable artificial intelligence. Psychon. Bull. Rev. 28(2), 454–475 (2021). https://doi.org/10.3758/s13423-020-01825-5
Xu, Feiyu, Uszkoreit, Hans, Du, Yangzhou, Fan, Wei, Zhao, Dongyan, Zhu, Jun: Explainable AI: A Brief Survey on History, Research Areas, Approaches and Challenges. In: Tang, Jie, Kan, Min-Yen., Zhao, Dongyan, Li, Sujian, Zan, Hongying (eds.) NLPCC 2019. LNCS (LNAI), vol. 11839, pp. 563–574. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32236-6_51
Zellers, R., Bisk, Y., Schwartz, R., Choi, Y.: SWAG: A large-scale adversarial dataset for grounded commonsense inference. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 93–104. Association for Computational Linguistics (2018). https://aclanthology.org/D18-1009/
Zimmer, M., et al.: Differentiable logic machines. CoRR - Computing Research Repository abs/2102.11529, Cornell University Library (2021). https://arxiv.org/abs/2102.11529, latest revision 2023
Acknowledgments
We would like to thank Oliver Obst for sharing our questionnaire on LinkedIn and Osama Siddiqui for his help testing ChatGPT on different datasets. We would also like to thank the anonymous reviewers for their thoughtful reading and comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Krause, S., Stolzenburg, F. (2024). Commonsense Reasoning and Explainable Artificial Intelligence Using Large Language Models. In: Nowaczyk, S., et al. Artificial Intelligence. ECAI 2023 International Workshops. ECAI 2023. Communications in Computer and Information Science, vol 1947. Springer, Cham. https://doi.org/10.1007/978-3-031-50396-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-50396-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50395-5
Online ISBN: 978-3-031-50396-2
eBook Packages: Computer ScienceComputer Science (R0)