{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T06:25:31Z","timestamp":1774074331884,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":47,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819549689","type":"print"},{"value":"9789819549696","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"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\/978-981-95-4969-6_5","type":"book-chapter","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T08:47:54Z","timestamp":1763974074000},"page":"54-66","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating Large Language Models for\u00a0Real-World Engineering Tasks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1147-8205","authenticated-orcid":false,"given":"Ren\u00e9","family":"Heesch","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1434-8513","authenticated-orcid":false,"given":"Sebastian","family":"Eilermann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6522-4262","authenticated-orcid":false,"given":"Alexander","family":"Windmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8674-6895","authenticated-orcid":false,"given":"Alexander","family":"Diedrich","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8747-3596","authenticated-orcid":false,"given":"Oliver","family":"Niggemann","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,25]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Balhorn, L.S., Caballero, M., Schweidtmann, A.M.: Toward autocorrection of chemical process flowsheets using large language models. In: Computer Aided Chemical Engineering, vol.\u00a053, pp. 3109\u20133114. Elsevier (2024)","DOI":"10.1016\/B978-0-443-28824-1.50519-6"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Balzereit, K., Diedrich, A., et\u00a0al.: Generating causal hypotheses for explaining black-box industrial processes. In: 2023 5th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS). IEEE (2022)","DOI":"10.1109\/ICPS51978.2022.9816879"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Ban, T., Chen, L., et\u00a0al.: LLM-driven causal discovery via harmonized prior. IEEE Trans. Knowl. Data Eng. (2025)","DOI":"10.1109\/TKDE.2025.3528461"},{"key":"5_CR4","unstructured":"Betley, J., Tan, D., et\u00a0al.: Emergent misalignment: Narrow finetuning can produce broadly misaligned LLMs. arXiv preprint arXiv:2502.17424 (2025)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Bochman, A.: A logical theory of causality. MIT Press (2021)","DOI":"10.7551\/mitpress\/12387.001.0001"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chuganskaya, A.A., Kovalev, A.K., Panov, A.: The problem of concept learning and goals of reasoning in large language models. In: Garc\u00eda Bringas, P., P\u00e9rez, Garc\u00eda, ..., Corchado, E. (eds.) Hybrid Artificial Intelligent Systems, pp. 661\u2013672. Lecture Notes in Artificial Intelligence, Springer Nature Switzerland and Imprint Springer, Cham (2023)","DOI":"10.1007\/978-3-031-40725-3_56"},{"key":"5_CR7","unstructured":"DeepSeek-AI, Guo, D., et\u00a0al.: DeepSeek-R1: Incentivizing Reasoning capability in LLMs via reinforcement learning (2025)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Diedrich, A., Moddemann, L., Niggemann, O.: Learning system descriptions for cyber-physical systems. In: Proceedings of 12th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes (2024)","DOI":"10.1016\/j.ifacol.2024.07.289"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Diedrich, A., Niggemann, O.: On residual-based diagnosis of physical systems. Eng. Appl. Artif. Intell. (2022)","DOI":"10.1016\/j.engappai.2021.104636"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Efatmaneshnik, M., Bradley, J., Ryan, M.J.: Complexity and fragility in system of systems. Int. J. Syst. Syst. Eng. 7(4) (2016)","DOI":"10.1504\/IJSSE.2016.080323"},{"issue":"2","key":"5_CR11","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1016\/j.cirp.2012.05.001","volume":"61","author":"W ElMaraghy","year":"2012","unstructured":"ElMaraghy, W., ElMaraghy, H., Tomiyama, T., Monostori, L.: Complexity in engineering design and manufacturing. CIRP Ann. 61(2), 793\u2013814 (2012)","journal-title":"CIRP Ann."},{"key":"5_CR12","unstructured":"Feng, J., Russell, S., Steinhardt, J.: Monitoring latent world states in language models with propositional probes (2024). https:\/\/arxiv.org\/abs\/2406.19501"},{"key":"5_CR13","doi-asserted-by":"publisher","unstructured":"Grattafiori, A., Dubey, e.a.: The Llama 3 Herd of Models (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.21783","DOI":"10.48550\/arXiv.2407.21783"},{"issue":"1","key":"5_CR14","doi-asserted-by":"publisher","DOI":"10.1002\/aic.18259","volume":"70","author":"E Hirtreiter","year":"2024","unstructured":"Hirtreiter, E., Schulze Balhorn, L., Schweidtmann, A.M.: Toward automatic generation of control structures for process flow diagrams with large language models. AIChE J. 70(1), e18259 (2024)","journal-title":"AIChE J."},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long Short-Term Memory | Neural Computation. https:\/\/dl.acm.org\/doi\/10.1162\/neco.1997.9.8.1735 (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"5_CR16","unstructured":"Huang, J., Chang, K.C.C.: Towards reasoning in large language models: A survey (2023). https:\/\/arxiv.org\/abs\/2212.10403"},{"key":"5_CR17","unstructured":"Hurst, A., Lerer, A., et\u00a0al.: Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"5_CR18","unstructured":"Kang, S., An, G., Yoo, S.: A preliminary evaluation of LLM-based fault localization. arXiv preprint arXiv:2308.05487 (2023)"},{"issue":"1","key":"5_CR19","doi-asserted-by":"publisher","first-page":"11534","DOI":"10.1038\/s41598-023-38254-y","volume":"13","author":"S Kato","year":"2023","unstructured":"Kato, S., Zhang, C., Kano, M.: Simple algorithm for judging equivalence of differential-algebraic equation systems. Sci. Rep. 13(1), 11534 (2023)","journal-title":"Sci. Rep."},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"K\u00f6cher, A., Heesch, R., et\u00a0al.: A research agenda for AI planning in the field of flexible production systems. In: 2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS), pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/ICPS51978.2022.9816866"},{"key":"5_CR21","unstructured":"Li, K., Hopkins, A.K., et\u00a0al.: Emergent world representations: exploring a sequence model trained on a synthetic task. In: 2023 International Conference on Learning Representations (2024)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Meier, S., T\u00f6per, F., et\u00a0al.: Knowledge mining using generative AI for causal discovery in electronics production. In: 2024 47th International Spring Seminar on Electronics Technology (ISSE), vol.\u00a02024, pp. 1\u201310 (2024)","DOI":"10.1109\/ISSE61612.2024.10604102"},{"key":"5_CR23","unstructured":"Merkelbach, S., Diedrich, A., ..., Dumitrescu, R.: Using multi-modal LLMs to create models for fault diagnosis (short paper). In: 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Schloss Dagstuhl\u2013Leibniz-Zentrum f\u00fcr Informatik (2024)"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Ogundare, O., Araya, G.Q., Akrotirianakis, I., Shukla, A.: Resiliency analysis of llm generated models for industrial automation. In: 2023 International Conference on Modeling & E-Information Research, Artificial Learning and Digital Applications (ICMERALDA), pp. 113\u2013116. IEEE (2023)","DOI":"10.1109\/ICMERALDA60125.2023.10458189"},{"key":"5_CR25","unstructured":"Patel, R., Pavlick, E.: Mapping language models to grounded conceptual spaces. In: International Conference on Learning Representations (2022)"},{"key":"5_CR26","unstructured":"Peifeng, L., Qian, L., Zhao, X., Tao, B.: Joint knowledge graph and large language model for fault diagnosis and its application in aviation assembly. IEEE Trans. Indus. Inform. (2024)"},{"key":"5_CR27","unstructured":"Plaat, A., Wong, A., Verberne, S., Broekens, J., van Stein, N., Back, T.: Reasoning with large language models, a survey (2024). https:\/\/arxiv.org\/abs\/2407.11511"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Reinpold, L.M., Schieseck, M., et\u00a0al.: Exploring LLMs for verifying technical system specifications against requirements. In: 2024 IEEE 3rd Industrial Electronics Society Annual On-Line Conference (ONCON), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/ONCON62778.2024.10931625"},{"issue":"1","key":"5_CR29","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/0004-3702(87)90062-2","volume":"32","author":"R Reiter","year":"1987","unstructured":"Reiter, R.: A theory of diagnosis from first principles. Artif. Intell. 32(1), 57\u201395 (1987)","journal-title":"Artif. Intell."},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Saba, A., Hantach, R., Benslimane, M.: Text detection and recognition from piping and instrumentation diagrams. In: 2023 8th International Conference on Image, Vision and Computing (ICIVC), pp. 711\u2013716. IEEE (2023)","DOI":"10.1109\/ICIVC58118.2023.10270306"},{"key":"5_CR31","doi-asserted-by":"publisher","first-page":"2101","DOI":"10.1613\/jair.1.17175","volume":"82","author":"K Sowa","year":"2025","unstructured":"Sowa, K., Przegalinska, A.: From expert systems to generative artificial experts: a new concept for human-AI collaboration in knowledge work. J. Artif. Intell. Res. 82, 2101\u20132124 (2025)","journal-title":"J. Artif. Intell. Res."},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Steude, H., Windmann, A., Niggemann, O.: Learning Physical Concepts in CPS: A Case Study with a Three-Tank System. IFAC-PapersOnLine (2022)","DOI":"10.1016\/j.ifacol.2022.07.099"},{"key":"5_CR33","unstructured":"Suresh, V., Rawat, S.: GPT takes the sat: Tracing changes in test difficulty and students\u2019 math performance. Technical Report, working paper, Social Sciences Research Network (2024)"},{"key":"5_CR34","unstructured":"Sztyber-Betley, A., Chanthery, E., et\u00a0al.: Are diagnostic concepts within the reach of LLMs? In: 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025) (2025)"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Tang, H., Zhang, C., et\u00a0al.: Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities (2025)","DOI":"10.1145\/3715073.3715083"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Vicente, M., Guarda, J., Batista, F., et\u00a0al.: Gutenbrain: an architecture for equipment technical attributes extraction from piping and instrumentation diagrams. In: KDIR, pp. 204\u2013211 (2022)","DOI":"10.5220\/0011528500003335"},{"key":"5_CR37","unstructured":"Vranje\u0161, D., Ehrhardt, J., et\u00a0al.: Design principles for falsifiable, replicable and reproducible empirical machine learning research. In: 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024), pp.\u00a07\u20131 (2024)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Wang, L., Ma, C., et. al.: A survey on large language model based autonomous agents. Front. Comput. Sci. 18(6), 186345 (2024)","DOI":"10.1007\/s11704-024-40231-1"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Windmann, A., Wittenberg, P., Schieseck, M., Niggemann, O.: Artificial intelligence in industry 4.0: A review of integration challenges for industrial systems. In: 2024 IEEE 22nd International Conference on Industrial Informatics (INDIN), pp.\u00a01\u20138 (2024)","DOI":"10.1109\/INDIN58382.2024.10774364"},{"key":"5_CR40","unstructured":"Wu, Y., Li, Z., et\u00a0al.: Large language models in fault localisation. arXiv preprint arXiv:2308.15276 (2023)"},{"key":"5_CR41","unstructured":"Xia, Y., Jazdi, N., et\u00a0al.: Control industrial automation system with large language models. arXiv preprint arXiv:2409.18009 (2024)"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Xu, F., Lin, Q., et\u00a0al.: Are large language models really good logical reasoners? A comprehensive evaluation and beyond. IEEE Trans. Knowl. Data Eng. (2025)","DOI":"10.1109\/TKDE.2025.3536008"},{"key":"5_CR43","unstructured":"Yamada, Y., Bao, Y., et\u00a0al.: Evaluating spatial understanding of large language models. arXiv preprint arXiv:2310.14540 (2023)"},{"key":"5_CR44","unstructured":"Yang, A., Yang, B., et. al.: Qwen2 Technical Report (2024)"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Zeng, A., Chen, M., Zhang, L., Xu, Q.: Are transformers effective for time series forecasting? In: Proceedings of the AAAI Conference on Artificial Intelligence (2023)","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wang, X., et\u00a0al.: Llm4dyg: can large language models solve spatial-temporal problems on dynamic graphs? In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4350\u20134361 (2024)","DOI":"10.1145\/3637528.3671709"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhang, S., et\u00a0al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i12.17325"}],"container-title":["Lecture Notes in Computer Science","AI 2025: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4969-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T20:57:41Z","timestamp":1769893061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4969-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"ISBN":["9789819549689","9789819549696"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4969-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,25]]},"assertion":[{"value":"25 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canberra, ACT","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"1 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}