{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T04:03:15Z","timestamp":1784520195242,"version":"3.55.0"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Materials analysis involves procedures designed to determine the composition and properties of materials using measurement instruments, primarily aiming to uncover the mechanisms behind unexpected phenomena (e.g., discoloration) and support the development of effective countermeasures. To accelerate this analytical process, we herein introduce a retrieval-augmented conversational system that integrates a 6.6-billion-parameter language model\u2014trained explicitly for materials analysis\u2014with a database of over 26,000 historical cases related to the study of organic and inorganic materials, including quantum-beam analysis. The language model is developed from the ground up, optimized for domain-specific understanding and task-specific performance, and further refined through preference learning, incorporating partial edits from more than 40 domain experts. During interactions, the system generates hypotheses regarding potential underlying causes and recommends suitable analytical methods for testing these hypotheses. An integrated follow-up question mechanism proactively identifies and queries the missing information required to formulate optimal investigative strategies. Architectural optimizations, including a reduced-parameter encoder and grouped-query attention, enable on-premise inference using a single workstation equipped with only 16 GB of graphics processing unit memory. In evaluations simulating real-world use cases, the proposed system outperforms a size-matched general-purpose open-weight language model in over 70% of the cases, based on preference judgments regarding its helpfulness in enhancing the precision and speed of materials analysis. We present the design rationale and training methodology of the system, as well as representative examples of its conversational capabilities.<\/jats:p>","DOI":"10.1007\/s00521-026-12254-1","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T07:59:06Z","timestamp":1782201546000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development of a domain-tailored on-premise dialogue system for accelerated materials analysis"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3928-0519","authenticated-orcid":false,"given":"Shigeaki","family":"Goto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1167-0072","authenticated-orcid":false,"given":"Michiaki","family":"Kamiyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eiichi","family":"Sudo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hidehiko","family":"Kimura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"12254_CR1","doi-asserted-by":"publisher","unstructured":"Narendra S, Shetty K, Ratnaparkhi A (2024) Enhancing contract negotiations with LLM\u2013based legal document comparison. In: Aletras N, Chalkidis I, Barrett L, Goan\u021b\u0103 C, Preo\u021biuc\u2013Pietro D, Spanakis G (eds) Proceedings of the natural legal language processing workshop. Association for Computational Linguistics, Miami, pp 143\u2013153. https:\/\/doi.org\/10.18653\/v1\/2024.nllp-1.11","DOI":"10.18653\/v1\/2024.nllp-1.11"},{"key":"12254_CR2","doi-asserted-by":"publisher","unstructured":"Louie R, Nandi A, Fang W, Chang C, Brunskill E, Yang D (2024) Roleplay-doh: Enabling domain-experts to create LLM-simulated patients via eliciting and adhering to principles. In: Proceedings of the 2024 conference on empirical methods in natural language processing. Association for Computational Linguistics, Miami, pp 10570\u201310603. https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.591","DOI":"10.18653\/v1\/2024.emnlp-main.591"},{"key":"12254_CR3","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1007\/s00521-024-10449-y","volume":"37","author":"M Yousef","year":"2025","unstructured":"Yousef M, Mohamed K, Medhat W, Mohamed EH, Khoriba G, Arafa T (2025) BeGrading: large language models for enhanced feedback in programming education. Neural Comput Applic 37:1027\u20131040. https:\/\/doi.org\/10.1007\/s00521-024-10449-y","journal-title":"Neural Comput Applic"},{"key":"12254_CR4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-98629-1","volume":"15","author":"M Sheikholeslami","year":"2025","unstructured":"Sheikholeslami M, Mazrouei N, Gheisari Y, Fasihi A, Irajpour M, Motahharynia A (2025) DrugGen enhances drug discovery with large language models and reinforcement learning. Sci Rep 15:13445. https:\/\/doi.org\/10.1038\/s41598-025-98629-1","journal-title":"Sci Rep"},{"key":"12254_CR5","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s00521-024-10382-0","volume":"37","author":"O Prieto-Ordaz","year":"2025","unstructured":"Prieto-Ordaz O, Ram\u00edrez-Alonso G, Montes-y-G\u00f3mez M, Lopez-Santillan R (2025) Toward an enhanced automatic medical report generator based on large transformer models. Neural Comput Applic 37:43\u201362. https:\/\/doi.org\/10.1007\/s00521-024-10382-0","journal-title":"Neural Comput Applic"},{"key":"12254_CR6","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","volume":"630","author":"J Abramson","year":"2024","unstructured":"Abramson J, Adler J, Dunger J, Evans R, Green T, Pritzel A, Ronneberger O, Willmore L, Ballard AJ, Bambrick J, Bodenstein SW (2024) Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630:493\u2013500. https:\/\/doi.org\/10.1038\/s41586-024-07487-w","journal-title":"Nature"},{"key":"12254_CR7","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1246\/bcsj.20230130","volume":"96","author":"K Nakaguro","year":"2023","unstructured":"Nakaguro K, Mitsuta Y, Koseki S, Oshiyama T, Asada T (2023) Computational approach for molecular design of small organic molecules with high hole mobilities in amorphous phase using random forest technique and computer simulation method. Bull Chem Soc Jpn 96:1099\u20131107. https:\/\/doi.org\/10.1246\/bcsj.20230130","journal-title":"Bull Chem Soc Jpn"},{"key":"12254_CR8","doi-asserted-by":"publisher","DOI":"10.1093\/bulcsj\/uoae110","volume":"97","author":"R Sasaki","year":"2024","unstructured":"Sasaki R, Fujinami M, Nakai H (2024) Application and integration of computer vision technologies for automated recognition and recording of chemical experiments. Bull Chem Soc Jpn 97:uoae110. https:\/\/doi.org\/10.1093\/bulcsj\/uoae110","journal-title":"Bull Chem Soc Jpn"},{"key":"12254_CR9","doi-asserted-by":"publisher","first-page":"1953","DOI":"10.1021\/acs.jchemed.3c01056","volume":"101","author":"A Gleim","year":"2024","unstructured":"Gleim A, Pence HE (2024) Artificial intelligence chatbots in chemical information seeking: Narrative educational insights via a SWOT analysis. J Chem Educ 101:1953\u20131958. https:\/\/doi.org\/10.1021\/acs.jchemed.3c01056","journal-title":"J Chem Educ"},{"key":"12254_CR10","doi-asserted-by":"publisher","DOI":"10.3390\/infrastructures10020035","volume":"10","author":"FA Boamah","year":"2025","unstructured":"Boamah FA, Jin X, Senaratne S, Perera S (2025) Transition from traditional knowledge retrieval into AI-powered knowledge retrieval in infrastructure projects: a literature review. Infrastructures 10:35. https:\/\/doi.org\/10.3390\/infrastructures10020035","journal-title":"Infrastructures"},{"key":"12254_CR11","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1038\/s42256-024-00832-8","volume":"6","author":"AM Bran","year":"2024","unstructured":"Bran AM, Cox S, Schilter O, Baldassari C, White AD, Schwaller P (2024) Augmenting large language models with chemistry tools. Nat Mach Intell 6:525\u2013535. https:\/\/doi.org\/10.1038\/s42256-024-00832-8","journal-title":"Nat Mach Intell"},{"key":"12254_CR12","doi-asserted-by":"publisher","unstructured":"Skarlinski MD, Cox S, Laurent JM, Braza JD, Hinks M, Hammerling MJ, Ponnapati M, Rodriques SG, White AD (2024) Language agents achieve superhuman synthesis of scientific knowledge. arXiv:2409.13740. https:\/\/doi.org\/10.48550\/arXiv.2409.13740","DOI":"10.48550\/arXiv.2409.13740"},{"key":"12254_CR13","unstructured":"L\u00e1la J, O\u2019Donoghue O, Shtedritski A, Cox S, Rodriques SG, White AD (2023) PaperQA: retrieval\u2011augmented generative agent for scientific research. arXiv"},{"key":"12254_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrp.2025.102523","volume":"6","author":"Z Zhao","year":"2025","unstructured":"Zhao Z, Ma D, Chen L, Sun L, Li Z, Xia Y, Chen B, Xu H, Zhu Z, Zhu S, Fan S, Shen G, Yu K, Chen X (2025) Developing ChemDFM as a large language foundation model for chemistry. Cell Rep Phys Sci 6:102523. https:\/\/doi.org\/10.1016\/j.xcrp.2025.102523","journal-title":"Cell Rep Phys Sci"},{"key":"12254_CR15","doi-asserted-by":"publisher","first-page":"15416","DOI":"10.52202\/079017-0493","volume":"37","author":"Z Liu","year":"2024","unstructured":"Liu Z, Ping W, Roy R, Xu P, Lee C, Shoeybi M, Catanzaro B (2024) ChatQA: Surpassing GPT-4 on conversational QA and RAG. Adv Neural Inf Process Syst 37:15416\u201315459. https:\/\/doi.org\/10.52202\/079017-0493","journal-title":"Adv Neural Inf Process Syst"},{"key":"12254_CR16","doi-asserted-by":"publisher","unstructured":"Balaguer A, Benara V, de F. L. Cunha R, Estev\u00e3o Filho R, Hendry T, Holstein D, Marsman J, Mecklenburg N, Malvar S, Nunes LO, Padilha R, Sharp M, Silva B, Sharma S, Aski V, Chandra R (2024) RAG vs fine\u2011tuning: Pipelines, tradeoffs, and a case study on agriculture. arXiv:2401.08406. https:\/\/doi.org\/10.48550\/arXiv.2401.08406","DOI":"10.48550\/arXiv.2401.08406"},{"key":"12254_CR17","doi-asserted-by":"publisher","first-page":"725","DOI":"10.18653\/v1\/2024.findings-emnlp.41","volume":"2024","author":"K Mao","year":"2024","unstructured":"Mao K, Liu Z, Qian H, Mo F, Deng C, Dou Z (2024) RAG\u2013studio: Towards in\u2013domain adaptation of retrieval\u2013augmented generation through self\u2013alignment. Find Assoc Comput Linguist EMNLP 2024:725\u2013735. https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.41","journal-title":"Find Assoc Comput Linguist EMNLP"},{"key":"12254_CR18","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux MA, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F, Rodriguez A, Joulin A, Grave E, Lample G (2023) LLaMA: open and efficient foundation language models. arXiv"},{"key":"12254_CR19","unstructured":"Taylor R, Kardas M, Cucurull G, Scialom T, Hartshorn A, Saravia E, Poulton A, Kerkez V, Stojnic R (2022) Galactica: a large language model for science. arXiv"},{"key":"12254_CR20","unstructured":"Thoppilan R, de Freitas D, Hall J, Shazeer N, Kulshreshtha A, Cheng HT, Jin A, Bos T, Baker L, Du Y, Li Y (2022) LaMDA: language models for dialog applications. arXiv"},{"key":"12254_CR21","doi-asserted-by":"publisher","unstructured":"Bao S, He H, Wang F, Wu H, Wang H (2020) PLATO: Pre-trained dialogue generation model with discrete latent variable. In: Proceedings of the 58th annual meeting of the association for computational linguistics. Association for Computational Linguistics, pp 85\u201396. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.9","DOI":"10.18653\/v1\/2020.acl-main.9"},{"key":"12254_CR22","unstructured":"Wei J, Bosma M, Zhao VY, Guu K, Yu AW, Lester B, Du N, Dai AM, Le QV (2022) Finetuned language models are zero-shot learners. In: Proceedings of the International Conference on Learning Representations (ICLR 2022)"},{"key":"12254_CR23","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis P, Perez E, Piktus A et al (2020) Retrieval\u2013augmented generation for knowledge\u2013intensive NLP tasks. Adv Neural Inf Process Syst 33:9459\u20139474","journal-title":"Adv Neural Inf Process Syst"},{"key":"12254_CR24","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1039\/d4dd00074a","volume":"3","author":"L Ge","year":"2024","unstructured":"Ge L, Docherty R, Cooper SJ (2024) Materials science in the era of large language models: a perspective. Digit Discov 3:1249\u20131442. https:\/\/doi.org\/10.1039\/d4dd00074a","journal-title":"Digit Discov"},{"key":"12254_CR25","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-025-01554-0","volume":"11","author":"X Jiang","year":"2025","unstructured":"Jiang X, Wang W, Tian S, Wang H, Lookman T, Su Y (2025) Applications of natural language processing and large language models in materials discovery. npj Comput Mater 11:15. https:\/\/doi.org\/10.1038\/s41524-025-01554-0","journal-title":"npj Comput Mater"},{"key":"12254_CR26","doi-asserted-by":"publisher","unstructured":"Edge D, Trinh H, Cheng N, Bradley J, Chao A, Mody A, Truitt S, Metropolitansky D, Ness RO, Larson J (2024) From local to global: A graph RAG approach to query-focused summarization. arXiv:2404.16130. https:\/\/doi.org\/10.48550\/arXiv.2404.16130","DOI":"10.48550\/arXiv.2404.16130"},{"key":"12254_CR27","doi-asserted-by":"publisher","unstructured":"Kang M, Kwak JM, Baek J, Hwang SJ (2023) Knowledge graph\u2011augmented language models for knowledge\u2011grounded dialogue generation. arXiv:2305.18846. https:\/\/doi.org\/10.48550\/arXiv.2305.18846","DOI":"10.48550\/arXiv.2305.18846"},{"key":"12254_CR28","doi-asserted-by":"publisher","unstructured":"Peng B, Zhu Y, Liu Y, Bo X, Shi H, Hong C, Zhang Y, Tang S (2024) Graph retrieval\u2011augmented generation: a survey. arXiv:2408.08921. https:\/\/doi.org\/10.48550\/arXiv.2408.08921","DOI":"10.48550\/arXiv.2408.08921"},{"key":"12254_CR29","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1557\/mrc.2019.94","volume":"9","author":"AM Ganose","year":"2019","unstructured":"Ganose AM, Jain A (2019) Robocrystallographer: Automated crystal structure text descriptions and analysis. MRS Commun 9:874\u2013881. https:\/\/doi.org\/10.1557\/mrc.2019.94","journal-title":"MRS Commun"},{"key":"12254_CR30","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/add3bb","volume":"6","author":"AN Rubungo","year":"2025","unstructured":"Rubungo AN, Li K, Hattrick-Simpers J, Dieng AB (2025) LLM4Mat-bench: benchmarking large language models for materials property prediction. Mach Learn Sci Technol 6:020501. https:\/\/doi.org\/10.1088\/2632-2153\/add3bb","journal-title":"Mach Learn Sci Technol"},{"key":"12254_CR31","doi-asserted-by":"publisher","unstructured":"Jiang Z, Ma X, Chen W (2024) LongRAG: Enhancing retrieval\u2011augmented generation with long\u2011context LLMs. arXiv:2406.15319. https:\/\/doi.org\/10.48550\/arXiv.2406.15319","DOI":"10.48550\/arXiv.2406.15319"},{"key":"12254_CR32","doi-asserted-by":"publisher","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th annual meeting of the association for computational linguistics. Association for Computational Linguistics, pp 7871\u20137880. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"12254_CR33","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21:1\u201367","journal-title":"J Mach Learn Res"},{"key":"12254_CR34","first-page":"1","volume":"33","author":"M Zaheer","year":"2020","unstructured":"Zaheer M, Guruganesh G, Dubey KA, Ainslie J, Alberti C, Onta\u00f1\u00f3n S, Pham P, Ravula A, Wang Q, Yang L, Ahmed A (2020) Big bird: Transformers for longer sequences. Adv Neural Inf Process Syst 33:1\u201317","journal-title":"Adv Neural Inf Process Syst"},{"key":"12254_CR35","doi-asserted-by":"publisher","unstructured":"Izacard G, Grave E (2021) Leveraging passage retrieval with generative models for open domain question answering. In: Merlo P, Tiedemann J, Tsarfaty R (eds) Proceedings of the 16th conference of the european chapter of the association for computational linguistics. Association for Computational Linguistics, pp 874\u2013880. https:\/\/doi.org\/10.18653\/v1\/2021.eacl-main.74","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"12254_CR36","doi-asserted-by":"publisher","unstructured":"Elfeki M, Liu R, Voegele C (2025) Return of the encoder: Maximizing parameter efficiency for SLMs. arXiv:2501.16273. https:\/\/doi.org\/10.48550\/arXiv.2501.16273","DOI":"10.48550\/arXiv.2501.16273"},{"key":"12254_CR37","doi-asserted-by":"publisher","unstructured":"Child R, Gray S, Radford A, Sutskever I (2019) Generating long sequences with sparse transformers. arXiv:1904.10509. https:\/\/doi.org\/10.48550\/arXiv.1904.10509","DOI":"10.48550\/arXiv.1904.10509"},{"key":"12254_CR38","doi-asserted-by":"publisher","unstructured":"Ainslie J, Lee-Thorp J, de Jong M, Zemlyanskiy Y, Lebron F, Sanghai S (2023) GQA: Training generalized multi-query transformer models from multi-head checkpoints. In: Proceedings of the 2023 conference on empirical methods in natural language processing. Association for Computational Linguistics, Singapore, pp 4895\u20134901. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.298","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"12254_CR39","first-page":"6803","volume":"35","author":"T Dao","year":"2022","unstructured":"Dao T, Fu DY, Ermon S, Rudra A, R\u00e9 C (2022) FlashAttention: Fast and memory\u2013efficient exact attention with IO\u2013awareness. Adv Neural Inf Process Syst 35:6803","journal-title":"Adv Neural Inf Process Syst"},{"key":"12254_CR40","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1126\/science.abq1158","volume":"378","author":"Y Li","year":"2022","unstructured":"Li Y, Choi D, Chung J, Kushman N, Schrittwieser J, Leblond R, Eccles T, Keeling J, Gimeno F, Dal Lago A, Hubert T (2022) Competition-level code generation with AlphaCode. Science 378:1092\u20131097. https:\/\/doi.org\/10.1126\/science.abq1158","journal-title":"Science"},{"key":"12254_CR41","doi-asserted-by":"publisher","unstructured":"Wang Y, Le H, Gotmare AD, Bui NDQ, Li J, Hoi SCH (2023) CodeT5+: Open code large language models for code understanding and generation. In: Proceedings of the 2023 conference on empirical methods in natural language processing. Association for Computational Linguistics, Singapore, pp 1069\u20131088. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.67","DOI":"10.18653\/v1\/2023.emnlp-main.67"},{"key":"12254_CR42","doi-asserted-by":"publisher","unstructured":"Yen H, Gao T, Chen D (2024) Long-context language modeling with parallel context encoding. In: Ku L-W, Martins AFT, Srikumar V (eds) Proceedings of the 62nd annual meeting of the association for computational linguistics. Association for Computational Linguistics, Bangkok, pp 2588\u20132610. https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.142","DOI":"10.18653\/v1\/2024.acl-long.142"},{"key":"12254_CR43","first-page":"15284","volume":"2024","author":"J Monteiro","year":"2024","unstructured":"Monteiro J, Marcotte \u00c9, No\u00ebl PA, Zantedeschi V, V\u00e1zquez D, Chapados N, Pal C, Taslakian P (2024) XC\u2013cache: Cross\u2013attending to cached context for efficient LLM inference. Find Assoc Comput Linguist EMNLP 2024:15284\u201315302.","journal-title":"Find Assoc Comput Linguist EMNLP"},{"key":"12254_CR44","doi-asserted-by":"publisher","unstructured":"Adiwardana D, Luong M-T, So D R, Hall J, Fiedel N, Thoppilan R, Yang Z, Kulshreshtha A, Nemade G, Lu Y, Le Q V (2020) Towards a human-like open-domain chatbot. arXiv:2001.09977. https:\/\/doi.org\/10.48550\/arXiv.2001.09977","DOI":"10.48550\/arXiv.2001.09977"},{"key":"12254_CR45","unstructured":"Mishra V, Singh S, Ahlawat D, Zaki M, Bihani V, Grover HS, Mishra B, Miret S, Mausam, Krishnan NMA (2024) Foundational large language models for materials research. arXiv:2412.09560"},{"key":"12254_CR46","unstructured":"Fujii K, Nakamura T, Loem M, Iida H, Ohi M, Hattori K, Hirai S, Mizuki S, Yokota R, Okazaki N (2024) Continual pre-training for cross-lingual LLM adaptation: Enhancing Japanese language capabilities. In: Proceedings of the first conference on language modeling (COLM). University of Pennsylvania, Philadelphia, p 25"},{"key":"12254_CR47","unstructured":"Okazaki N, Hattori K, Shota H, Iida H, Ohi M, Fujii K, Nakamura T, Loem M, Yokota R, Mizuki S (2024) Building a large Japanese web corpus for large language models. In: Proceedings of the first conference on language modeling (COLM). University of Pennsylvania, Philadelphia"},{"key":"12254_CR48","unstructured":"Sasaki A, Hirakawa M, Horie S, Nakamura T (2023) ELYZA-Japanese-Llama-2-7b. Hugging Face. https:\/\/huggingface.co\/elyza\/ELYZA-japanese-Llama-2-7b. Accessed 19 June 2025"},{"key":"12254_CR49","unstructured":"Lee M, Nakamura F, Shing M, McCann P, Akiba T, Orii N (2023) Japanese StableLM base beta 7B. Hugging Face. https:\/\/huggingface.co\/stabilityai\/japanese-stablelm-base-beta-7b. Accessed 19 June 2025"},{"key":"12254_CR50","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1039\/d4dd00319e","volume":"4","author":"C Bajan","year":"2025","unstructured":"Bajan C, Lambard G (2025) Exploring the expertise of large language models in materials science and metallurgical engineering. Digit Discov 4:500\u2013512. https:\/\/doi.org\/10.1039\/d4dd00319e","journal-title":"Digit Discov"},{"key":"12254_CR51","doi-asserted-by":"publisher","first-page":"6125","DOI":"10.1016\/j.cell.2024.09.022","volume":"187","author":"S Gao","year":"2024","unstructured":"Gao S, Fang A, Huang Y, Giunchiglia V, Noori A, Schwarz JR, Ektefaie Y, Kondic J, Zitnik M (2024) Empowering biomedical discovery with AI agents. Cell 187:6125\u20136151. https:\/\/doi.org\/10.1016\/j.cell.2024.09.022","journal-title":"Cell"},{"key":"12254_CR52","unstructured":"Kulkarni A, Alotaibi F, Zeng X, Wu L, Zeng T, Yao BM, Liu M, Zhang S, Huang L, Zhou D (2025) Scientific hypothesis generation and validation: Methods, datasets, and future directions. arXiv"},{"key":"12254_CR53","doi-asserted-by":"publisher","unstructured":"Cheng M, Luo Y, Ouyang J, Liu Q, Liu H, Li L, Yu S, Zhang B, Cao J, Ma J, Wang D, Chen E (2025) A survey on knowledge\u2011oriented retrieval\u2011augmented generation. arXiv:2503.10677. https:\/\/doi.org\/10.48550\/arXiv.2503.10677","DOI":"10.48550\/arXiv.2503.10677"},{"key":"12254_CR54","unstructured":"Bazgir A, Madugula RP, Zhang Y (2025) MatAgent: A human\u2013in\u2013the\u2013loop multi\u2013agent LLM framework for accelerating the material science discovery cycle. In: ICLR 2025 Workshop AI4MAT \u2013 Accelerated Materials Design. Poster, 2025"},{"key":"12254_CR55","unstructured":"Ren S, Jian P, Ren Z, Leng C, Xie C, Zhang J (2025) Towards scientific intelligence: A survey of LLM-based scientific agents. arXiv"},{"key":"12254_CR56","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: pre-training of Deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT 2019. Association for Computational Linguistics, Minneapolis, pp 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"12254_CR57","unstructured":"Beltagy I, Peters ME, Cohan A (2020) Longformer: The long-document transformer. arXiv"},{"key":"12254_CR58","doi-asserted-by":"crossref","unstructured":"Guo M, Ainslie J, Uthus D, Onta\u00f1\u00f3n S, Ni J, Sung YH, Yang Y (2022) LongT5: Efficient text-to-text transformer for long sequences. In: Findings of the Association for Computational Linguistics: NAACL 2022, pp 724\u2013736","DOI":"10.18653\/v1\/2022.findings-naacl.55"},{"key":"12254_CR59","unstructured":"Shazeer N (2019) Fast transformer decoding: One write-head is all you need. arXiv"},{"key":"12254_CR60","doi-asserted-by":"publisher","first-page":"38","DOI":"10.18653\/v1\/2020.emnlp-demos.6","volume-title":"Proceedings of the 2020 conference on empirical methods in natural language processing: System demonstrations","author":"T Wolf","year":"2020","unstructured":"Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P, Rault T, Louf R, Funtowicz M, Davison J, Shleifer S, von Platen P, Ma C, Jernite Y, Plu J, Xu C, Le Scao T, Gugger S, Drame M, Lhoest Q, Rush A (2020) Transformers: State-of-the-art natural language processing. In: Liu Q, Schlangen D (eds) Proceedings of the 2020 conference on empirical methods in natural language processing: System demonstrations. Association for Computational Linguistics, pp 38\u201345. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6"},{"key":"12254_CR61","first-page":"2440","volume-title":"Proceedings of the twelfth language resources and evaluation conference","author":"M Guo","year":"2020","unstructured":"Guo M, Dai Z, Vrande\u010di\u0107 D, Al-Rfou R (2020) Wiki-40B: Multilingual language model dataset. In: Calzolari N (ed) Proceedings of the twelfth language resources and evaluation conference. European Language Resources Association, Marseille, pp 2440\u20132452"},{"key":"12254_CR62","doi-asserted-by":"crossref","unstructured":"Hoffmann J, Borgeaud S, Mensch A, Buchatskaya E, Cai T, Rutherford E, de Las Casas D, Hendricks LA, Welbl J, Clark A, Hennigan T, Noland E, Millican K, van den Driessche G, Damoc B, Guy A, Osindero S, Simonyan K, Elsen E, Vinyals O, Rae J, Sifre L (2022) An empirical analysis of compute-optimal large language model training. In: Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A (eds) Proceedings of the 36th conference on neural information processing systems (NeurIPS 2022), New Orleans, 2022, pp 30016\u201330030","DOI":"10.52202\/068431-2176"},{"key":"12254_CR63","unstructured":"Zhang J, Zhao Y, Saleh M, Liu PJ (2020) PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization. In: Proceedings of the 37th international conference on machine learning. PMLR, pp 11328\u201311339"},{"key":"12254_CR64","doi-asserted-by":"publisher","first-page":"742","DOI":"10.18653\/v1\/2024.findings-naacl.48","volume":"2024","author":"Z Zhang","year":"2024","unstructured":"Zhang Z, Gangi Reddy R, Small K, Zhang T, Ji H (2024) Towards better generalization in open-domain question answering by mitigating context memorization. Find Assoc Comput Linguist NAACL 2024:742\u2013753. https:\/\/doi.org\/10.18653\/v1\/2024.findings-naacl.48","journal-title":"Find Assoc Comput Linguist NAACL"},{"key":"12254_CR65","doi-asserted-by":"publisher","first-page":"3982","DOI":"10.18653\/v1\/D19-1410","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","author":"N Reimers","year":"2019","unstructured":"Reimers N, Gurevych I (2019) Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In: Inui K, Jiang J, Ng V, Wan X (eds) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, Hong Kong, pp 3982\u20133992. https:\/\/doi.org\/10.18653\/v1\/D19-1410"},{"key":"12254_CR66","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv"},{"key":"12254_CR67","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov R, Sharma A, Mitchell E, Ermon S, Manning CD, Finn C (2023) Direct preference optimization: your language model is secretly a reward model. Adv Neural Inf Process Syst 36:53728\u201353741","journal-title":"Adv Neural Inf Process Syst"},{"key":"12254_CR68","unstructured":"von Werra L, Belkada Y, Tunstall L, Beeching E, Thrush T, Lambert N, Huang S, Rasul K, Gallou\u00e9dec Q (2020) TRL: Transformer reinforcement learning. GitHub repository. https:\/\/github.com\/huggingface\/trl. Accessed 20 June 2025"},{"key":"12254_CR69","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","volume":"645","author":"D Guo","year":"2025","unstructured":"Guo D, Yang D, Zhang H, Song J, Wang P, Zhu Q, Xu R, Zhang R, Ma S, Bi X, Zhang X, Yu X, Wu Y, Wu ZF, Gou Z, Shao Z, Li Z, Gao Z, Liu A, Xue B, Wang B, Wu B, Feng B, Lu C, Zhao C, Deng C, Ruan C, Dai D, Chen D, Ji D, Li E, Lin F, Dai F, Luo F, Hao G, Chen G, Li G, Zhang H, Xu H, Ding H, Gao H, Qu H, Li H, Guo J, Li J, Chen J, Yuan J, Tu J, Qiu J, Li J, Cai JL, Ni J, Liang J, Chen J, Dong K, Hu K, You K, Gao K, Guan K, Huang KX, Yu K, Wang L, Zhang L, Zhao L, Wang L, Zhang L, Zhang M, Zhang M, Tang M, Zhou M, Li M, Wang M, Li M, Tian N, Huang P, Zhang P, Wang Q, Chen Q, Du Q, Ge R, Zhang R, Pan R, Wang R, Chen RJ, Jin RL, Chen R, Lu S, Zhou S, Chen S, Ye S, Wang S, Yu S, Zhou S, Pan S, Li S, Zhou S, Wu S, Yun T, Pei T, Sun T, Wang T, Zeng W, Liu W, Liang W, Gao W, Yu W, Zhang W, Xiao WL, An W, Liu X, Wang X, Chen X, Nie X, Cheng X, Liu X, Xie X, Liu X, Yang X, Li X, Su X, Lin X, Li XQ, Jin X, Shen X, Chen X, Sun X, Wang X, Song X, Zhou X, Wang X, Shan X, Li YK, Wang YQ, Wei YX, Zhang Y, Xu YH, Li Y, Zhao Y, Sun YF, Wang YH, Yu Y, Zhang YC, Shi Y, Xiong YL, He Y, Piao Y, Wang YS, Tan Y, Ma Y, Liu Y, Guo YQ, Ou Y, Wang YD, Gong Y, Zou YH, He YJ, Zhu Y, Xiong YF, Luo YX, You YX, Liu YX, Zhou Y, Zhu YX, Huang YP, Li YH, Zheng Y, Zhu YC, Ma YX, Zhang ZL, Fu Z, Xu ZH, Xie Z, Zhang ZY, Hao Z, Ma Z, Yan Z, Wu Z, Gu Z, Zhu Z, Liu ZJ, Li Z, Xie ZW, Song Z, Pan Z, Huang Z, Xu ZP, Zhang ZY, Zhang Z (2025) DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645:633\u2013638. https:\/\/doi.org\/10.1038\/s41586-025-09422-z","journal-title":"Nature"},{"key":"12254_CR70","unstructured":"Blakeman A, Grattafiori A, Basant A, Gupta A, Khattar A, Renduchintala A, Vavre A, Shukla A, Bercovich A, Ficek A, Shaposhnikov A, Kondratenko A, Bukharin A, Milesi A, Taghibakhshi A, Liu A, Barton A, Mahabaleshwarkar AS, Klein A, Zuker A, Geifman A, Shen A, Bhiwandiwalla A, Tao A, Guan A, Mandarwal A, Mehta A, Aithal A, Poojary A, Ahamed A, Thekkumpate AK, Dattagupta A, Zhu B, Sadeghi B, Simkin B, Lanir B, Schifferer B, Nushi B, Kartal B, Darvish Rouhani B, Ginsburg B, Norick B, Soubasis B, Kisacanin B, Yu B, Catanzaro B, del Mundo C, Hwang C, Wang C, Hsieh C-P, Zhang C, Yu C, Mungekar C, Patel C, Alexiuk C, Parisien C, Neale C, Mosk-Aoyama D, Su D, Corneil D, Afrimi D, Rohrer D, Serebrenik D, Gitman D, Levy D, Stosic D, Mosallanezhad D, Narayanan D, Nathawani D, Rekesh D, Yared D, Kakwani D, Ahn D, Riach D, Stosic D, Minasyan E, Lin E, Long E, Long EP, Lantz E, Evans E, Ning E, Chung E, Harper E, Tramel E, Galinkin E, Pounds E, Briones E, Bakhturina E, Ladhak F, Wang F, Jia F, Soares F, Chen F, Galko F, Siino F, Hubara Agam G, Ajjanagadde G, Bhatt G, Prasad G, Armstrong G, Shen G, Batmaz G, Nalbandyan G, Qian H, Sharma H, Ross H, Ngo H, Sahota H, Wang H, Soni H, Upadhyay H, Mao H, Nguyen HC, Nguyen HQ, Cunningham I, Shahaf I, Gitman I, Loshchilov I, Moshkov I, Putterman I, Kautz J, Scowcroft JP, Casper J, Mitra J, Glick J, Chen J, Oliver J, Zhang J, Zeng J, Lou J, Zhang J, Huang J, Conway J, Guman J, Kamalu J, Greco J, Cohen J, Jennings J, Daw J, Veron Vialard J, Yi J, Parmar J, Xu K, Zhu K, Briski K, Cheung K, Luna K, Santhanam K, Shih K, Kong K, Bhardwaj K, Puvvada KC, Pawelec K, Anik K, McAfee L, Sleiman L, Derczynski L, Ding L, Liebenwein L, Vega L, Grover M, Van Segbroeck M, Rodrigues de Melo M, Sreedhar MN, Kilaru M, Ashkenazi M, Romeijn M, Cai M, Kliegl M, Moosaei M, Novikov M, Samadi M, Corpuz M, Wang M, Price M, Boone M, Evans M, Martinez M, Chrzanowski M, Shoeybi M, Patwary M, Mulepati N, Hereth N, Assaf N, Habibi N, Zmora N, Haber N, Sessions N, Bhatia N, Jukar N, Pope N, Ludwig N, Tajbakhsh N, Juluru N, Hrinchuk O, Kuchaiev O, Delalleau O, Olabiyi O, Ullman Argov O, Xie O, Chadha P, Shamis P, Molchanov P, Morkisz P, Dykas P, Jin P, Xu P, Januszewski P, Thombre PP, Varshney P, Gundecha P, Miao Q, Mahabadi RK, El-Yaniv R, Zilberstein R, Shafipour R, Harang R, Izzo R, Shahbazyan R, Garg R, Borkar R, Gala R, Islam R, Waleffe R, Watve R, Koren R, Zhang R, Hewett RJ, Prenger R, Timbrook R, Mahdavi S, Modi S, Kriman S, Kariyappa S, Satheesh S, Kaji S, Pasumarthi S, Narentharen S, Narenthiran S, Bak S, Kashirsky S, Poulos S, Mor S, Ramasamy S, Acharya S, Ghosh S, Sreenivas ST, Thomas S, Fan S, Gopal S, Prabhumoye S, Pachori S, Toshniwal S, Ding S, Singh S, Sun S, Ithape S, Majumdar S, Singhal S, Alborghetti S, Ge S, Devare SD, Barua SK, Panguluri S, Gupta S, Priyadarshi S, Akter SN, Bui T, Ene T-D, Kong T, Do T, Blankevoort T, Balough T, Asida T, Bar Natan T, Konuk T, Vashishth T, Karpas U, De U, Noorozi V, Noroozi V, Srinivasan V, Elango V, Korthikanti V, Kurin V, Lavrukhin V, Jiang W, Ahmad WU, Du W, Ping W, Zhou W, Jennings W, Zhang W, Prazuch W, Ren X, Karnati Y, Choi Y, Meyer Y, Wu Y-F, Zhang Y, Lin Y, Geifman Y, Fu Y, Subara Y, Suhara Y, Gao Y, Moshe Z, Dong Z, Liu Z, Chen Z, Yan Z (2025) Nemotron 3 nano: open, efficient mixture-of-experts hybrid mamba-transformer model for agentic reasoning. arXiv"},{"key":"12254_CR71","unstructured":"Yang A, Li A, Yang B, Zhang B, Hui B, Zheng B, Yu B, Gao C, Huang C, Lv C, Zheng C, Liu D, Zhou F, Huang F, Hu F, Ge H, Wei H, Lin H, Tang J, Yang J, Tu J, Zhang J, Yang J, Yang J, Zhou J, Zhou J, Lin J, Dang K, Bao K, Yang K, Yu L, Deng L, Li M, Xue M, Li M, Zhang P, Wang P, Zhu Q, Men R, Gao R, Liu S, Luo S, Li T, Tang T, Yin W, Ren X, Wang X, Zhang X, Ren X, Fan Y, Su Y, Zhang Y, Zhang Y, Wan Y, Liu Y, Wang Z, Cui Z, Zhang Z, Zhou Z, Qiu Z (2025) Qwen3 technical report. arXiv"},{"key":"12254_CR72","unstructured":"Preferred Networks, Inc (2025) PLaMo-embedding-1B. Hugging Face. https:\/\/huggingface.co\/pfnet\/plamo-embedding-1b. Accessed 17 April 2025"},{"key":"12254_CR73","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1162\/tacl_a_00021","volume":"6","author":"J Welbl","year":"2018","unstructured":"Welbl J, Stenetorp P, Riedel S (2018) Constructing datasets for multi-hop reading comprehension across documents. Trans Assoc Comput Linguist 6:287\u2013302. https:\/\/doi.org\/10.1162\/tacl_a_00021","journal-title":"Trans Assoc Comput Linguist"},{"key":"12254_CR74","unstructured":"Chen Z, Cano AH, Romanou A, Bonnet A, Matoba K, Salvi F, Pagliardini M, Fan S, K\u00f6pf A, Mohtashami A, Sallinen A (2023) MEDITRON-70B: scaling medical pretraining for large language models. arXiv"},{"key":"12254_CR75","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00752","author":"A Gu","year":"2023","unstructured":"Gu A, Dao T (2023) Mamba: linear-time sequence modeling with selective state spaces. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2312.00752","journal-title":"arXiv"},{"key":"12254_CR76","doi-asserted-by":"publisher","first-page":"4328","DOI":"10.52202\/068431-0313","volume":"35","author":"XL Li","year":"2022","unstructured":"Li XL, Thickstun J, Gulrajani I, Liang P, Hashimoto TB (2022) Diffusion-LM improves controllable text generation. Adv Neural Inf Process Syst 35:4328\u20134343","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12254-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-026-12254-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12254-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T03:38:52Z","timestamp":1784518732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-026-12254-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":76,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["12254"],"URL":"https:\/\/doi.org\/10.1007\/s00521-026-12254-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"assertion":[{"value":"28 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing financial or non-financial interests.","order":1,"name":"Ethics","label":"Conflicts of interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study is a system design and evaluation study. The Experimental Ethics Review Committee of Toyota Central R&D Laboratories, Inc. determined that formal ethics review was unnecessary (November 2022, application number 22\u00a0A-30).","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"528"}}