Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Advertisement

Humanities and Social Sciences Communications
  • View all journals
  • Search
  • My Account Login
  • Content Explore content
  • About the journal
  • Publish with us
  • Sign up for alerts
  • RSS feed
  1. nature
  2. humanities and social sciences communications
  3. articles
  4. article
Large language model tools as catalysts for collective cognition in collaborative new-product development: a quasi-experimental study
Download PDF
Download PDF
  • Article
  • Open access
  • Published: 23 February 2026

Large language model tools as catalysts for collective cognition in collaborative new-product development: a quasi-experimental study

  • Deyin Zhang1,2,
  • Shijian Luo1,
  • Yue Liu1,
  • Xiyuan Zhang1,
  • Yuqi Hu1,
  • Jianan Shen1,
  • Peiqi Yi1,
  • Kayu Zhao1 &
  • …
  • Wei Liu2 

Humanities and Social Sciences Communications , Article number:  (2026) Cite this article

We are providing an unedited version of this manuscript to give early access to its findings. Before final publication, the manuscript will undergo further editing. Please note there may be errors present which affect the content, and all legal disclaimers apply.

Subjects

  • Cultural and media studies
  • Information systems and information technology
  • Psychology
  • Science, technology and society

Abstract

Modern organisations frequently face complex cognitive challenges in Collaborative New-Product Development (Co-NPD), particularly when integrating dispersed knowledge and coordinating work across different development phases. To investigate how Large Language Models (LLMs) influence collective cognition and collaborative processes, this study introduces the 2I2A model, which defines four collaboration spaces and eight associated communication dimensions. A mixed-methods design was adopted, combining quantitative analysis of collaborative behaviours with semi-structured interviews analysed using grounded theory. The findings indicate that LLMs mainly support the early stages of Co-NPD by expanding collective cognitive boundaries, improving knowledge integration and facilitating idea generation. However, their contribution to deeper analytical reasoning, negotiation and solution integration is more limited. The grounded theory analysis additionally highlights potential drawbacks, including reduced collaborative naturalness and a tendency toward over-reliance on LLM-generated suggestions. Overall, the study suggests that the 2I2A model offers a useful framework for examining how collective cognition develops in Co-NPD and clarifies both the potential and the boundaries of LLM assistance in collaborative innovation.

Data availability

The datasets generated and analysed during this study contain human interaction data and are subject to ethical approval conditions, participant consent, and applicable privacy and data-protection requirements.An anonymised subset of the data, including segment-level coded datasets, coding schemes, grounded theory analysis outputs, and quantitative analysis files (SPSS), has been made available to the editors and reviewers during peer review via the journal’s submission system.Original audio recordings and full verbatim conversational transcripts cannot be publicly shared due to ethical and confidentiality constraints, as they contain potentially identifiable interpersonal communication data and were not consented for unrestricted disclosure.Further anonymised data supporting the findings of this study may be made available from the corresponding author upon reasonable request, subject to ethical approval and participant consent.

References

  • Alaskar TH, Alsadi AK, Aloulou WJ, Ayadi FM (2024) Big data analytics, strategic capabilities, and innovation performance: mediation approach of organizational ambidexterity. Sustainability 16(12):5111. https://doi.org/10.3390/su16125111

    Google Scholar 

  • Alavi M, Leidner DE (2001) Review: knowledge management and knowledge management systems: conceptual foundations and research issues. MIS Q 25(1):107–136. https://doi.org/10.2307/3250961

    Google Scholar 

  • Alkhwaldi AF (2024) Understanding the acceptance of business intelligence from healthcare professionals’ perspective: an empirical study of healthcare organizations. Int J Organ Anal 32(9):2135–2163. https://doi.org/10.1108/IJOA-10-2023-4063

    Google Scholar 

  • Alkhwaldi AF, Abdulmuhsin AA, Masa’deh R, Abu-AlSondos IA (2025) Business intelligence adoption in higher education: the role of data-driven decision-making culture and UTAUT. J Int Educ Bus 18(4):484–504. https://doi.org/10.1108/JIEB-08-2024-0110

    Google Scholar 

  • Andrews RW, Lilly JM, Srivastava D, Feigh KM (2023) The role of shared mental models in human-AI teams: a theoretical review. Theor Issues Ergonomics Sci 24(2):129–175. https://doi.org/10.1080/1463922X.2022.2061080

    Google Scholar 

  • Asarnow S (2020) Shared agency without shared intention. Philos Q 70(281):665–688. https://doi.org/10.1093/pq/pqaa012

    Google Scholar 

  • Badke-Schaub P, Neumann A, Lauche K, Mohammed S (2007) Mental models in design teams: a valid approach to performance in design collaboration?. CoDesign 3(1):5–20. https://doi.org/10.1080/15710880601170768

    Google Scholar 

  • Ball LJ, Ormerod TC, Morley NJ (2004) Spontaneous analogising in engineering design: a comparative analysis of experts and novices. Des Stud 25(5):495–508. https://doi.org/10.1016/j.destud.2004.05.004

    Google Scholar 

  • Beverland MB, Micheli P, Farrelly FJ (2016) Resourceful sensemaking: overcoming barriers between marketing and design in NPD. J Prod Innov Manag 33(5):628–648. https://doi.org/10.1111/jpim.12313

    Google Scholar 

  • Bowen GA (2008) Naturalistic inquiry and the saturation concept: a research note. Qualitative Res 8(1):137–152. https://doi.org/10.1177/1468794107085301

    Google Scholar 

  • Burton JW, Lopez-Lopez E, Hechtlinger S, Rahwan Z, Aeschbach S, Bakker MA, Becker JA, Berditchevskaia A, Berger J, Brinkmann L, Flek L, Herzog SM, Huang S, Kapoor S, Narayanan A, Nussberger A-M, Yasseri T, Nickl P, Almaatouq A, Hertwig R (2024) How large language models can reshape collective intelligence. Nat Hum Behav 8(9):1643–1655. https://doi.org/10.1038/s41562-024-01959-9

    Google Scholar 

  • Carragher DJ, Sturman D, Hancock PJB (2024) Trust in automation and the accuracy of human–algorithm teams performing one-to-one face matching tasks. Cogn Res Princ Implic 9(1):41. https://doi.org/10.1186/s41235-024-00564-8

    Google Scholar 

  • Carraro M, Furlan A, Netland T (2025) Unlocking team performance: how shared mental models drive proactive problem-solving. Hum Relat 78(4):407–437. https://doi.org/10.1177/00187267241247962

    Google Scholar 

  • Carroll JM (1997) Human–computer interaction: psychology as a science of design. Int J Hum Comput Stud 46(4):501–522. https://doi.org/10.1006/ijhc.1996.0101

    Google Scholar 

  • Cha KJ, Kim YS, Park B, Lee CK (2015) Knowledge management technologies for collaborative intelligence: a study of case company in Korea. Int J Distrib Sens Netw 11(9):368273. https://doi.org/10.1155/2015/368273

    Google Scholar 

  • Chalmers PA (2003) The role of cognitive theory in human–computer interface. Comput Hum Behav 19(5):593–607. https://doi.org/10.1016/S0747-5632(02)00086-9

    Google Scholar 

  • Chan C-S (1990) Cognitive processes in architectural design problem solving. Des Stud 11(2):60–80. https://doi.org/10.1016/0142-694X(90)90021-4

    Google Scholar 

  • Charmaz K, Thornberg R (2021) The pursuit of quality in grounded theory. Qualitative Res Psychol 18(3):305–327. https://doi.org/10.1080/14780887.2020.1780357

    Google Scholar 

  • Charters E (2003) The use of think-aloud methods in qualitative research an introduction to think-aloud methods. Brock Educ J 12(2), https://doi.org/10.26522/brocked.v12i2.38

  • Chen O, Paas F, Sweller J (2023) A cognitive load theory approach to defining and measuring task complexity through element interactivity. Educ Psychol Rev 35(2):63. https://doi.org/10.1007/s10648-023-09782-w

    Google Scholar 

  • Chen Y, Wang Y, Nevo S, Benitez-Amado J, Kou G (2015) IT capabilities and product innovation performance: the roles of corporate entrepreneurship and competitive intensity. Inf Manag 52(6):643–657. https://doi.org/10.1016/j.im.2015.05.003

    Google Scholar 

  • Christiansen JK, Varnes CJ (2009) Formal rules in product development: sensemaking of structured approaches. J Prod Innov Manag 26(5):502–519. https://doi.org/10.1111/j.1540-5885.2009.00677.x

    Google Scholar 

  • Chun Tie Y, Birks M, Francis K (2019) Grounded theory research: a design framework for novice researchers. SAGE Open Med 7: 2050312118822927. https://doi.org/10.1177/2050312118822927

    Google Scholar 

  • Clarke A, Healy K, Lynch D, Featherstone G (2023) The use of a constructivist grounded theory method—a good fit for social work research. Int J Qualitative Methods 22: 16094069231186257. https://doi.org/10.1177/16094069231186257

    Google Scholar 

  • Cody WF, Kreulen JT, Krishna V, Spangler WS (2002) The integration of business intelligence and knowledge management. IBM Syst J 41(4):697–713. https://doi.org/10.1147/sj.414.0697

    Google Scholar 

  • Cohn C, Snyder C, Montenegro J, Biswas G (2024) Towards a human-in-the-loop LLM approach to collaborative discourse analysis. In: Olney AM, Chounta I-A, Liu Z, Santos OC, Bittencourt II (eds) Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky. Springer Nature Switzerland, pp. 11–19 https://doi.org/10.1007/978-3-031-64312-5_2

  • Cooke NJ, Cohen MC, Fazio WC, Inderberg LH, Johnson CJ, Lematta GJ, Peel M, Teo A (2024) From teams to teamness: future directions in the science of team cognition. Hum Factors 66(6):1669–1680. https://doi.org/10.1177/00187208231162449

    Google Scholar 

  • Corallo A, Lazoi M, Secundo G (2012) Inter-organizational knowledge integration in Collaborative NPD projects: evidence from the aerospace industry. Knowl Manag Res Pract 10(4):354–367. https://doi.org/10.1057/kmrp.2012.25

    Google Scholar 

  • Corbin JM, Strauss A (1990) Grounded theory research: procedures, canons, and evaluative criteria. Qualitative Sociol 13(1):3–21. https://doi.org/10.1007/BF00988593

    Google Scholar 

  • Cowan R (2001) Expert systems: aspects of and limitations to the codifiability of knowledge. Res Policy 30(9):1355–1372. https://doi.org/10.1016/S0048-7333(01)00156-1

    Google Scholar 

  • Creswell JW, Clark VLP (2017) Designing and conducting mixed methods research. Sage publications. https://books.google.com/books?hl=zh-CN&lr=&id=BXEzDwAAQBAJ&oi=fnd&pg=PP1&dq=Creswell+%26+Clark+(2017)&ots=UlzeNkisoF&sig=U_vgeSWRg0RvMoyYdgTznvCwX_Y

  • Cuskley C, Woods R, Flaherty M (2024) The limitations of large language models for understanding human language and cognition. Open Mind 8:1058–1083. https://doi.org/10.1162/opmi_a_00160

    Google Scholar 

  • Danish JA, Enyedy N, Saleh A, Humburg M (2020) Learning in embodied activity framework: a sociocultural framework for embodied cognition. Int J Comput Support Collab Learn 15(1):49–87. https://doi.org/10.1007/s11412-020-09317-3

    Google Scholar 

  • DeChurch LA, Mesmer-Magnus JR (2010) The cognitive underpinnings of effective teamwork: a meta-analysis. J Appl Psychol 95(1):32–53. https://doi.org/10.1037/a0017328

    Google Scholar 

  • Dell’Era C, Magistretti S, Cautela C, Verganti R, Zurlo F (2020) Four kinds of design thinking: from ideating to making, engaging, and criticizing. Creativity Innov Manag 29(2):324–344. https://doi.org/10.1111/caim.12353

    Google Scholar 

  • Demetriadis S, Dimitriadis Y (2023) Conversational agents and language models that learn from human dialogues to support design thinking. In: Frasson C, Mylonas P, Troussas C (eds) Augmented intelligence and intelligent tutoring systems. Springer Nature Switzerland, pp. 691–700. https://doi.org/10.1007/978-3-031-32883-1_60

  • Eccles DW, Arsal G (2017) The think aloud method: what is it and how do I use it?. Qualitative Res Sport Exerc Health 9(4):514–531. https://doi.org/10.1080/2159676X.2017.1331501

    Google Scholar 

  • Edwards JS, Shaw D, Collier PM (2005) Knowledge management systems: finding a way with technology. J Knowl Manag 9(1):113–125. https://doi.org/10.1108/13673270510583009

    Google Scholar 

  • Ericsson KA (2017) Protocol analysis. In: A companion to cognitive science. John Wiley and Sons, Ltd. pp. 425–432. https://doi.org/10.1002/9781405164535.ch33

  • Fan I-S, Li G, Lagos-Hernandez M, Bermell-Garci´a P, Twelves M (2008) A rule level knowledge management system for knowledge based engineering applications. pp. 813–821. https://doi.org/10.1115/DETC2002/CIE-34501

  • Fauconnier G (1994) Mental spaces: aspects of meaning construction in natural language. Cambridge University Press

  • Feng KJK, Liao QV, Xiao Z, Wortman Vaughan J, Zhang AX, McDonald DW (2025) Canvil: designerly adaptation for LLM-powered user experiences. In: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3706598.3713139

  • Fiore SM, Wiltshire TJ (2016) Technology as teammate: examining the role of external cognition in support of team cognitive processes. Front Psychol, 7. https://doi.org/10.3389/fpsyg.2016.01531

  • Galesic M, Barkoczi D, Berdahl AM, Biro D, Carbone G, Giannoccaro I, Goldstone RL, Gonzalez C, Kandler A, Kao AB, Kendal R, Kline M, Lee E, Massari GF, Mesoudi A, Olsson H, Pescetelli N, Sloman SJ, Smaldino PE, Stein DL (2023) Beyond collective intelligence: collective adaptation. J R Soc Interface 20(200):20220736. https://doi.org/10.1098/rsif.2022.0736

    Google Scholar 

  • Gao C, Lan X, Li N, Yuan Y, Ding J, Zhou Z, Xu F, Li Y (2024) Large language models empowered agent-based modeling and simulation: a survey and perspectives. Humanit Soc Sci Commun 11(1):1259. https://doi.org/10.1057/s41599-024-03611-3

    Google Scholar 

  • Ge S, Sun Y, Cui Y, Wei D (2025) An innovative solution to design problems: applying the chain-of-thought technique to integrate LLM-based agents with concept generation methods. IEEE Access 13:10499–10512. https://doi.org/10.1109/ACCESS.2024.3494054

    Google Scholar 

  • Gibson CB (2001) From knowledge accumulation to accommodation: cycles of collective cognition in work groups. J Organ Behav 22(2):121–134. https://doi.org/10.1002/job.84

    Google Scholar 

  • Gross T (2013) Supporting effortless coordination: 25 years of awareness research. Comput Support Cooperat Work 22(4):425–474. https://doi.org/10.1007/s10606-013-9190-x

    Google Scholar 

  • Hao X, Demir E, Eyers D (2024) Exploring collaborative decision-making: a quasi-experimental study of human and generative AI interaction. Technol Soc 78:102662. https://doi.org/10.1016/j.techsoc.2024.102662

    Google Scholar 

  • Heintz C, Scott-Phillips T (2023) Expression unleashed: the evolutionary and cognitive foundations of human communication. Behav Brain Sci 46:e1. https://doi.org/10.1017/S0140525X22000012

    Google Scholar 

  • Herm L-V, Heinrich K, Wanner J, Janiesch C (2023) Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability. Int J Inf Manag 69:102538. https://doi.org/10.1016/j.ijinfomgt.2022.102538

    Google Scholar 

  • Hirschberg J, Manning CD (2015) Advances in natural language processing. Science 349(6245):261–266. https://doi.org/10.1126/science.aaa8685

    Google Scholar 

  • Ho M-T, Vuong Q-H (2025) Five premises to understand human–computer interactions as AI is changing the world. AI SOCIETY 40(2):1161–1162. https://doi.org/10.1007/s00146-024-01913-3

    Google Scholar 

  • Hoff KA, Bashir M (2015) Trust in automation: integrating empirical evidence on factors that influence trust. Hum Factors 57(3):407–434. https://doi.org/10.1177/0018720814547570

    Google Scholar 

  • Holm S (1979) A simple sequentially rejective multiple test procedure. Scand J Stat 6(2):65–70

    Google Scholar 

  • Huang C, Deng Y, Lei W, Lv J, Chua T-S, Huang J (2025) How to enable effective cooperation between humans and NLP models: a survey of principles, formalizations, and beyond. In: Che W, Nabende J, Shutova E, Pilehvar MT (eds) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, pp. 466–488, https://doi.org/10.18653/v1/2025.acl-long.22

  • Hurtienne J (2009) Cognition in HCI: an ongoing story. Hum Technol 5(1):12–28. https://doi.org/10.17011/ht/urn.20094141408

    Google Scholar 

  • Iskra, M, Voigt L, Raab M (2024) Accounting for dynamic cognition–action interaction in decision-making tasks in sports: a scoping review. Sport Exercise Perform Psychol, https://doi.org/10.1037/spy0000361

  • Järvelä S, Kirschner PA, Hadwin A, Järvenoja H, Malmberg J, Miller M, Laru J (2016) Socially shared regulation of learning in CSCL: Understanding and prompting individual- and group-level shared regulatory activities. Int J Comput Support Collab Learn 11(3):263–280. https://doi.org/10.1007/s11412-016-9238-2

    Google Scholar 

  • Jin X, Dong H, Evans M, Yao A (2024) Inspirational stimuli to support creative ideation for the design of artificial intelligence-powered products. J Mech Des 146: 121402. https://doi.org/10.1115/1.4065696

    Google Scholar 

  • Jin Y, Benami O (2010) Creative patterns and stimulation in conceptual design. AI EDAM 24(2):191–209. https://doi.org/10.1017/S0890060410000053

    Google Scholar 

  • Jordan MI, Mitchell TM (2015) Machine learning: trends, perspectives, and prospects. Science, https://doi.org/10.1126/science.aaa8415

  • Kang HB, Lin DC-E Chen Y-Y, Hong MK, Martelaro N, Kittur A (2025) BioSpark: beyond analogical inspiration to LLM-augmented transfer. In: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3706598.3714053

  • Kernan Freire S, Wang C, Foosherian M, Wellsandt S, Ruiz-Arenas S, Niforatos E (2024) Knowledge sharing in manufacturing using LLM-powered tools: User study and model benchmarking. Front Artif Intelli 7. https://doi.org/10.3389/frai.2024.1293084

  • Kim J, Ryu H (2014) A design thinking rationality framework: framing and solving design problems in early concept generation. Hum Comput Interact 29(5–6):516–553. https://doi.org/10.1080/07370024.2014.896706

    Google Scholar 

  • Kim MH, Kim YS, Lee HS, Park JA (2007) An underlying cognitive aspect of design creativity: limited commitment mode control strategy. Des Stud 28(6):585–604. https://doi.org/10.1016/j.destud.2007.04.006

    Google Scholar 

  • Kolasani S (2023) Optimizing natural language processing, large language models (LLMs) for efficient customer service, and hyper-personalization to enable sustainable growth and revenue. Trans Latest Trends Artif Intell, 4(4). https://ijsdcs.com/index.php/TLAI/article/view/476

  • Kozar O (2010) Towards better group work: seeing the difference between cooperation and collaboration. Engl Teach Forum 48(2):16–23

    Google Scholar 

  • Kyriakopoulos K, De Ruyter K (2004) Knowledge stocks and information flows in new product development. J Manag Stud 41(8):1469–1498. https://doi.org/10.1111/j.1467-6486.2004.00482.x

    Google Scholar 

  • Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33(1):159–174. https://doi.org/10.2307/2529310

    Google Scholar 

  • Lane D, Seery N (2011) Examining the development of sketch thinking and behaviour. In: 118th ASEE Annual Conference and Exposition. https://peer.asee.org/17944

  • Lebiere C, Blaha LM, Fallon CK, Jefferson B (2021) Adaptive cognitive mechanisms to maintain calibrated trust and reliance in automation. Front Robot AI, 8. https://doi.org/10.3389/frobt.2021.652776

  • Leblebici-Başar D, Altarriba J (2013) The role of imagery and emotion in the translation of concepts into product form. Des J 16(3):295–314. https://doi.org/10.2752/175630613X13660502571787

    Google Scholar 

  • Lee JD, See KA (2004) Trust in automation: designing for appropriate reliance. Hum Factors 46(1):50–80. https://doi.org/10.1518/hfes.46.1.50_30392

    Google Scholar 

  • Lee J, Gu N, Williams AP (2014) Parametric design strategies for the generation of creative designs. Int J Architectural Comput 12(3):263–282. https://doi.org/10.1260/1478-0771.12.3.263

    Google Scholar 

  • Lee JH, Ostwald MJ (2025) Enhancing online design collaboration: revealing cognitive and linguistic fusion in remote teamwork. Int J Des Creativity Innov 13(3):139–158. https://doi.org/10.1080/21650349.2025.2481254

    Google Scholar 

  • Lee JH, Ostwald MJ, Gu N (2020) Collaborative design: team cognition and communication. In: Lee JH, Ostwald MJ, Gu N (eds) Design thinking: creativity, collaboration and culture. Springer International Publishing, pp. 113–145, https://doi.org/10.1007/978-3-030-56558-9_5

  • Li X, Wang S, Zeng S, Wu Y, Yang Y (2024) A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth 1(1):9. https://doi.org/10.1007/s44336-024-00009-2

    Google Scholar 

  • Liikkanen LA, Perttula M (2009) Exploring problem decomposition in conceptual design among novice designers. Des Stud 30(1):38–59. https://doi.org/10.1016/j.destud.2008.07.003

    Google Scholar 

  • Liu J, Yao Y, An P, Wang Q (2024) PeerGPT: probing the roles of LLM-based peer agents as team moderators and participants in children’s collaborative learning. In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, 1–6. https://doi.org/10.1145/3613905.3651008

  • Lloyd P, Scott P (1994) Discovering the design problem. Des Stud 15(2):125–140. https://doi.org/10.1016/0142-694X(94)90020-5

    Google Scholar 

  • Lobo JRA, Szejka AL, Canciglieri Junior O (2025) Towards a cognitive new product development framework based on collaborative engineering and digital technologies. In: Šormaz DN, Bidanda B, Alhawari O, Geng Z (eds), Intelligent Production and Industry 5.0 with Human Touch, Resilience, and Circular Economy. Springer Nature Switzerland. pp. 77–86 https://doi.org/10.1007/978-3-031-77723-3_7

  • Lombard M, Snyder-Duch J, Bracken CC (2002) Content analysis in mass communication: assessment and reporting of intercoder reliability. Hum Commun Res 28(4):587–604. https://doi.org/10.1111/j.1468-2958.2002.tb00826.x

    Google Scholar 

  • London K, Singh V (2013) Integrated construction supply chain design and delivery solutions. Architectural Eng Des Manag 9(3):135–157. https://doi.org/10.1080/17452007.2012.684451

    Google Scholar 

  • Marzi G, Balzano M (2025) Artificial intelligence and the reconfiguration of NPD Teams: adaptability and skill differentiation in sustainable product innovation. Technovation 145: 103254. https://doi.org/10.1016/j.technovation.2025.103254

    Google Scholar 

  • Mathieu JE, Heffner TS, Goodwin GF, Salas E, Cannon-Bowers JA (2000) The influence of shared mental models on team process and performance. J Appl Psychol 85(2):273–283. https://doi.org/10.1037/0021-9010.85.2.273

    Google Scholar 

  • Murtaza M, Cheng C-T, Fard M, Zeleznikow J (2024) Transforming driver education: a comparative analysis of LLM-augmented training and conventional instruction for autonomous vehicle technologies. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-024-00407-z

  • Nagaraj V, Berente N, Lyytinen K, Gaskin J (2020) Team design thinking, product innovativeness, and the moderating role of problem unfamiliarity. J Prod Innov Manag 37(4):297–323. https://doi.org/10.1111/jpim.12528

    Google Scholar 

  • Nahar N, Zhou S, Lewis G, Kästner C (2022) Collaboration challenges in building ML-enabled systems: Communication, documentation, engineering, and process. In: Proceedings of the 44th International Conference on Software Engineering, 413–425. https://doi.org/10.1145/3510003.3510209

  • Nejjar M, Zacharias L, Stiehle F, Weber I (2023) LLMs for science: usage for code generation and data analysis. J Softw Evol Process e2723. https://doi.org/10.1002/smr.2723

  • Omidvar Tehrani BMI, Anubhai A (2024) Evaluating human-AI partnership for LLM-based code migration. In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, 1–8. https://doi.org/10.1145/3613905.3650896

  • Onnasch L, Wickens CD, Li H, Manzey D (2014) Human performance consequences of stages and levels of automation: an integrated meta-analysis. Hum Factors 56(3):476–488. https://doi.org/10.1177/0018720813501549

    Google Scholar 

  • Ostergaard KJ, Summers JD (2008) A taxonomy for collaborative design. 755–764. https://doi.org/10.1115/DETC2003/DAC-48781

  • Oygür I (2018) The machineries of user knowledge production. Des Stud 54:23–49. https://doi.org/10.1016/j.destud.2017.10.002

    Google Scholar 

  • Parasuraman R, Manzey DH (2010) Complacency and bias in human use of automation: an attentional integration. Hum Factors 52(3):381–410. https://doi.org/10.1177/0018720810376055

    Google Scholar 

  • Parasuraman R, Sheridan TB, Wickens CD (2000) A model for types and levels of human interaction with automation. IEEE Trans Syst Man Cybern Part A Syst Hum 30(3):286–297. https://doi.org/10.1109/3468.844354

    Google Scholar 

  • Patel D, Alismail A (2024) Relationship between cognitive load theory, intrinsic motivation and emotions in healthcare professions education: a perspective on the missing link. Adv Med Educ Pract 15:57–62. https://doi.org/10.2147/AMEP.S441405

    Google Scholar 

  • Pratt W, Reddy MC, McDonald DW, Tarczy-Hornoch P, Gennari JH (2004) Incorporating ideas from computer-supported cooperative work. J Biomed Inform 37(2):128–137. https://doi.org/10.1016/j.jbi.2004.04.001

    Google Scholar 

  • Qin J, van der Rhee B, Venkataraman V, Ahmadi T (2021) The impact of IT infrastructure capability on NPD performance: the roles of market knowledge and innovation process formality. J Bus Res 133:252–264. https://doi.org/10.1016/j.jbusres.2021.04.072

    Google Scholar 

  • Qiu Y, Jin Y (2025) A method for synthesizing ontology-based textual design datasets: evaluating the potential of large language model in domain-specific dataset generation. J Mech Des, 147(4). Scopus. https://doi.org/10.1115/1.4067478

  • Razmerita L, Kirchner K, Nabeth T (2014) Social media in organizations: leveraging personal and collective knowledge processes. J Organ Comput Electron Commer 24(1):74–93. https://doi.org/10.1080/10919392.2014.866504

    Google Scholar 

  • Riyadh HA, Khrais LT, Alfaiza SA, Sultan AA (2021) Association between mass collaboration and knowledge management: a case ofJordan companies. Int J Organ Anal 31(4):973–987. https://doi.org/10.1108/IJOA-08-2021-2893

    Google Scholar 

  • Salma Z, Hijón-Neira R, Pizarro C (2025) Designing co-creative systems: five paradoxes in human–AI collaboration. Information 16(10):909. https://doi.org/10.3390/info16100909

    Google Scholar 

  • Sarker IH (2021) Data science and analytics: an overview from data-driven smart computing, decision-making and applications perspective. SN Comput Sci 2(5):377. https://doi.org/10.1007/s42979-021-00765-8

    Google Scholar 

  • Scharowski N, Perrig SAC, Svab M, Opwis K, Brühlmann F (2023) Exploring the effects of human-centered AI explanations on trust and reliance. Front Comput Sci, 5. https://doi.org/10.3389/fcomp.2023.1151150

  • Shmueli G, Koppius OR (2011) Predictive analytics in information systems research. MIS Q 35(3):553–572. https://doi.org/10.2307/23042796

    Google Scholar 

  • Shteynberg G, Hirsh JB, Wolf W, Bargh JA, Boothby EJ, Colman AM, Echterhoff G, Rossignac-Milon M (2023) Theory of collective mind. Trends Cogn Sci 27(11):1019–1031. https://doi.org/10.1016/j.tics.2023.06.009

    Google Scholar 

  • Shu-Hsien Liao (2005) Expert system methodologies and applications—a decade review from 1995 to 2004. Expert Syst Appl 28(1):93–103. https://doi.org/10.1016/j.eswa.2004.08.003

    Google Scholar 

  • Stauffer LA, Ullman DG (1991) Fundamental processes of mechanical designers based on empirical data. J Eng Des 2(2):113–125. https://doi.org/10.1080/09544829108901675

    Google Scholar 

  • Stempfle J, Badke-Schaub P (2002) Thinking in design teams—an analysis of team communication. Des Stud 23(5):473–496. https://doi.org/10.1016/S0142-694X(02)00004-2

    Google Scholar 

  • Sternberg RJ (1998) Handbook of creativity. Cambridge University Press

  • Suh S, Chen M, Min B, Li TJ-J, Xia H (2024) Luminate: structured generation and exploration of design space with large language models for human-AI co-creation. In: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3613904.3642400

  • Tan J (2010) Grounded theory in practice: issues and discussion for new qualitative researchers. J Document 66(1):93–112. https://doi.org/10.1108/00220411011016380

    Google Scholar 

  • Trovato M, Belluomo L, Bici M, Prist M, Campana F, Cicconi P (2025) Machine learning in design for additive manufacturing: a state-of-the-art discussion for a support tool in product design lifecycle. Int J Adv Manuf Technol 137(5):2157–2180. https://doi.org/10.1007/s00170-025-15273-9

    Google Scholar 

  • Tseng S-M (2008) The effects of information technology on knowledge management systems. Expert Syst Appl 35(1):150–160. https://doi.org/10.1016/j.eswa.2007.06.011

    Google Scholar 

  • Ugbebor FO, Adeteye DA, Ugbebor JO (2024) Predictive analytics models for SMES to forecast market trends, customer behavior, and potential business risks. J Knowl Learn Sci Technol 3(3):355–381. https://doi.org/10.60087/jklst.v3.n3.p355-381

    Google Scholar 

  • Urquhart C, Lehmann H, Myers MD (2010) Putting the ‘theory’ back into grounded theory: guidelines for grounded theory studies in information systems. Inf Syst J 20(4):357–381. https://doi.org/10.1111/j.1365-2575.2009.00328.x

    Google Scholar 

  • Vlasceanu M, Dyckovsky AM, Coman A (2024) A network approach to investigate the dynamics of individual and collective beliefs: advances and applications of the BENDING model. Perspect Psychol Sci 19(2):444–453. https://doi.org/10.1177/17456916231185776

    Google Scholar 

  • Vu MD, Wang H, Chen J, Li Z, Zhao S, Xing Z, Chen C (2024) GPTVoiceTasker: advancing multi-step mobile task efficiency through dynamic interface exploration and learning. In: Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology. https://doi.org/10.1145/3654777.3676356

  • Wang J, Tigelaar DEH, Zhou T, Admiraal W (2023) The effects of mobile technology usage on cognitive, affective, and behavioural learning outcomes in primary and secondary education: a systematic review with meta-analysis. J Comput Assist Learn 39(2):301–328. https://doi.org/10.1111/jcal.12759

    Google Scholar 

  • Wei R, Li K, Lan J (2024) Improving collaborative learning performance based on LLM virtual assistant. In: 2024 13th International Conference on Educational and Information Technology (ICEIT), 1–6. https://doi.org/10.1109/ICEIT61397.2024.10540942

  • Wickens CD (2002) Multiple resources and performance prediction. Theor Issues Ergon Sci 3(2):159–177. https://doi.org/10.1080/14639220210123806

    Google Scholar 

  • Wohllebe A, Lagodka C (2024) Can ChatGPT replace human content writers in SEO copywriting? An empirical comparison for performance measurement of generative AI in search engine optimization in E-Commerce. In: Bolz T, Schuster G (eds) Generative Künstliche Intelligenz in Marketing und Sales: Innovative Unternehmenspraxis: Insights, Strategien und Impulse. Springer Fachmedien, pp. 303–313. https://doi.org/10.1007/978-3-658-45132-5_21

  • Woo BM, Tan E, Yuen FL, Hamlin JK (2023) Socially evaluative contexts facilitate mentalizing. Trends Cogn Sci 27(1):17–29. https://doi.org/10.1016/j.tics.2022.10.003

    Google Scholar 

  • Woolley AW (2025) Generative AI and collaboration: opportunities for cultivating collective intelligence. J Org Des. https://doi.org/10.1007/s41469-025-00199-z

  • Xu, X. (Tone), Konnova A, Gao B, Peng C, Vo D, Dow SP (2025) Productive vs. reflective: how different ways of integrating AI into design workflows affect cognition and motivation. In: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3706598.3713649

  • Yang Y, Chen Y, Feng X, Sun D, Pang S (2024) Investigating the mechanisms of analytics-supported reflective assessment for fostering collective knowledge. J Comput High Educ 36(1):242–273. https://doi.org/10.1007/s12528-024-09398-1

    Google Scholar 

  • Ye Y, You H, Du J (2023) Improved trust in human-robot collaboration with ChatGPT. IEEE Access 11:55748–55754. https://doi.org/10.1109/ACCESS.2023.3282111

    Google Scholar 

  • Zahra SA, Neubaum DO, Larrañeta B (2007) Knowledge sharing and technological capabilities: the moderating role of family involvement. J Bus Res 60(10):1070–1079. https://doi.org/10.1016/j.jbusres.2006.12.014

    Google Scholar 

  • Zamfirescu-Pereira JD, Jun E, Terry M, Yang Q, Hartmann B (2025) Beyond code generation: LLM-supported exploration of the program design space. In: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3706598.3714154

  • Zhang P, Soergel D (2014) Towards a comprehensive model of the cognitive process and mechanisms of individual sensemaking. J Assoc Inf Sci Technol 65(9):1733–1756. https://doi.org/10.1002/asi.23125

    Google Scholar 

  • Zhang Z, Peng W, Chen X, Cao L, Li TJ-J (2025) LADICA: a large shared display interface for generative AI cognitive assistance in co-located team collaboration. In: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3706598.3713289

  • Zhou J, Li R, Tang J, Tang T, Li H, Cui W, Wu Y (2024) Understanding nonlinear collaboration between human and AI agents: a co-design framework for creative design. In: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, 1–16. https://doi.org/10.1145/3613904.3642812

Download references

Author information

Authors and Affiliations

  1. Zhejiang University, Hangzhou, China

    Deyin Zhang, Shijian Luo, Yue Liu, Xiyuan Zhang, Yuqi Hu, Jianan Shen, Peiqi Yi & Kayu Zhao

  2. King’s College London, London, United Kingdom

    Deyin Zhang & Wei Liu

Authors
  1. Deyin Zhang
    View author publications

    Search author on:PubMed Google Scholar

  2. Shijian Luo
    View author publications

    Search author on:PubMed Google Scholar

  3. Yue Liu
    View author publications

    Search author on:PubMed Google Scholar

  4. Xiyuan Zhang
    View author publications

    Search author on:PubMed Google Scholar

  5. Yuqi Hu
    View author publications

    Search author on:PubMed Google Scholar

  6. Jianan Shen
    View author publications

    Search author on:PubMed Google Scholar

  7. Peiqi Yi
    View author publications

    Search author on:PubMed Google Scholar

  8. Kayu Zhao
    View author publications

    Search author on:PubMed Google Scholar

  9. Wei Liu
    View author publications

    Search author on:PubMed Google Scholar

Contributions

DY organized the experiments, constructed the analytical model, wrote the data analysis and the final manuscript, and was responsible for the overall design and methodology. Y and KY annotated the data and prepared figures, PQ and XY prepared the experiments and recruited the participants, JN and YQ translated and revised the paper in English, and SJ and W supervised the entire research project and were responsible for the manuscript.

Corresponding authors

Correspondence to Shijian Luo or Wei Liu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethical approval

This study involved human participants through interviews and quasi-experimental collaborative design tasks. No biomedical, clinical, or invasive procedures were conducted. All data were collected anonymously and handled confidentially for research purposes only. The study was conducted in accordance with the Declaration of Helsinki and institutional guidelines for research involving human participants. Ethical approval was granted by the Zhejiang University Ethics Committee (Approval Date: 30 April 2024; the committee does not issue approval numbers).

Informed consent

All participants provided written informed consent prior to taking part in the study, between 14 May and 30 July 2024. They were informed of the study purpose, procedures, potential risks, and their right to withdraw at any time without penalty. No personally identifiable or sensitive information was collected, and all audio recordings and transcripts were anonymised during analysis. All procedures adhered to institutional ethical standards for research involving human participants.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, D., Luo, S., Liu, Y. et al. Large language model tools as catalysts for collective cognition in collaborative new-product development: a quasi-experimental study. Humanit Soc Sci Commun (2026). https://doi.org/10.1057/s41599-026-06738-7

Download citation

  • Received: 16 January 2025

  • Accepted: 10 February 2026

  • Published: 23 February 2026

  • DOI: https://doi.org/10.1057/s41599-026-06738-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Download PDF

Associated content

Collection

Technology and learning

Advertisement

Explore content

  • Research articles
  • Reviews & Analysis
  • News & Comment
  • Collections
  • Follow us on X
  • Sign up for alerts
  • RSS feed

About the journal

  • Journal Information
  • Referee instructions
  • Editor instructions
  • Journal policies
  • Open Access Fees and Funding
  • Calls for Papers
  • Events
  • Contact

Publish with us

  • For authors
  • Language editing services
  • Open access funding
  • Submit manuscript

Search

Advanced search

Quick links

  • Explore articles by subject
  • Find a job
  • Guide to authors
  • Editorial policies

Humanities and Social Sciences Communications (Humanit Soc Sci Commun)

ISSN 2662-9992 (online)

nature.com sitemap

About Nature Portfolio

  • About us
  • Press releases
  • Press office
  • Contact us

Discover content

  • Journals A-Z
  • Articles by subject
  • protocols.io
  • Nature Index

Publishing policies

  • Nature portfolio policies
  • Open access

Author & Researcher services

  • Reprints & permissions
  • Research data
  • Language editing
  • Scientific editing
  • Nature Masterclasses
  • Research Solutions

Libraries & institutions

  • Librarian service & tools
  • Librarian portal
  • Open research
  • Recommend to library

Advertising & partnerships

  • Advertising
  • Partnerships & Services
  • Media kits
  • Branded content

Professional development

  • Nature Awards
  • Nature Careers
  • Nature Conferences

Regional websites

  • Nature Africa
  • Nature China
  • Nature India
  • Nature Japan
  • Nature Middle East
  • Privacy Policy
  • Use of cookies
  • Legal notice
  • Accessibility statement
  • Terms & Conditions
  • Your US state privacy rights
Springer Nature

© 2026 Springer Nature Limited