Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions (2404.03429v1)

Published 4 Apr 2024 in cs.CL

Abstract: Intelligent tutoring systems (ITSs) that imitate human tutors and aim to provide immediate and customized instructions or feedback to learners have shown their effectiveness in education. With the emergence of generative artificial intelligence, LLMs further entitle the systems to complex and coherent conversational interactions. These systems would be of great help in language education as it involves developing skills in communication, which, however, drew relatively less attention. Additionally, due to the complicated cognitive development at younger ages, more endeavors are needed for practical uses. Scaffolding refers to a teaching technique where teachers provide support and guidance to students for learning and developing new concepts or skills. It is an effective way to support diverse learning needs, goals, processes, and outcomes. In this work, we investigate how pedagogical instructions facilitate the scaffolding in ITSs, by conducting a case study on guiding children to describe images for language learning. We construct different types of scaffolding tutoring systems grounded in four fundamental learning theories: knowledge construction, inquiry-based learning, dialogic teaching, and zone of proximal development. For qualitative and quantitative analyses, we build and refine a seven-dimension rubric to evaluate the scaffolding process. In our experiment on GPT-4V, we observe that LLMs demonstrate strong potential to follow pedagogical instructions and achieve self-paced learning in different student groups. Moreover, we extend our evaluation framework from a manual to an automated approach, paving the way to benchmark various conversational tutoring systems.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. E. Mousavinasab, N. Zarifsanaiey, S. R. Niakan Kalhori, M. Rakhshan, L. Keikha, and M. Ghazi Saeedi, “Intelligent tutoring systems: a systematic review of characteristics, applications, and evaluation methods,” Interact. Learn. Environ., vol. 29, no. 1, pp. 142–163, Jan. 2021, doi: 10.1080/10494820.2018.1558257.
  2. A. Keleş, R. Ocak, A. Keleş, and A. Gülcü, “ZOSMAT: Web-based intelligent tutoring system for teaching–learning process,” Expert Syst. Appl., vol. 36, no. 2, pp. 1229–1239, Mar. 2009, doi: 10.1016/j.eswa.2007.11.064.
  3. J. A. Kulik and J. D. Fletcher, “Effectiveness of Intelligent Tutoring Systems,” Rev. Educ. Res., vol. 86, no. 1, pp. 42–78, Mar. 2016, doi: 10.3102/0034654315581420.
  4. J. Wei, Y. Tay, R. Bommasani, C. Raffel, B. Zoph, S. Borgeaud, D. Yogatama, M. Bosma, D. Zhou, D. Metzler, and E. H. Chi, “Emergent Abilities of Large Language Models,” Transactions on Machine Learning Research, 2022.
  5. L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, and J. Schulman, “Training language models to follow instructions with human feedback,” Adv. Neural Inf. Process. Syst., vol. 35, pp. 27730–27744, 2022.
  6. Y. Chen, N. Ding, H.-T. Zheng, Z. Liu, M. Sun, and B. Zhou, “Empowering Private Tutoring by Chaining Large Language Models,” 2023, [Online]. Available: http://arxiv.org/abs/2309.08112.
  7. B. D. Nye, D. Mee, and M. G. Core, “Generative Large Language Models for Dialog-Based Tutoring: An Early Consideration of Opportunities and Concerns,” CEUR Workshop Proc., vol. 3487, pp. 78–88, 2023.
  8. E. Kasneci, K. Seßler, S. Küchemann, M. Bannert, D. Dementieva, F. Fischer, U. Gasser, G. Groh, S. Günnemann, E. Hüllermeier, and S. Krusche, “ChatGPT for good? On opportunities and challenges of large language models for education,” Learn. Individ. Differ., vol. 103, p. 102274, 2023.
  9. J. X. Weng, A. Y. Huang, O. H. Lu, I. Y. Chen, and S. J. Yang, “The implementation of precision education for learning analytics,” in 2020 IEEE Int. Conf. on Teaching, Assessment, and Learning for Engineering (TALE), Dec. 2020, pp. 327–332.
  10. F. Ouyang, M. Wu, L. Zheng, L. Zhang, and P. Jiao, “Integration of artificial intelligence performance prediction and learning analytics to improve student learning in online engineering course,” Int. J. Educ. Technol. High. Educ., vol. 20, no. 1, pp. 1–23, 2023.
  11. D. Leony, P. J. Muñoz-Merino, A. Pardo, and C. D. Kloos, “Provision of awareness of learners’ emotions through visualizations in a computer interaction-based environment,” Expert Syst. Appl., vol. 40, no. 13, pp. 5093–5100, 2013.
  12. J. Macina, N. Daheim, L. Wang, T. Sinha, M. Kapur, I. Gurevych, and M. Sachan, “Opportunities and Challenges in Neural Dialog Tutoring,” in Proc. of the 17th Conf. of the Eur. Chapter of the Assoc. for Comput. Linguistics, May 2023, pp. 2349–2364.
  13. S. Ruan, L. Jiang, J. Xu, B. J. K. Tham, Z. Qiu, Y. Zhu, E. L. Murnane, E. Brunskill, and J. A. Landay, “Quizbot: A dialogue-based adaptive learning system for factual knowledge,” in Proc. of the 2019 CHI Conf. on Human Factors in Computing Systems, May 2019, pp. 1–13.
  14. S. Wollny, J. Schneider, D. Di Mitri, J. Weidlich, M. Rittberger, and H. Drachsler, “Are we there yet?-a systematic literature review on chatbots in education,” Front. Artif. Intell., vol. 4, p. 654924, 2021.
  15. K. Stasaski, K. Kao, and M. A. Hearst, “CIMA: A large open access dialogue dataset for tutoring,” in Proc. of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, July 2020, pp. 52–64.
  16. A. Suresh, J. Jacobs, C. Harty, M. Perkoff, J. H. Martin, and T. Sumner, “The talkmoves dataset: K-12 mathematics lesson transcripts annotated for teacher and student discursive moves,” arXiv preprint arXiv:2204.09652, 2022.
  17. L. Wang, M. Sachan, X. Zeng, and K. F. Wong, “Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation,” arXiv preprint arXiv:2302.13496, 2023.
  18. Y. Chen, N. Ding, H. T. Zheng, Z. Liu, M. Sun, and B. Zhou, “Empowering Private Tutoring by Chaining Large Language Models,” arXiv preprint arXiv:2309.08112, 2023.
  19. Y. Dan, Z. Lei, Y. Gu, Y. Li, J. Yin, J. Lin, L. Ye, Z. Tie, Y. Zhou, Y. Wang, and A. Zhou, “Educhat: A large-scale language model-based chatbot system for intelligent education,” arXiv preprint arXiv:2308.02773, 2023.
  20. A. Walqui, “Scaffolding instruction for english language learners: A conceptual framework,” Int. J. Biling. Educ. Biling., vol. 9, no. 2, pp. 159–180, 2006, doi: 10.1080/13670050608668639.
  21. H. Kayi-Aydar, “Scaffolding language learning in an academic ESL classroom,” ELT J., vol. 67, no. 3, pp. 324–335, Jul. 2013, doi: 10.1093/elt/cct016.
  22. L. C. de Oliveira, L. Jones, and S. L. Smith, “Interactional scaffolding in a first-grade classroom through the teaching–learning cycle,” Int. J. Biling. Educ. Biling., vol. 26, no. 3, pp. 270–288, Mar. 2023, doi: 10.1080/13670050.2020.1798867.
  23. M. Y. Damanhouri, “The Effectiveness of Scaffolding as a Teaching Strategy in Enhancing English Language Learners’ Motivation in Writing: A Case Study,” J. Arts Humanit., vol. 10, no. 03, pp. 49–58, 2021, doi: 10.18533/jah.v10i03.2056.
  24. T. Gonulal and S. Loewen, “Scaffolding Technique,” in The TESOL Encyclopedia of English Language Teaching, Wiley, 2018, pp. 1–5.
  25. S. Puntambekar, “Distributed Scaffolding: Scaffolding Students in Classroom Environments,” Educ. Psychol. Rev., vol. 34, no. 1, pp. 451–472, 2022, doi: 10.1007/s10648-021-09636-3.
  26. S. Puntambekar and R. Hubscher, “Tools for Scaffolding Students in a Complex Learning Environment: What Have We Gained and What Have We Missed?,” Educ. Psychol., vol. 40, no. 1, pp. 1–12, Mar. 2005, doi: 10.1207/s15326985ep4001-1.
  27. S. P. Lajoie, “Extending the Scaffolding Metaphor,” Instr. Sci., vol. 33, no. 5, pp. 541–557, 2005, doi: 10.1007/s11251-005-1279-2.
  28. Y. Yamada, Y. Bao, A. K. Lampinen, J. Kasai, and I. Yildirim, “Evaluating Spatial Understanding of Large Language Models,” arXiv preprint arXiv:2310.14540, 2023.
  29. J. H. Wong, H. Zhang, and N. F. Chen, “Variations of multi-task learning for spoken language assessment,” in Proc. Interspeech, 2022, pp. 4456–4460.
  30. Z. Yang, L. Li, K. Lin, J. Wang, C. C. Lin, Z. Liu, and L. Wang, “The dawn of lmms: Preliminary explorations with gpt-4v (ision),” arXiv preprint arXiv:2309.17421, vol. 9, no. 1, 2023.
  31. L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, and J. Schulman, “Training language models to follow instructions with human feedback,” Adv. Neural Inf. Process. Syst., vol. 35, pp. 27730–27744, Dec. 2022.
  32. T. Khot, H. Trivedi, M. Finlayson, Y. Fu, K. Richardson, P. Clark, and A. Sabharwal, “Decomposed Prompting: A Modular Approach for Solving Complex Tasks,” arXiv preprint arXiv:2210.02406, 2022.
  33. A. S. Palincsar, “Social constructivist perspectives on teaching and learning,” Annu. Rev. Psychol., vol. 49, pp. 345–375, 1998, doi: 10.1146/annurev.psych.49.1.345.
  34. C. K. K. Chan, P. J. Burtis, M. Scardamalia, and C. Bereiter, “Constructive Activity in Learning From Text,” Am. Educ. Res. J., vol. 29, no. 1, pp. 97–118, Mar. 1992, doi: 10.3102/00028312029001097.
  35. J. van Aalst, “Distinguishing knowledge-sharing, knowledge-construction, and knowledge-creation discourses,” Int. J. Comput. Collab. Learn., vol. 4, no. 3, pp. 259–287, Sep. 2009, doi: 10.1007/s11412-009-9069-5.
  36. K. L. McNeill, D. J. Lizotte, J. Krajcik, and R. W. Marx, “Supporting Students’ Construction of Scientific Explanations by Fading Scaffolds in Instructional Materials,” J. Learn. Sci., vol. 15, no. 2, pp. 153–191, Dec. 2006.
  37. B. J. Reiser, “Scaffolding Complex Learning: The Mechanisms of Structuring and Problematizing Student Work,” J. Learn. Sci., vol. 13, no. 3, pp. 273–304, Jul. 2004, doi: 10.1207/s15327809jls1303-2.
  38. Y. S. Hsu, T. L. Lai, and W. H. Hsu, “A Design Model of Distributed Scaffolding for Inquiry-Based Learning,” Res. Sci. Educ., vol. 45, no. 2, pp. 241–273, 2015, doi: 10.1007/s11165-014-9421-2.
  39. N. Mercer and C. Howe, “Explaining the dialogic processes of teaching and learning: The value and potential of sociocultural theory,” Learn. Cult. Soc. Interact., vol. 1, no. 1, pp. 12–21, Mar. 2012, doi: 10.1016/j.lcsi.2012.03.001.
  40. G. Wells and R. M. Arauz, “Dialogue in the Classroom,” J. Learn. Sci., vol. 15, no. 3, pp. 379–428, Jul. 2006, doi: 10.1207/s15327809jls1503-3.
  41. R. Alexander, “Developing dialogic teaching: Genesis, process, trial,” Res. Pap. Educ., vol. 33, no. 5, pp. 561–598, 2018.
  42. S. Haruehansawasin and P. Kiattikomol, “Scaffolding in problem-based learning for low-achieving learners,” J. Educ. Res., vol. 111, no. 3, pp. 363–370, May 2018, doi: 10.1080/00220671.2017.1287045.
  43. A. Soller, B. Goodman, F. Linton, and R. Gaimari, “Promoting Effective Peer Interaction in an Intelligent Collaborative Learning System,” in Intelligent Tutoring Systems, B. P. Goettl, H. M. Halff, C. L. Redfield, and V. J. Shute, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 1998, pp. 186–195.
  44. J. Sweller, “Cognitive Load Theory,” in The psychology of learning and motivation: Cognition in education, Vol. 55, San Diego, CA, US: Elsevier Academic Press, 2011, pp. 37–76.
  45. F. Reinhold, S. Hoch, B. Werner, J. Richter-Gebert, and K. Reiss, “Learning fractions with and without educational technology: What matters for high-achieving and low-achieving students?,” Learn. Instr., vol. 65, p. 101264, Feb. 2020, doi: 10.1016/j.learninstruc.2019.101264.
  46. M. C. Duffy and R. Azevedo, “Motivation matters: Interactions between achievement goals and agent scaffolding for self-regulated learning within an intelligent tutoring system,” Comput. Hum. Behav., vol. 52, pp. 338–348, 2015.
  47. S. Khaliliaqdam, “ZPD, Scaffolding and Basic Speech Development in EFL Context,” Procedia - Soc. Behav. Sci., vol. 98, pp. 891–897, May 2014, doi: 10.1016/j.sbspro.2014.03.497.
  48. H. C. Dulay and M. K. Burt, “SHOULD WE TEACH CHILDREN SYNTAX?,” Lang. Learn., vol. 23, no. 2, pp. 245–258, Dec. 1973, doi: 10.1111/j.1467-1770.1973.tb00659.x.
  49. M. Li, T. Shi, C. Ziems, M. Y. Kan, N. Chen, Z. Liu, and D. Yang, “CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation,” in Proc. of the 2023 Conf. on Empirical Methods in Natural Language Processing, Dec. 2023, pp. 1487–1505.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Zhengyuan Liu (41 papers)
  2. Stella Xin Yin (4 papers)
  3. Carolyn Lee (1 paper)
  4. Nancy F. Chen (97 papers)
Citations (6)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets