I attended the NeurIPS’23 Workshop on Generative AI for Education (GAIED) in New Orleans. The organizers put together a nice summary of the research presented at the workshop; a lot of the work focused on using in-context learning with OpenAI models. (My paper followed that trend.)

During the workshop, a number of interesting sources came up during presentations or in conversations. This is my list of those sources (alphabetical):

[1] Shobhit Chaurasia and Raymond J. Mooney. 2017. Dialog for Language to Code. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), November 2017. Asian Federation of Natural Language Processing, Taipei, Taiwan, 175–180. Retrieved December 16, 2023 from https://aclanthology.org/I17-2030
[2] Alon Halevy, Peter Norvig, and Fernando Pereira. 2009. The Unreasonable Effectiveness of Data. IEEE Intell. Syst. 24, 2 (March 2009), 8–12. https://doi.org/10.1109/MIS.2009.36
[3] Yunsung Kim and Chris Piech. 2023. The Student Zipf Theory: Inferring Latent Structures in Open-Ended Student Work To Help Educators. In LAK23: 13th International Learning Analytics and Knowledge Conference, March 13, 2023, Arlington TX USA. ACM,464–475. https://doi.org/10.1145/3576050.3576116
[4] Jingyi Li, Eric Rawn, Jacob Ritchie, Jasper Tran O’Leary, and Sean Follmer. 2023. Beyond the Artifact: Power as a Lens for Creativity Support Tools. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST ‘23), October 29, 2023, New York, NY, USA. ACM, 1–15. https://doi.org/10.1145/3586183.3606831
[5] Xinyi Lu, Simin Fan, Jessica Houghton, Lu Wang, and Xu Wang. 2023. ReadingQuizMaker: A Human-NLP Collaborative System that Supports Instructors to Design High-Quality Reading Quiz Questions. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, April 19, 2023, Hamburg Germany. ACM, 1–18. https://doi.org/10.1145/3544548.3580957
[6] Gloria Mark. 2023. Attention Span: A Groundbreaking Way to Restore Balance, Happiness and Productivity. Hanover Square Press.
[7] Allen Nie, Emma Brunskill, and Chris Piech. 2021. Play to Grade: Testing Coding Games as Classifying Markov Decision Process. https://doi.org/10.48550/arXiv.2110.14615
[8] Robin Schmucker, Meng Xia, Amos Azaria, and Tom Mitchell. 2023. Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems. https://doi.org/10.48550/arXiv.2310.01420
[9] Sherpa Labs. Sherpa. Retrieved December 16, 2023 from https://sherpalabs.co/
[10] Lisa Wang, Angela Sy, Larry Liu, and Chris Piech. 2017. Deep Knowledge Tracing On Programming Exercises. In Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale (L@S ‘17), April 12, 2017, New York, NY, USA. ACM, 201–204. https://doi.org/10.1145/3051457.3053985
[11] Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, and Lu Wang. 2023. Merging Generated and Retrieved Knowledge for Open-Domain QA. https://doi.org/10.48550/arXiv.2310.14393

During her talk and in the panel discussion, Elena Glassman highlighted two theories of learning that she thinks should be better known:

  • Variation Theory
  • Analogical Learning Theory

Here are a few links I dredged up from Google on those two theories (so not necessarily recommended):

Elena Glassman’s talk also introduced me to the idea of alignable differences:

  • Elena L. Glassman, Tianyi Zhang, Björn Hartmann, and Miryung Kim. 2018. Visualizing API Usage Examples at Scale. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18), April 21, 2018, New York, NY, USA. ACM, 1–12. https://doi.org/10.1145/3173574.3174154
  • Litao Yan, Miryung Kim, Bjoern Hartmann, Tianyi Zhang, and Elena L. Glassman. 2022. Concept-Annotated Examples for Library Comparison. In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, October 29, 2022, Bend OR USA. ACM, 1–16. https://doi.org/10.1145/3526113.3545647

The paper I presented at the workshop:

Zachary Levonian, Chenglu Li, Wangda Zhu, Anoushka Gade, Owen Henkel, Millie-Ellen Postle, and Wanli Xing. 2023. Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference. In NeurIPS’23 Workshop on Generative AI for Education (GAIED), New Orleans, USA. DOI:https://doi.org/10.48550/arXiv.2310.03184