Assertion Enhanced Few-Shot Learning: Instructive Technique for Large Language Models to Generate Educational Explanations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917571508305920 |
|---|---|
| author | Shahriar, Tasmia Ramos, Kelly Matsuda, Noboru |
| author_facet | Shahriar, Tasmia Ramos, Kelly Matsuda, Noboru |
| contents | Human educators possess an intrinsic ability to anticipate and seek educational explanations from students, which drives them to pose thought-provoking questions when students cannot articulate these explanations independently. We aim to imbue Intelligent Tutoring Systems with this ability using few-shot learning capability of Large Language Models. Our work proposes a novel prompting technique, Assertion Enhanced Few-Shot Learning, to facilitate the generation of accurate, detailed oriented educational explanations. Our central hypothesis is that, in educational domain, few-shot demonstrations are necessary but not a sufficient condition for quality explanation generation. We conducted a study involving 12 in-service teachers, comparing our approach to Traditional Few-Shot Learning. The results show that Assertion Enhanced Few-Shot Learning improves explanation accuracy by 15% and yields higher-quality explanations, as evaluated by teachers. We also conduct a qualitative ablation study to factor the impact of assertions to provide educator-friendly prompting guidelines for generating explanations in their domain of interest. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_03122 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Assertion Enhanced Few-Shot Learning: Instructive Technique for Large Language Models to Generate Educational Explanations Shahriar, Tasmia Ramos, Kelly Matsuda, Noboru Computation and Language Human educators possess an intrinsic ability to anticipate and seek educational explanations from students, which drives them to pose thought-provoking questions when students cannot articulate these explanations independently. We aim to imbue Intelligent Tutoring Systems with this ability using few-shot learning capability of Large Language Models. Our work proposes a novel prompting technique, Assertion Enhanced Few-Shot Learning, to facilitate the generation of accurate, detailed oriented educational explanations. Our central hypothesis is that, in educational domain, few-shot demonstrations are necessary but not a sufficient condition for quality explanation generation. We conducted a study involving 12 in-service teachers, comparing our approach to Traditional Few-Shot Learning. The results show that Assertion Enhanced Few-Shot Learning improves explanation accuracy by 15% and yields higher-quality explanations, as evaluated by teachers. We also conduct a qualitative ablation study to factor the impact of assertions to provide educator-friendly prompting guidelines for generating explanations in their domain of interest. |
| title | Assertion Enhanced Few-Shot Learning: Instructive Technique for Large Language Models to Generate Educational Explanations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2312.03122 |