Evaluating Large Language Models for automatic analysis of teacher simulations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929441467269120 |
|---|---|
| author | de-Fitero-Dominguez, David Albaladejo-González, Mariano Garcia-Cabot, Antonio Garcia-Lopez, Eva Moreno-Cediel, Antonio Barno, Erin Reich, Justin |
| author_facet | de-Fitero-Dominguez, David Albaladejo-González, Mariano Garcia-Cabot, Antonio Garcia-Lopez, Eva Moreno-Cediel, Antonio Barno, Erin Reich, Justin |
| contents | Digital Simulations (DS) provide safe environments where users interact with an agent through conversational prompts, providing engaging learning experiences that can be used to train teacher candidates in realistic classroom scenarios. These simulations usually include open-ended questions, allowing teacher candidates to express their thoughts but complicating an automatic response analysis. To address this issue, we have evaluated Large Language Models (LLMs) to identify characteristics (user behaviors) in the responses of DS for teacher education. We evaluated the performance of DeBERTaV3 and Llama 3, combined with zero-shot, few-shot, and fine-tuning. Our experiments discovered a significant variation in the LLMs' performance depending on the characteristic to identify. Additionally, we noted that DeBERTaV3 significantly reduced its performance when it had to identify new characteristics. In contrast, Llama 3 performed better than DeBERTaV3 in detecting new characteristics and showing more stable performance. Therefore, in DS where teacher educators need to introduce new characteristics because they change depending on the simulation or the educational objectives, it is more recommended to use Llama 3. These results can guide other researchers in introducing LLMs to provide the highly demanded automatic evaluations in DS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20360 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Large Language Models for automatic analysis of teacher simulations de-Fitero-Dominguez, David Albaladejo-González, Mariano Garcia-Cabot, Antonio Garcia-Lopez, Eva Moreno-Cediel, Antonio Barno, Erin Reich, Justin Artificial Intelligence Digital Simulations (DS) provide safe environments where users interact with an agent through conversational prompts, providing engaging learning experiences that can be used to train teacher candidates in realistic classroom scenarios. These simulations usually include open-ended questions, allowing teacher candidates to express their thoughts but complicating an automatic response analysis. To address this issue, we have evaluated Large Language Models (LLMs) to identify characteristics (user behaviors) in the responses of DS for teacher education. We evaluated the performance of DeBERTaV3 and Llama 3, combined with zero-shot, few-shot, and fine-tuning. Our experiments discovered a significant variation in the LLMs' performance depending on the characteristic to identify. Additionally, we noted that DeBERTaV3 significantly reduced its performance when it had to identify new characteristics. In contrast, Llama 3 performed better than DeBERTaV3 in detecting new characteristics and showing more stable performance. Therefore, in DS where teacher educators need to introduce new characteristics because they change depending on the simulation or the educational objectives, it is more recommended to use Llama 3. These results can guide other researchers in introducing LLMs to provide the highly demanded automatic evaluations in DS. |
| title | Evaluating Large Language Models for automatic analysis of teacher simulations |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2407.20360 |