Steps are all you need: Rethinking STEM Education with Prompt Engineering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908402812190720 |
|---|---|
| author | Addala, Krishnasai Baghel, Kabir Dev Paul Gupta, Navya Vyalla, Rishitej Reddy Kirtani, Chhavi Anand, Avinash Shah, Rajiv Ratn |
| author_facet | Addala, Krishnasai Baghel, Kabir Dev Paul Gupta, Navya Vyalla, Rishitej Reddy Kirtani, Chhavi Anand, Avinash Shah, Rajiv Ratn |
| contents | Few shot and Chain-of-Thought prompting have shown promise when applied to Physics Question Answering Tasks, but are limited by the lack of mathematical ability inherent to LLMs, and are prone to hallucination. By utilizing a Mixture of Experts (MoE) Model, along with analogical prompting, we are able to show improved model performance when compared to the baseline on standard LLMs. We also survey the limits of these prompting techniques and the effects they have on model performance. Additionally, we propose Analogical CoT prompting, a prompting technique designed to allow smaller, open source models to leverage Analogical prompting, something they have struggled with, possibly due to a lack of specialist training data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05023 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Steps are all you need: Rethinking STEM Education with Prompt Engineering Addala, Krishnasai Baghel, Kabir Dev Paul Gupta, Navya Vyalla, Rishitej Reddy Kirtani, Chhavi Anand, Avinash Shah, Rajiv Ratn Computation and Language Few shot and Chain-of-Thought prompting have shown promise when applied to Physics Question Answering Tasks, but are limited by the lack of mathematical ability inherent to LLMs, and are prone to hallucination. By utilizing a Mixture of Experts (MoE) Model, along with analogical prompting, we are able to show improved model performance when compared to the baseline on standard LLMs. We also survey the limits of these prompting techniques and the effects they have on model performance. Additionally, we propose Analogical CoT prompting, a prompting technique designed to allow smaller, open source models to leverage Analogical prompting, something they have struggled with, possibly due to a lack of specialist training data. |
| title | Steps are all you need: Rethinking STEM Education with Prompt Engineering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.05023 |