Affordably Fine-tuned LLMs Provide Better Answers to Course-specific MCQs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916644049125376 |
|---|---|
| author | Raimondi, Bianca Giallorenzo, Saverio Gabbrielli, Maurizio |
| author_facet | Raimondi, Bianca Giallorenzo, Saverio Gabbrielli, Maurizio |
| contents | In education, the capability of generating human-like text of Large Language Models (LLMs) inspired work on how they can increase the efficiency of learning and teaching. We study the affordability of these models for educators and students by investigating how LLMs answer multiple-choice questions (MCQs) with respect to hardware constraints and refinement techniques. We explore this space by using generic pre-trained LLMs (the 7B, 13B, and 70B variants of LLaMA-2) to answer 162 undergraduate-level MCQs from a course on Programming Languages (PL) -- the MCQ dataset is a contribution of this work, which we make publicly available. Specifically, we dissect how different factors, such as using readily-available material -- (parts of) the course's textbook -- for fine-tuning and quantisation (to decrease resource usage) can change the accuracy of the responses. The main takeaway is that smaller textbook-based fine-tuned models outperform generic larger ones (whose pre-training requires conspicuous resources), making the usage of LLMs for answering MCQs resource- and material-wise affordable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05891 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Affordably Fine-tuned LLMs Provide Better Answers to Course-specific MCQs Raimondi, Bianca Giallorenzo, Saverio Gabbrielli, Maurizio Computation and Language Artificial Intelligence In education, the capability of generating human-like text of Large Language Models (LLMs) inspired work on how they can increase the efficiency of learning and teaching. We study the affordability of these models for educators and students by investigating how LLMs answer multiple-choice questions (MCQs) with respect to hardware constraints and refinement techniques. We explore this space by using generic pre-trained LLMs (the 7B, 13B, and 70B variants of LLaMA-2) to answer 162 undergraduate-level MCQs from a course on Programming Languages (PL) -- the MCQ dataset is a contribution of this work, which we make publicly available. Specifically, we dissect how different factors, such as using readily-available material -- (parts of) the course's textbook -- for fine-tuning and quantisation (to decrease resource usage) can change the accuracy of the responses. The main takeaway is that smaller textbook-based fine-tuned models outperform generic larger ones (whose pre-training requires conspicuous resources), making the usage of LLMs for answering MCQs resource- and material-wise affordable. |
| title | Affordably Fine-tuned LLMs Provide Better Answers to Course-specific MCQs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2501.05891 |