Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.05794 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912811612897280 |
|---|---|
| author | Cohen, Eilam Bul, Itamar Inbar, Danielle Loewenbach, Omri |
| author_facet | Cohen, Eilam Bul, Itamar Inbar, Danielle Loewenbach, Omri |
| contents | Large language models (LLMs) enable strong text generation, and in general there is a practical tradeoff between fine-tuning and prompt engineering. We introduce Simplify-This, a comparative study evaluating both paradigms for text simplification with encoder-decoder LLMs across multiple benchmarks, using a range of evaluation metrics. Fine-tuned models consistently deliver stronger structural simplification, whereas prompting often attains higher semantic similarity scores yet tends to copy inputs. A human evaluation favors fine-tuned outputs overall. We release code, a cleaned derivative dataset used in our study, checkpoints of fine-tuned models, and prompt templates to facilitate reproducibility and future work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05794 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Simplify-This: A Comparative Analysis of Prompt-Based and Fine-Tuned LLMs Cohen, Eilam Bul, Itamar Inbar, Danielle Loewenbach, Omri Computation and Language Machine Learning Large language models (LLMs) enable strong text generation, and in general there is a practical tradeoff between fine-tuning and prompt engineering. We introduce Simplify-This, a comparative study evaluating both paradigms for text simplification with encoder-decoder LLMs across multiple benchmarks, using a range of evaluation metrics. Fine-tuned models consistently deliver stronger structural simplification, whereas prompting often attains higher semantic similarity scores yet tends to copy inputs. A human evaluation favors fine-tuned outputs overall. We release code, a cleaned derivative dataset used in our study, checkpoints of fine-tuned models, and prompt templates to facilitate reproducibility and future work. |
| title | Simplify-This: A Comparative Analysis of Prompt-Based and Fine-Tuned LLMs |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2601.05794 |