Short-form Text Rewriting with Phi Silica
For practitioners needing on-device or low-latency text rewriting, this work shows that targeted adaptation of small language models can substantially narrow the performance gap with large cloud models.
This paper adapts a small language model (Phi Silica) for short-form text rewriting through dataset curation, prompt distillation, and parameter-efficient fine-tuning, achieving improved semantic fidelity, reduced hallucinations, and higher preference win rate against GPT-5-chat rewrites.
Short-form text rewriting is a constrained variant of paraphrasing in which limited context and high semantic density leave little room for variation. While large language models perform well on general paraphrasing, small language models (SLMs) often struggle with semantic fidelity and hallucination robustness in short-form settings. In this work, we present an empirical study of adapting an SLM, Phi Silica, for short-form rewrite through dataset curation, prompt distillation, parameter-efficient fine-tuning, and evaluation. We curate a dataset of short presentation-style text from public slide decks and use GPT-5-chat both to generate rewrite supervision and to conduct LLM-as-a-judge evaluation. Our results show that finetuning improves semantic fidelity, reduces hallucinations, and increases preference win rate against GPT-5-chat rewrites. The findings suggest that targeted adaptation for SLMs can substantially narrow the gap to cloud models and provide practical guidance for adapting SLMs to precision-critical rewrite tasks.