Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.18294 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909703542407168 |
|---|---|
| author | Ramu, Pritika Saxena, Apoorv Y, Meghanath M Sankar, Varsha Basu, Debraj |
| author_facet | Ramu, Pritika Saxena, Apoorv Y, Meghanath M Sankar, Varsha Basu, Debraj |
| contents | Adapting LLMs to specific stylistic characteristics, like brand voice or authorial tones, is crucial for enterprise communication but challenging to achieve from corpora which lacks instruction-response formatting without compromising instruction adherence. We introduce StyleAdaptedLM, a framework that efficiently transfers stylistic traits to instruction-following models using Low-Rank Adaptation (LoRA). LoRA adapters are first trained on a base model with diverse unstructured stylistic corpora, then merged with a separate instruction-following model. This enables robust stylistic customization without paired data or sacrificing task performance. Experiments across multiple datasets and models demonstrate improved stylistic consistency while preserving instruction adherence, with human evaluations confirming brand-specific convention uptake. StyleAdaptedLM offers an efficient path for stylistic personalization in LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18294 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StyleAdaptedLM: Enhancing Instruction Following Models with Efficient Stylistic Transfer Ramu, Pritika Saxena, Apoorv Y, Meghanath M Sankar, Varsha Basu, Debraj Computation and Language Adapting LLMs to specific stylistic characteristics, like brand voice or authorial tones, is crucial for enterprise communication but challenging to achieve from corpora which lacks instruction-response formatting without compromising instruction adherence. We introduce StyleAdaptedLM, a framework that efficiently transfers stylistic traits to instruction-following models using Low-Rank Adaptation (LoRA). LoRA adapters are first trained on a base model with diverse unstructured stylistic corpora, then merged with a separate instruction-following model. This enables robust stylistic customization without paired data or sacrificing task performance. Experiments across multiple datasets and models demonstrate improved stylistic consistency while preserving instruction adherence, with human evaluations confirming brand-specific convention uptake. StyleAdaptedLM offers an efficient path for stylistic personalization in LLMs. |
| title | StyleAdaptedLM: Enhancing Instruction Following Models with Efficient Stylistic Transfer |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.18294 |