A Multi-Stage Workflow for the Review of Marketing Content with Reasoning Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915719633960960 |
|---|---|
| author | Purpura, Alberto Chen, Emily Shinde, Swapnil |
| author_facet | Purpura, Alberto Chen, Emily Shinde, Swapnil |
| contents | Reasoning Large Language Models (LLMs) have shown promising results when tasked with solving complex problems. In this paper, we propose and evaluate a multi-stage workflow that leverages the capabilities of fine-tuned reasoning LLMs to assist in the review process of marketing content, making sure they comply with a given list of requirements. The contributions of this paper are the following: (i) we present a novel approach -- that does not rely on any external knowledge representation -- for the automatic identification of compliance issues in textual content; (ii) compare the effectiveness of different fine-tuning strategies like Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) in training models to solve this problem; (iii) we evaluate the effectiveness of training small LLMs to generate reasoning tokens before providing their final response; (iv) we evaluate how the choice and combinations of different reward functions affects the performance of a model trained with GRPO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06054 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Multi-Stage Workflow for the Review of Marketing Content with Reasoning Large Language Models Purpura, Alberto Chen, Emily Shinde, Swapnil Computation and Language Artificial Intelligence Reasoning Large Language Models (LLMs) have shown promising results when tasked with solving complex problems. In this paper, we propose and evaluate a multi-stage workflow that leverages the capabilities of fine-tuned reasoning LLMs to assist in the review process of marketing content, making sure they comply with a given list of requirements. The contributions of this paper are the following: (i) we present a novel approach -- that does not rely on any external knowledge representation -- for the automatic identification of compliance issues in textual content; (ii) compare the effectiveness of different fine-tuning strategies like Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) in training models to solve this problem; (iii) we evaluate the effectiveness of training small LLMs to generate reasoning tokens before providing their final response; (iv) we evaluate how the choice and combinations of different reward functions affects the performance of a model trained with GRPO. |
| title | A Multi-Stage Workflow for the Review of Marketing Content with Reasoning Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.06054 |