# Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows

arXiv: https://arxiv.org/abs/2505.24189 · HTML: https://mlsanity.com/paper/2505.24189/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [The Natural Language Decathlon: Multitask Learning as Question Answering](https://mlsanity.com/paper/1806.08730/) (2018)
- [TIDE: A General Toolbox for Identifying Object Detection Errors](https://mlsanity.com/paper/2008.08115/) (2020)
- [Reducing hallucination in structured outputs via Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.08189/) (2024)
- [AutoFlow: Automated Workflow Generation for Large Language Model Agents](https://mlsanity.com/paper/2407.12821/) (2024)
- [What's Wrong with Your Code Generated by Large Language Models? An Extensive Study](https://mlsanity.com/paper/2407.06153/) (2024)
- [Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks](https://mlsanity.com/paper/2204.02892/) (2022)
- [SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain](https://mlsanity.com/paper/2407.19584/) (2024)
- [Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?](https://mlsanity.com/paper/2402.00841/) (2024)
- [FlowMind: Automatic Workflow Generation with LLMs](https://mlsanity.com/paper/2404.13050/) (2024)
- [Automating the Enterprise with Foundation Models](https://mlsanity.com/paper/2405.03710/) (2024)
- [A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation](https://mlsanity.com/paper/2407.02742/) (2024)
- [Azimuth: Systematic Error Analysis for Text Classification](https://mlsanity.com/paper/2212.08216/) (2022)

## Built on by (most cited first, 6 of 6)

- [Performance Trade-offs of Optimizing Small Language Models for E-Commerce](https://mlsanity.com/paper/2510.21970/) (2025)
- [On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL](https://mlsanity.com/paper/2601.14456/) (2026)
- [Trained Miniatures: Low cost, High Efficacy SLMs for Sales & Marketing](https://mlsanity.com/paper/2508.15617/) (2025)
- [FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning](https://mlsanity.com/paper/2602.11782/) (2026)
- [LIFT: Last-Mile Fine-Tuning for Table Explicitation](https://mlsanity.com/paper/2605.13424/) (2026)
- [Quantifying Prior Dominance in RAG Systems](https://mlsanity.com/paper/2606.23695/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) such as GPT-4o can handle a wide range of complex tasks with the right prompt. As per token costs are reduced, the advantages of fine-tuning Small Language Models (SLMs) for real-world applications -- faster inference, lower costs -- may no longer be clear. In this work, we present evidence that, for domain-specific tasks that require structured outputs, SLMs still have a quality advantage. We compare fine-tuning an SLM against prompting LLMs on the task of generating low-code workflows in JSON form. We observe that while a good prompt can yield reasonable results, fine-tuning improves quality by 10% on average. We also perform systematic error analysis to reveal model limitations.