mlsanityData to 14 Oct 2026

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

arXiv 2505.24189 ↗First posted 30 May 2025cs.LG cs.AI cs.CLcited by 6

Not on the map. Why?

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.

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

19 of 29 references.

References · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  6. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  7. 2023BloombergGPT: A Large Language Model for Financecited by 939
  8. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 236
  9. 2020TIDE: A General Toolbox for Identifying Object Detection Errorscited by 114
  10. 2024Reducing hallucination in structured outputs via Retrieval-Augmented Generationcited by 93
  11. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 83
  12. 2024What's Wrong with Your Code Generated by Large Language Models? An Extensive Studycited by 53
7 more
  1. 2022Sub-Task Decomposition Enables Learning in Sequence to Sequence Taskscited by 41
  2. 2024SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domaincited by 39
  3. 2024Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?cited by 33
  4. 2024FlowMind: Automatic Workflow Generation with LLMscited by 30
  5. 2024Automating the Enterprise with Foundation Modelscited by 14
  6. 2024A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentationcited by 10
  7. 2022Azimuth: Systematic Error Analysis for Text Classificationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Performance Trade-offs of Optimizing Small Language Models for E-Commercecited by 1
  2. 2026On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RLcited by 1
  3. 2025Trained Miniatures: Low cost, High Efficacy SLMs for Sales & Marketingcited by 0
  4. 2026FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoningcited by 0
  5. 2026LIFT: Last-Mile Fine-Tuning for Table Explicitationcited by 0
  6. 2026Quantifying Prior Dominance in RAG Systemscited by 0