# The Prompt is Mightier than the Example

arXiv: https://arxiv.org/abs/2505.18485 · HTML: https://mlsanity.com/paper/2505.18485/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 24 May 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 20 of 20)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers](https://mlsanity.com/paper/2212.10559/) (2022)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [Generating Multi-label Discrete Patient Records using Generative Adversarial Networks](https://mlsanity.com/paper/1703.06490/) (2017)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks](https://mlsanity.com/paper/2206.06565/) (2022)
- [REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers](https://mlsanity.com/paper/2302.02041/) (2023)
- [Why Does the Effective Context Length of LLMs Fall Short?](https://mlsanity.com/paper/2410.18745/) (2024)
- [Generative Table Pre-training Empowers Models for Tabular Prediction](https://mlsanity.com/paper/2305.09696/) (2023)
- [TabuLa: Harnessing Language Models for Tabular Data Synthesis](https://mlsanity.com/paper/2310.12746/) (2023)
- [TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data](https://mlsanity.com/paper/2106.03096/) (2021)
- [TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models](https://mlsanity.com/paper/2409.16118/) (2024)
- [Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens](https://mlsanity.com/paper/2310.13220/) (2023)
- [STAN: Synthetic Network Traffic Generation with Generative Neural Models](https://mlsanity.com/paper/2009.12740/) (2020)
- [Improving Movement Predictions of Traffic Actors in Bird's-Eye View Models using GANs and Differentiable Trajectory Rasterization](https://mlsanity.com/paper/2004.06247/) (2020)

## Abstract (arXiv)

Numerous recent prompt optimization approaches like chain-of-thought, have been demonstrated to significantly improve the quality of content generated by large language models (LLMs). In-context learning (ICL), a recent paradigm where a few representative examples guide content generation has also led to strong improvements in generation quality of LLM generated content. This idea has been applied to great effect in synthetic tabular data generation, where LLMs, through effective use of ICL and prompt optimization, can generate data that approximate samples from complex, heterogeneous distributions based on representative examples. However, ensuring high-fidelity synthetic data often requires a very large number of ICL examples which may be unavailable or costly to obtain. At the same time, as LLMs get larger and larger, their in-built prior knowledge becomes vast and can potentially substitute for specific data examples. In this paper, we introduce Knowledge-Guided Prompting (KGP) as a new knob in prompt optimization and explore the ability of KGP-based prompt optimization to offset the cost of ICL. Specifically, we explore the question `how many examples can a prompt substitute for?' and explore knowledge-guided prompting (KGP) where domain knowledge, either inferred or available, is explicitly injected into the prompt, reducing dependence on ICL examples. Our experiments systematically explore the trade-off between ICL and KGP, revealing an empirical scaling law that quantifies how quality of generated synthetic data varies with increasing domain knowledge and decreasing example count. Our results demonstrate that knowledge-guided prompting can be a scalable alternative, or addition, to in-context examples, unlocking new approaches to synthetic data generation.