# GRaSp: Automatic Example Optimization for In-Context Learning in Low-Data Tasks

arXiv: https://arxiv.org/abs/2605.07454 · HTML: https://mlsanity.com/paper/2605.07454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 11 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 10 of 10)

- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Reordering Examples Helps during Priming-based Few-Shot Learning](https://mlsanity.com/paper/2106.01751/) (2021)
- [FiNER: Financial Numeric Entity Recognition for XBRL Tagging](https://mlsanity.com/paper/2203.06482/) (2022)
- [How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?](https://mlsanity.com/paper/2404.03302/) (2024)
- [Improving Short Text Classification With Augmented Data Using GPT-3](https://mlsanity.com/paper/2205.10981/) (2022)
- [Se2: Sequential Example Selection for In-Context Learning](https://mlsanity.com/paper/2402.13874/) (2024)
- [Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models](https://mlsanity.com/paper/2404.00884/) (2024)

## Abstract (arXiv)

In-context learning enables large language models to adapt to new tasks, but their performance is highly sensitive to the selected examples. Finding effective demonstrations is particularly difficult in domain-specific, low-data settings where high-quality examples are scarce. We propose GRaSp, a three-stage framework for automatic in-context example optimization. By first generating a large synthetic candidate pool, then structuring it with clustering and dimensionality reduction, and finally using genetic algorithms to find the optimal in-context examples, the framework shows consistent improvements on the NER task. We also introduce a custom diversity-adaptive mutation mechanism, allowing it to transition from the initial broad inter-cluster exploration to focused intra-cluster refinement as the population converges. We evaluate GRaSp on financial named entity recognition (FiNER-139), comparing synthetic and human-annotated candidate pools across pool sizes of 500 and 5000. With non-synthetic data, GRaSp achieves 45.84% micro-F1, consistently outperforming both zero-shot and random few-shot baselines. Synthetic data matches the random baseline but does not exceed it, suggesting that distributional variety in the candidate pool is critical for generalization.