# EvoMerge: Neuroevolution for Large Language Models

arXiv: https://arxiv.org/abs/2402.00070 · HTML: https://mlsanity.com/paper/2402.00070/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 7 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 3 of 3)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [WARM: On the Benefits of Weight Averaged Reward Models](https://mlsanity.com/paper/2401.12187/) (2024)

## Built on by (most cited first, 1 of 1)

- [FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion](https://mlsanity.com/paper/2406.03280/) (2024)

## Abstract (arXiv)

Extensive fine-tuning on Large Language Models does not always yield better results. Oftentimes, models tend to get better at imitating one form of data without gaining greater reasoning ability and may even end up losing some intelligence. Here I introduce EvoMerge, a systematic approach to large language model training and merging. Leveraging model merging for weight crossover and fine-tuning for weight mutation, EvoMerge establishes an evolutionary process aimed at pushing models beyond the limits of conventional fine-tuning.