Mergenetic: a Simple Evolutionary Model Merging Library (2025.acl-demo)

Copied to clipboard

Challenge: Recent work shows that combining model merging with evolutionary algorithms can boost performance, but there is currently no library for experimenting with different evolutionary algorithms and merging methods.
Approach: They propose an open-source library for evolutionary model merging that enables easy composition of merging methods and evolutionary algorithms while incorporating lightweight fitness estimators to reduce evaluation costs.
Outcome: The proposed library produces competitive results across languages and tasks using modest hardware.

Similar Papers

Arcee’s MergeKit: A Toolkit for Merging Large Language Models (2024.emnlp-industry)

Copied to clipboard

Challenge: Open-source language models can merge their parameters to improve performance and versatility without additional training.
Approach: They propose to integrate model checkpoints into powerful multitask models without additional training.
Outcome: the library has facilitated the merging of thousands of models, contributing to some of the world’s most powerful open-source model checkpoints.
MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs (2025.naacl-long)

Copied to clipboard

Challenge: State-of-the-art methods for merging expert models with different architectures do not address parameter interference and require extensive fine-tuning to restore performance.
Approach: They propose a method for merging experts with different architectures into a unified Mixture-of-Experts model with a goal of enhancing performance in each domain while retaining effectiveness on general tasks.
Outcome: Experiments across multiple domains show that the proposed methods reduce fine-tuning costs and improve performance over state-of-the-art methods.
Unlocking the Potential of Model Merging for Low-Resource Languages (2024.findings-emnlp)

Copied to clipboard

Challenge: Adapting large language models (LLMs) to new languages requires continual pre-training followed by supervised fine-tuning.
Approach: They propose a model merging solution that integrates LLMs with distinct capabilities into a single model without additional training.
Outcome: The proposed model merging outperforms CT-then-SFT in low-resource languages with scarce data.
Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging (2024.findings-emnlp)

Copied to clipboard

Challenge: Adapting general-purpose language models to new skills is currently expensive . Adaptation to new skill sets requires repeated training or models forget older skills .
Approach: They propose a parallel-train-then-merge procedure that adds new skills to preexisting models in isolation and later merges with the general model.
Outcome: The proposed method is cheaper than retraining models on updated datasets . it improves model compliance with safe prompts while preserving model's ability to refuse dangerous or harmful prompts.
LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging (2025.findings-emnlp)

Copied to clipboard

Challenge: a framework for model merging is proposed without additional training . task vectors from fine-tuned models exhibit a limited number of dominant singular values .
Approach: They propose a framework for model merging based on low-rank estimation of task vectors without access to the base model.
Outcome: The proposed framework improves models without additional training without additional inputs.
Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: a zero-shot merging framework for large language models consolidates specialized domain experts into a single model without any further training.
Approach: They propose a zero-shot merging framework that consolidates specialized domain experts into a single model without further training.
Outcome: Experiments on code generation, mathematical reasoning, medical question answering, and instruction-following benchmarks confirm the versatility and effectiveness of the proposed framework.
Knowledge Fusion By Evolving Weights of Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Experimental results on mainstream language models show that Evolver outperforms previous state-of-the-art models by large margins due to the high training costs of large language models.
Approach: They propose a method to integrate multiple models from diverse training scenarios into a unified model.
Outcome: The proposed method outperforms state-of-the-art models on mainstream language models by large margins.
DivMerge: A divergence-based model merging method for multi-tasking (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for multitask learning struggle with interference between tasks, especially as the number of tasks grows.
Approach: They propose a reference-free method that minimizes the divergence between models' outputs and those of the merged model, automatically balancing task importance.
Outcome: The proposed method outperforms existing methods on classification and generative tasks and remains robust when scaling to more tasks.
Dynamic Fisher-weighted Model Merging via Bayesian Optimization (2025.naacl-long)

Copied to clipboard

Challenge: Existing merging approaches involve scaling the parameters model-wise or integrating parameter importance parameter-wise.
Approach: They propose a method for merging model-based models at the parameter level without training data or joint training.
Outcome: The proposed model merging framework outperforms baseline models on validation sets.
To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to model merging ignore the fundamental roles of neurons, connectivity and activation.
Approach: They propose a framework that relies on neuronal mechanisms to mitigate task interference . they decomposed task-specific representations into two complementary subspaces . their results offer new insights into mitigating task interference and improving knowledge fusion .
Outcome: The proposed framework reduces task interference within neurons and improves knowledge fusion.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations