# Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories

arXiv: https://arxiv.org/abs/2509.12951 · HTML: https://mlsanity.com/paper/2509.12951/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [Model merging with SVD to tie the Knots](https://mlsanity.com/paper/2410.19735/) (2024)
- [Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging](https://mlsanity.com/paper/2406.15479/) (2024)
- [EMR-Merging: Tuning-Free High-Performance Model Merging](https://mlsanity.com/paper/2405.17461/) (2024)
- [CrossNER: Evaluating Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2012.04373/) (2020)
- [DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling](https://mlsanity.com/paper/2406.11617/) (2024)
- [Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering](https://mlsanity.com/paper/2409.16167/) (2024)
- [LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks](https://mlsanity.com/paper/2402.11455/) (2024)
- [Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts](https://mlsanity.com/paper/2210.03797/) (2022)
- [GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling](https://mlsanity.com/paper/1906.02437/) (2019)
- [See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition](https://mlsanity.com/paper/2407.05417/) (2024)
- [Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation](https://mlsanity.com/paper/2505.24174/) (2025)

## Abstract (arXiv)

Model merging refers to the process of integrating multiple distinct models into a unified model that preserves and combines the strengths and capabilities of the individual models. Most existing approaches rely on task vectors to combine models, typically under the assumption that model parameters are accessible. However, for extremely large language models (LLMs) such as GPT-4, which are often provided solely as black-box services through API interfaces (Language-Model-as-a-Service), model weights are not available to end users. This presents a significant challenge, which we refer to as black-box model merging (BMM) with massive LLMs. To address this challenge, we propose a derivative-free optimization framework based on the evolutionary algorithm (Evo-Merging) that enables effective model merging using only inference-time API queries. Our method consists of two key components: (1) sparsity-based denoising, designed to identify and filter out irrelevant or redundant information across models, and (2) sign-aware scaling, which dynamically computes optimal combination weights for the relevant models based on their performance. We also provide a formal justification, along with a theoretical analysis, for our asymmetric sparsification. Extensive experimental evaluations demonstrate that our approach achieves state-of-the-art results on a range of tasks, significantly outperforming existing strong baselines.