# Towards Modular LLMs by Building and Reusing a Library of LoRAs

arXiv: https://arxiv.org/abs/2405.11157 · HTML: https://mlsanity.com/paper/2405.11157/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Builds on 81 of its 96 references that are in the map.
- First posted on arXiv 18 May 2024.

## Builds on (most cited first, 30 of 81)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)

## Built on by (most cited first, 30 of 72)

- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [Text-to-LoRA: Instant Transformer Adaption](https://mlsanity.com/paper/2506.06105/) (2025)
- [A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning](https://mlsanity.com/paper/2408.07057/) (2024)
- [CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing](https://mlsanity.com/paper/2502.01976/) (2025)
- [Concept-skill Transferability-based Data Selection for Large Vision-Language Models](https://mlsanity.com/paper/2406.10995/) (2024)
- [Training Plug-n-Play Knowledge Modules with Deep Context Distillation](https://mlsanity.com/paper/2503.08727/) (2025)
- [LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing](https://mlsanity.com/paper/2507.00029/) (2025)
- [MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models](https://mlsanity.com/paper/2405.13053/) (2024)
- [Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning](https://mlsanity.com/paper/2406.16989/) (2024)
- [FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion](https://mlsanity.com/paper/2406.03280/) (2024)
- [Understanding LoRA as Knowledge Memory: An Empirical Analysis](https://mlsanity.com/paper/2603.01097/) (2026)
- [SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models](https://mlsanity.com/paper/2408.10174/) (2024)
- [LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2507.05346/) (2025)
- [Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts](https://mlsanity.com/paper/2408.15901/) (2024)
- [Permissioned LLMs: Enforcing Access Control in Large Language Models](https://mlsanity.com/paper/2505.22860/) (2025)
- [Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP](https://mlsanity.com/paper/2510.21453/) (2025)
- [MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts](https://mlsanity.com/paper/2408.01505/) (2024)
- [LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits](https://mlsanity.com/paper/2502.08141/) (2025)
- [Efficient Model Development through Fine-tuning Transfer](https://mlsanity.com/paper/2503.20110/) (2025)
- [SpectR: Dynamically Composing LM Experts with Spectral Routing](https://mlsanity.com/paper/2504.03454/) (2025)
- [Effective LoRA Adapter Routing using Task Representations](https://mlsanity.com/paper/2601.21795/) (2026)
- [MASS: MoErging through Adaptive Subspace Selection](https://mlsanity.com/paper/2504.05342/) (2025)
- [Glider: Global and Local Instruction-Driven Expert Router](https://mlsanity.com/paper/2410.07172/) (2024)
- [Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide](https://mlsanity.com/paper/2411.09539/) (2024)
- [FedMerge: Federated Personalization via Model Merging](https://mlsanity.com/paper/2504.06768/) (2025)
- [From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging](https://mlsanity.com/paper/2506.14126/) (2025)
- [HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization](https://mlsanity.com/paper/2510.12266/) (2025)
- [Exploring How LLMs Capture and Represent Domain-Specific Knowledge](https://mlsanity.com/paper/2504.16871/) (2025)
- [One Rank at a Time: Cascading Error Dynamics in Sequential Learning](https://mlsanity.com/paper/2505.22602/) (2025)

## Abstract (arXiv)

The growing number of parameter-efficient adaptations of a base large language model (LLM) calls for studying whether we can reuse such trained adapters to improve performance for new tasks. We study how to best build a library of adapters given multi-task data and devise techniques for both zero-shot and supervised task generalization through routing in such library. We benchmark existing approaches to build this library and introduce model-based clustering, MBC, a method that groups tasks based on the similarity of their adapter parameters, indirectly optimizing for transfer across the multi-task dataset. To re-use the library, we present a novel zero-shot routing mechanism, Arrow, which enables dynamic selection of the most relevant adapters for new inputs without the need for retraining. We experiment with several LLMs, such as Phi-2 and Mistral, on a wide array of held-out tasks, verifying that MBC-based adapters and Arrow routing lead to superior generalization to new tasks. We make steps towards creating modular, adaptable LLMs that can match or outperform traditional joint training.