# Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures

arXiv: https://arxiv.org/abs/2402.17934 · HTML: https://mlsanity.com/paper/2402.17934/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning](https://mlsanity.com/paper/2309.05444/) (2023)
- [Lifting the Curse of Multilinguality by Pre-training Modular Transformers](https://mlsanity.com/paper/2205.06266/) (2022)
- [XOR QA: Cross-lingual Open-Retrieval Question Answering](https://mlsanity.com/paper/2010.11856/) (2020)
- [Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2303.02861/) (2023)
- [Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference](https://mlsanity.com/paper/2110.03742/) (2021)
- [Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation](https://mlsanity.com/paper/2205.12647/) (2022)
- [AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model](https://mlsanity.com/paper/2208.01448/) (2022)
- [Learning Language Specific Sub-network for Multilingual Machine Translation](https://mlsanity.com/paper/2105.09259/) (2021)
- [SiRA: Sparse Mixture of Low Rank Adaptation](https://mlsanity.com/paper/2311.09179/) (2023)
- [Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization](https://mlsanity.com/paper/2311.09344/) (2023)
- [Efficient Test Time Adapter Ensembling for Low-resource Language Varieties](https://mlsanity.com/paper/2109.04877/) (2021)
- [FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning](https://mlsanity.com/paper/2309.04663/) (2023)

## Abstract (arXiv)

Adapting pretrained large language models (LLMs) to various downstream tasks in tens or hundreds of human languages is computationally expensive. Parameter-efficient fine-tuning (PEFT) significantly reduces the adaptation cost, by tuning only a small amount of parameters. However, common PEFT methods LoRA (Hu et al., 2022) suffer from suboptimal performance on diverse dataset mixtures, due to aggressive parameter tying and negative interference among different datasets. In this work, we propose Featurized Low-rank Mixtures (FLix), a novel PEFT method designed for effective multitask multilingual adaptation. FLix associates each unique dataset feature, such as the dataset's language or task, with its own low-rank weight update parameters. By composing feature-specific parameters for each dataset, FLix can accommodate diverse dataset mixtures and generalize better to unseen datasets. Our experiments show that FLix leads to significant improvements over a variety of tasks for both supervised learning and zero-shot settings with gains of up to 14.2 inexact match points in zero-shot semantic parsing.