paper-with-me

Papers

Composable Sparse Fine-Tuning for Cross-Lingual Transfer

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and sparse fine-tuning have been developed. Adapters are modular, as they can be combined to adapt a model towards different facets of knowledge (e.g., dedicated language and/or task adapters). Sparse fine-tuning is expressive, as it controls the behavior of all model components. In this work, we introduce a new fine-tuning method with both these desirable properties. In particular, we learn sparse, real-valued masks based on a simple variant of the Lottery Ticket Hypothesis. Task-specific masks are obtained from annotated data in a source language, and language-specific masks from masked language modeling in a target language. Both these masks can then be composed with the pretrained model. Unlike adapter-based fine-tuning, this method neither increases the number of parameters at inference time nor alters the original model architecture. Most importantly, it outperforms adapters in zero-shot cross-lingual transfer by a large margin in a series of multilingual benchmarks, including Universal Dependencies, MasakhaNER, and AmericasNLI. Based on an in-depth analysis, we additionally find that sparsity is crucial to prevent both 1) interference between the fine-tunings to be composed and 2) overfitting. We release the code and models at [ANONYMOUS-URL].

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual TransferLanguage ModelingLanguage ModellingMasked Language ModelingTransfer LearningZero-Shot Cross-Lingual Transfer

Similar Papers 제목 키워드 기반

DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer

2025-05-21 · Sona Elza Simon, Preethi Jyothi

Effective cross-lingual transfer remains a critical challenge in scaling the benefits of large language models from high-resource to low-resource languages. Towards this goal, prior studies have explored many approaches …

Cross-Lingual TransferNatural Language InferenceSentiment AnalysisSentiment Classification+1

Composable Sparse Fine-Tuning for Cross-Lingual Transfer

2021-10-14 · ACL 2022 5 · Alan Ansell, Edoardo Maria Ponti, Anna Korhonen, Ivan Vulić

Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques l…

Cross-Lingual TransferLanguage ModelingLanguage ModellingMasked Language Modeling+2

SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning

2022-07-11 · Zihao Ye, Ruihang Lai, Junru Shao, Tianqi Chen 외

Sparse tensors are rapidly becoming critical components of modern deep learning workloads. However, developing high-performance sparse operators can be difficult and tedious, and existing vendor libraries cannot satisfy …

Deep Learning

Efficient Model Editing with Task-Localized Sparse Fine-tuning

2025-04-03 · Leonardo Iurada, Marco Ciccone, Tatiana Tommasi

Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network linearization to derive task vectors, l…

DisentanglementModel EditingNegationTask Arithmetic

FedP$^2$EFT: Federated Learning to Personalize Parameter Efficient Fine-Tuning for Multilingual LLMs

2025-02-05 · Royson Lee, Minyoung Kim, Fady Rezk, Rui Li 외

Federated learning (FL) has enabled the training of multilingual large language models (LLMs) on diverse and decentralized multilingual data, especially on low-resource languages. To improve client-specific performance, …

Federated Learningparameter-efficient fine-tuning