paper-with-me

Papers

DEFT: Data Efficient Fine-Tuning for Pre-Trained Language Models via Unsupervised Core-Set Selection

2023-10-25 · Devleena Das, Vivek Khetan

Recent advances have led to the availability of many pre-trained language models (PLMs); however, a question that remains is how much data is truly needed to fine-tune PLMs for downstream tasks? In this work, we introduce DEFT-UCS, a data-efficient fine-tuning framework that leverages unsupervised core-set selection to identify a smaller, representative dataset that reduces the amount of data needed to fine-tune PLMs for downstream tasks. We examine the efficacy of DEFT-UCS in the context of text-editing LMs, and compare to the state-of-the art text-editing model, CoEDIT. Our results demonstrate that DEFT-UCS models are just as accurate as CoEDIT, across eight different datasets consisting of six different editing tasks, while finetuned on 70% less data.

📄 PDF Abstract BibTeX arXiv:2310.16776

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Vision-Language Models are Strong Noisy Label Detectors

2024-09-29 · Tong Wei, Hao-Tian Li, Chun-Shu Li, Jiang-Xin Shi 외

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a si…

Denoisingimage-classificationImage Classificationparameter-efficient fine-tuning

From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers

2024-02-02 · Bharat Runwal, Tejaswini Pedapati, Pin-Yu Chen

Pretrained Language Models (PLMs) have become the de facto starting point for fine-tuning on downstream tasks. However, as model sizes continue to increase, traditional fine-tuning of all the parameters becomes challengi…

Decoderparameter-efficient fine-tuning

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

DEFT-VTON: Efficient Virtual Try-On with Consistent Generalised H-Transform

2025-09-16 · Xingzi Xu, Qi Li, Shuwen Qiu, Julien Han 외 arxiv

Diffusion models enable high-quality virtual try-on (VTO) with their established image synthesis abilities. Despite the extensive end-to-end training of large pre-trained models involved in current VTO methods, real-worl…

parameter-efficient fine-tuningVirtual Try-on

UPB at SemEval-2020 Task 6: Pretrained Language Models for Definition Extraction

2020-09-11 · SEMEVAL 2020 · Andrei-Marius Avram, Dumitru-Clementin Cercel, Costin-Gabriel Chiru

This work presents our contribution in the context of the 6th task of SemEval-2020: Extracting Definitions from Free Text in Textbooks (DeftEval). This competition consists of three subtasks with different levels of gran…

Definition ExtractionGeneral ClassificationLanguage ModelingLanguage Modelling+1