Parameter-efficient fine-tuning of large-scale pre-trained language models

N Ding, Y Qin, G Yang, F Wei, Z Yang, Y Su… - Nature Machine …, 2023 - nature.com
With the prevalence of pre-trained language models (PLMs) and the pre-training–fine-tuning
paradigm, it has been continuously shown that larger models tend to yield better …

Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning

H Liu, D Tam, M Muqeeth, J Mohta… - Advances in …, 2022 - proceedings.neurips.cc
Few-shot in-context learning (ICL) enables pre-trained language models to perform a
previously-unseen task without any gradient-based training by feeding a small number of …

Test-time prompt tuning for zero-shot generalization in vision-language models

M Shu, W Nie, DA Huang, Z Yu… - Advances in …, 2022 - proceedings.neurips.cc
Pre-trained vision-language models (eg, CLIP) have shown promising zero-shot
generalization in many downstream tasks with properly designed text prompts. Instead of …

Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models

N Ding, Y Qin, G Yang, F Wei, Z Yang, Y Su… - arXiv preprint arXiv …, 2022 - arxiv.org
Despite the success, the process of fine-tuning large-scale PLMs brings prohibitive
adaptation costs. In fact, fine-tuning all the parameters of a colossal model and retaining …

Privacy-preserving prompt tuning for large language model services

Y Li, Z Tan, Y Liu - arXiv preprint arXiv:2305.06212, 2023 - arxiv.org
Prompt tuning provides an efficient way for users to customize Large Language Models
(LLMs) with their private data in the emerging LLM service scenario. However, the sensitive …

Pre-trained adversarial perturbations

Y Ban, Y Dong - Advances in Neural Information Processing …, 2022 - proceedings.neurips.cc
Self-supervised pre-training has drawn increasing attention in recent years due to its
superior performance on numerous downstream tasks after fine-tuning. However, it is well …

MixPHM: redundancy-aware parameter-efficient tuning for low-resource visual question answering

J Jiang, N Zheng - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Recently, finetuning pretrained vision-language models (VLMs) has been a prevailing
paradigm for achieving state-of-the-art performance in VQA. However, as VLMs scale, it …

Generative multi-modal knowledge retrieval with large language models

X Long, J Zeng, F Meng, Z Ma, K Zhang… - Proceedings of the …, 2024 - ojs.aaai.org
Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-
intensive multi-modal applications. However, existing methods face challenges in terms of …

Unified detoxifying and debiasing in language generation via inference-time adaptive optimization

Z Yang, X Yi, P Li, Y Liu, X Xie - arXiv preprint arXiv:2210.04492, 2022 - arxiv.org
Warning: this paper contains model outputs exhibiting offensiveness and biases. Recently
pre-trained language models (PLMs) have prospered in various natural language …

On prefix-tuning for lightweight out-of-distribution detection

Y Ouyang, Y Cao, Y Gao, Z Wu, J Zhang… - Proceedings of the 61st …, 2023 - aclanthology.org
Abstract Out-of-distribution (OOD) detection, a fundamental task vexing real-world
applications, has attracted growing attention in the NLP community. Recently fine-tuning …