Results 11 to 20 of about 1,512,342 (361)
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning [PDF]
Neural Information Processing Systems, 2022 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 training examples as part of the input.
Haokun Liu +6 more
semanticscholar +1 more source
Retrograde Tuning of Tuning [PDF]
Neuron, 2008 One way to localize sounds is to measure differences in sound intensity at the two ears. This comparison is made in the lateral superior olive, where signals from both ears converge. Magnusson et al. in this issue of Neuron show that dendritic GABA release can regulate this comparison, which may allow animals localizing sounds to adapt to listening ...
Xu-Friedman, Matthew A., Regehr, Wade G.
openaire +2 more sources
Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022 To appear in EMNLP 2022.
Yifan Chen 0004 +5 more
openaire +2 more sources
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified. We show that with small-to-medium training data, applying BitFit on pre-trained BERT models is competitive with (and ...
Elad Ben-Zaken +2 more
semanticscholar +1 more source
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning [PDF]
International Conference on Machine Learning, 2023 We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies on the Flan Collection of tasks and methods, we tease apart the effect of ...
S. Longpre +10 more
semanticscholar +1 more source
Tuning in Higher Education: Ten years on
Tuning Journal for Higher Education, 2023 When the first issue of the Tuning Journal for Higher Education was published in November 2013, the Tuning initiative had become of global significance, running projects in all continents.
Julia María González Ferreras +1 more
doaj +1 more source
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention [PDF]
arXiv.org, 2023 We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter only introduces 1.2M learnable parameters upon the frozen LLaMA 7B model ...
Renrui Zhang +8 more
semanticscholar +1 more source
Tuning in by tuning out distractions [PDF]
Proceedings of the National Academy of Sciences, 2016 Working memory is a limited workspace for temporarily holding information in mind, and it is critical for thinking and problem solving. A person’s ability to perform a variety of complicated intelligent behaviors, such as abstract reasoning, mathematics, and acquiring new languages, depends greatly on his or her specific working memory capacity.
Kirsten C S, Adam, Edward K, Vogel
openaire +2 more sources
Fine-Tuning Language Models with Just Forward Passes [PDF]
Neural Information Processing Systems, 2023 Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but as LMs grow in size, backpropagation requires a prohibitively large amount of memory.
Sadhika Malladi +6 more
semanticscholar +1 more source
TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation [PDF]
ACM Conference on Recommender Systems, 2023 Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains, thereby prompting researchers to explore their potential for use in recommendation systems. Initial attempts have leveraged the exceptional capabilities of LLMs,
Keqin Bao +5 more
semanticscholar +1 more source