AdaMix, a parameter-efficient fine-tuning method, outperforms full model fine-tuning in few-shot NLU tasks across benchmarks like GLUE. Using prompt-based strategies without extra validation or unlabeled data, AdaMix consistently boosts performance with both BERT and RoBERTa encoders, demonstrating stability and efficiency in few-shot scenarios.AdaMix, a parameter-efficient fine-tuning method, outperforms full model fine-tuning in few-shot NLU tasks across benchmarks like GLUE. Using prompt-based strategies without extra validation or unlabeled data, AdaMix consistently boosts performance with both BERT and RoBERTa encoders, demonstrating stability and efficiency in few-shot scenarios.

Smarter AI Training with Few-Shot Natural Language Tasks

2025/10/02 17:00

Abstract and 1. Introduction

  1. Background

    2.1 Mixture-of-Experts

    2.2 Adapters

  2. Mixture-of-Adaptations

    3.1 Routing Policy

    3.2 Consistency regularization

    3.3 Adaptation module merging and 3.4 Adaptation module sharing

    3.5 Connection to Bayesian Neural Networks and Model Ensembling

  3. Experiments

    4.1 Experimental Setup

    4.2 Key Results

    4.3 Ablation Study

  4. Related Work

  5. Conclusions

  6. Limitations

  7. Acknowledgment and References

Appendix

A. Few-shot NLU Datasets B. Ablation Study C. Detailed Results on NLU Tasks D. Hyper-parameter

A Few-shot NLU Datasets

Data. In contrast to the fully supervised setting in the above experiments, we also perform fewshot experiments following the prior study (Wang et al., 2021) on six tasks including MNLI (Williams et al., 2018), RTE (Dagan et al., 2005; Bar Haim et al., 2006; Giampiccolo et al., 2007; Bentivogli et al., 2009), QQP[1] and SST-2 (Socher et al.). The results are reported on their development set following (Zhang et al., 2021). MPQA (Wiebe et al., 2005) and Subj (Pang and Lee, 2004) are used for polarity and subjectivity detection, where we follow (Gao et al., 2021) to keep 2, 000 examples for testing. The few-shot model only has access to |K| labeled samples for any task. Following true few-shot learning setting (Perez et al., 2021; Wang et al., 2021), we do not use any additional validation set for any hyper-parameter tuning or early stopping. The performance of each model is reported after fixed number of training epochs. For a fair comparison, we use the same set of few-shot labeled instances for training as in (Wang et al., 2021). We train each model with 5 different seeds and report average performance with standard deviation across the runs. In the few-shot experiments, we follow (Wang et al., 2021) to train AdaMix via the prompt-based fine-tuning strategy. In contrast to (Wang et al., 2021), we do not use any unlabeled data.

\

B Ablation Study

\ Table 11: Ablation study demonstrating the impact of parameter sharing in AdaMix adapter framework.

\

C Detailed Results on NLU Tasks

The results on NLU tasks are included in Table 1 and Table 13. The performance AdaMix with RoBERTa-large encoder achieves the best performance in terms of different task metrics in the GLUE benchmark. AdaMix with adapters is the

\ \ Table 12: Varying the bottleneck dimension of adapters in AdaMix with BERT-base and RoBERTa-large encoder. * denotes the bottleneck dimension used in AdaMix with adapters.

\ \ only PEFT method which outperforms full model fine-tuning on all the tasks and on average score. Additionally, the improvement brought by AdaMix is more significant with BERT-base as the encoder, demonstrating 2.2% and 1.2% improvement over the performance of full model fine-tuning and the best performing baseline UNIPELT with BERTbase. The improvement is observed to be consistent as that with RoBERTa-large on every task. The NLG results are included in Table 4 and 5.

D Hyper-parameter

Detailed hyper-parameter configuration for different tasks presented in Table 15 and Table 16.

\

:::info Authors:

(1) Yaqing Wang, Purdue University ([email protected]);

(2) Sahaj Agarwal, Microsoft ([email protected]);

(3) Subhabrata Mukherjee, Microsoft Research ([email protected]);

(4) Xiaodong Liu, Microsoft Research ([email protected]);

(5) Jing Gao, Purdue University ([email protected]);

(6) Ahmed Hassan Awadallah, Microsoft Research ([email protected]);

(7) Jianfeng Gao, Microsoft Research ([email protected]).

:::


:::info This paper is available on arxiv under CC BY 4.0 DEED license.

:::

[1] https://www.quora.com/q/quoradata/

Piyasa Fırsatı
Sleepless AI Logosu
Sleepless AI Fiyatı(AI)
$0.03923
$0.03923$0.03923
-0.90%
USD
Sleepless AI (AI) Canlı Fiyat Grafiği
Sorumluluk Reddi: Bu sitede yeniden yayınlanan makaleler, halka açık platformlardan alınmıştır ve yalnızca bilgilendirme amaçlıdır. MEXC'nin görüşlerini yansıtmayabilir. Tüm hakları telif sahiplerine aittir. Herhangi bir içeriğin üçüncü taraf haklarını ihlal ettiğini düşünüyorsanız, kaldırılması için lütfen [email protected] ile iletişime geçin. MEXC, içeriğin doğruluğu, eksiksizliği veya güncelliği konusunda hiçbir garanti vermez ve sağlanan bilgilere dayalı olarak alınan herhangi bir eylemden sorumlu değildir. İçerik, finansal, yasal veya diğer profesyonel tavsiye niteliğinde değildir ve MEXC tarafından bir tavsiye veya onay olarak değerlendirilmemelidir.

Ayrıca Şunları da Beğenebilirsiniz

South African lawmakers put Starlink launch on hold over policy clash

South African lawmakers put Starlink launch on hold over policy clash

Elon Musk’s Starlink may face delays in delivering satellite internet to South Africa. Lawmakers are opposing a recent…
Paylaş
Technext2025/12/15 20:31
United States Building Permits Change dipped from previous -2.8% to -3.7% in August

United States Building Permits Change dipped from previous -2.8% to -3.7% in August

The post United States Building Permits Change dipped from previous -2.8% to -3.7% in August appeared on BitcoinEthereumNews.com. Information on these pages contains forward-looking statements that involve risks and uncertainties. Markets and instruments profiled on this page are for informational purposes only and should not in any way come across as a recommendation to buy or sell in these assets. You should do your own thorough research before making any investment decisions. FXStreet does not in any way guarantee that this information is free from mistakes, errors, or material misstatements. It also does not guarantee that this information is of a timely nature. Investing in Open Markets involves a great deal of risk, including the loss of all or a portion of your investment, as well as emotional distress. All risks, losses and costs associated with investing, including total loss of principal, are your responsibility. The views and opinions expressed in this article are those of the authors and do not necessarily reflect the official policy or position of FXStreet nor its advertisers. The author will not be held responsible for information that is found at the end of links posted on this page. If not otherwise explicitly mentioned in the body of the article, at the time of writing, the author has no position in any stock mentioned in this article and no business relationship with any company mentioned. The author has not received compensation for writing this article, other than from FXStreet. FXStreet and the author do not provide personalized recommendations. The author makes no representations as to the accuracy, completeness, or suitability of this information. FXStreet and the author will not be liable for any errors, omissions or any losses, injuries or damages arising from this information and its display or use. Errors and omissions excepted. The author and FXStreet are not registered investment advisors and nothing in this article is intended…
Paylaş
BitcoinEthereumNews2025/09/18 02:20
Strategy (MSTR) Stock: Michael Saylor Signals Bitcoin Purchase as BTC Falls to $87,600

Strategy (MSTR) Stock: Michael Saylor Signals Bitcoin Purchase as BTC Falls to $87,600

TLDR Strategy chairman Michael Saylor hinted at another Bitcoin acquisition Sunday as BTC dropped to $87,600, posting his signature “orange dots” chart The company
Paylaş
Blockonomi2025/12/15 20:23