paper-with-me

홈 › Papers

TangoBERT: Reducing Inference Cost by using Cascaded Architecture

2022-04-13 · Jonathan Mamou, Oren Pereg, Moshe Wasserblat, Roy Schwartz

The remarkable success of large transformer-based models such as BERT, RoBERTa and XLNet in many NLP tasks comes with a large increase in monetary and environmental cost due to their high computational load and energy consumption. In order to reduce this computational load in inference time, we present TangoBERT, a cascaded model architecture in which instances are first processed by an efficient but less accurate first tier model, and only part of those instances are additionally processed by a less efficient but more accurate second tier model. The decision of whether to apply the second tier model is based on a confidence score produced by the first tier model. Our simple method has several appealing practical advantages compared to standard cascading approaches based on multi-layered transformer models. First, it enables higher speedup gains (average lower latency). Second, it takes advantage of batch size optimization for cascading, which increases the relative inference cost reductions. We report TangoBERT inference CPU speedup on four text classification GLUE tasks and on one reading comprehension task. Experimental results show that TangoBERT outperforms efficient early exit baseline models; on the the SST-2 task, it achieves an accuracy of 93.9% with a CPU speedup of 8.2x.

📄 PDF Abstract BibTeX arXiv:2204.06271

Code (0)

등록된 구현이 없습니다.

Tasks

CPUReading ComprehensionSST-2text-classificationText Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음

Similar Papers 제목 키워드 기반

CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades

2026-04-14 · Raeyoung Chang, Dongwook Kwon, Jisoo Lee, Nikhil Verma arxiv

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, tri…

General Knowledge

Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving

2026-06-25 · Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana, Ammar Abbas 외 arxiv

Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Operators often default to a single model that is either expensive for easy queries or insufficient for har…

Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation

2024-02-19 · Bharat Srikishan, Anika Tabassum, Srikanth Allu, Ramakrishnan Kannan 외

Deep learning architectures have achieved state-of-the-art (SOTA) performance on computer vision tasks such as object detection and image segmentation. This may be attributed to the use of over-parameterized, monolithic …

Image Segmentationobject-detectionObject DetectionSegmentation+1

Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral

2025-02-18 · António Farinhas, Nuno M. Guerreiro, Sweta Agrawal, Ricardo Rei 외

Larger models often outperform smaller ones but come with high computational costs. Cascading offers a potential solution. By default, it uses smaller models and defers only some instances to larger, more powerful models…

Machine Translation

Safety-Aware Cascaded Inference for Crop Damage Assessment with Controlled Error Trade-offs

2026-07-28 · José Thiéry Messigbédé Hagbe, Gani Kawsar Gounou, Songbian Karim Zimé arxiv

In picture-based agricultural insurance for smallholder farmers, missed damage detections carry substantially higher cost than false alarms: a farmer who sustained real losses receives no payout, while unnecessary expert…