Pith. sign in

REVIEW 7 cited by

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.12993 v1 pith:VSGBFURZ submitted 2020-04-27 cs.CL cs.LG

Ji Xin , Raphael Tang , Jaejun Lee , Yaoliang Yu , Jimmy Lin This is my paper · ORCID
classification cs.CLcs.LG
keywords bertdeebertinferenceapplicationsmodelmodelsableaccelerate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We propose a simple but effective method, DeeBERT, to accelerate BERT inference. Our approach allows samples to exit earlier without passing through the entire model. Experiments show that DeeBERT is able to save up to ~40% inference time with minimal degradation in model quality. Further analyses show different behaviors in the BERT transformer layers and also reveal their redundancy. Our work provides new ideas to efficiently apply deep transformer-based models to downstream tasks. Code is available at https://github.com/castorini/DeeBERT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts

    cs.LG 2026-07 conditional novelty 6.0 of 10

    In looped transformers, halting-gate failures come mainly from how gate training reshapes the trajectory; fixed-prior depth supervision plus simple confidence readouts yields better accuracy per unit of compute.

  2. Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A vision-language model learns to dynamically switch between code-based and visual reasoning for chart questions, improving average accuracy by about one point over fixed strategies.

  3. FREE: Fast and Robust Vision Language Models with Early Exits

    cs.LG 2025-06 conditional novelty 6.0 of 10

    An adversarial early-exit method for frozen-backbone vision language models that reuses the final classifier and reports 1.5x inference speedup with comparable accuracy.

  4. Harnessing Input-Adaptive Inference for Efficient VLN

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A three-part input-adaptive inference method (view masking, adaptive early exit, view caching) cuts VLN computation roughly in half on seven benchmarks with moderate success-rate loss.

  5. Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

    cs.LG 2025-07 reject novelty 4.0 of 10

    Pretrained LLM layers can be skipped/repeated per input to build custom paths, but the search uses ground-truth answers, so the accuracy gains are fitted, not predicted.

  6. MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAG

    cs.DB 2025-07 conditional novelty 4.0 of 10

    A fully on-device RAG pipeline using a partitioned, partially disk-loaded graph index and selective sentence-window reduction claims 1.72-8.89x faster vector search and up to 40.2% lower power than baselines, with com...

  7. T-TAMER: Provably Taming Trade-offs in ML Serving

    cs.LG 2025-09 reject novelty 3.0 of 10

    T-TAMER claims recall is necessary and sufficient for provably optimal early-exit and cascade serving policies, but the main extensions are under-derived and partly reduce to known Gittins-index results.

Pith tools