mlsanityData to 7 Oct 2026

Analysis of Levenshtein Transformer's Decoder and Its Variants

arXiv 2402.12249 ↗First posted 19 Feb 2024cs.CLcited by 0

On the map: Efficient LLM inference and serving → Speculative decoding

Abstract (arXiv)

Levenshtein transformer (LevT) is a non-autoregressive machine translation model with high decoding efficiency and comparable translation quality in terms of bleu score, due to its parallel decoding and iterative refinement procedure. Are there any deficiencies of its translations and what improvements could be made? In this report, we focus on LevT's decoder and analyse the decoding results length, subword generation, and deletion module's capability. We hope to identify weaknesses of the decoder for future improvements. We also compare translations of the original LevT, knowledge-distilled LevT, LevT with translation memory, and the KD-LevT with translation memory to see how KD and translation memory can help.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving. Builds on 4 of its 5 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

4 of 5 references.

References · 4

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Sequence-Level Knowledge Distillationcited by 761
  3. 2017Non-Autoregressive Neural Machine Translationcited by 457
  4. 2019Understanding Knowledge Distillation in Non-autoregressive Machine Translationcited by 121

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation
  2. 2023Towards Example-Based NMT with Multi-Levenshtein Transformers
  3. 2023Accelerating Transformer Inference for Translation via Parallel Decoding
  4. 2021The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
  5. 2025Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation
  6. 2021Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding
  7. 2024Optimizing example selection for retrieval-augmented machine translation with translation memories
  8. 2024Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation