AI Paper Atlas

Research map / Benchmarks / WMT14 De-En

WMT14 De-En leaderboard

30 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on WMT14 De-En. Best BLEU: 37.9 (SIR, ICLR 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

WMT14 De-En · BLEU

30 papers, each with its best reported number for its own method; higher is better.

#BLEU ↑MethodPaperTopic
137.9SIR
NLLB-200-distilled-600M
A Semantic Invariant Robust Watermark for Large Language Models
ICLR 2024 · Machine translation table
Language, safety and interpretability
234.94F2-XEnDec
Transformer-big
Self-supervised and Supervised Joint Training for Resource-rich Machine Translation
ICML 2021 · Table 1
Self-supervised and contrastive
334.84APT (BERT encoder, GPT decoder)
BERT; GPT
Acquiring Knowledge from Pre-Trained Model to Neural Machine Translation
AAAI 2020 · Table 1
Pruning and efficient tuning
433.57AB-Net
bert-base-german-cased; bert-base-cased
Incorporating BERT into Parallel Sequence Decoding with Adapters
NeurIPS 2020 · Table 1
Attention and transformers
533.1Transcormer base
Transformer
Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling
NeurIPS 2022 · Table 1
Attention and transformers
632.51AOZPT
Llama-3.1-8B
Online Black-Box Prompt Optimization with Regret Guarantees under Noisy Feedback
ICLR 2026 · Table 13
Bayesian optimization
732.29Viterbi Decoding
PCFG-NAT
Non-autoregressive Machine Translation with Probabilistic Context-free Grammar
NeurIPS 2023 · Table 2
Molecules and proteins
832.27CTC w/ NMLA + beam&lm
CTC w/ NMLA
Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation
NeurIPS 2022 · Table 2
Recognition and long-tail
931.9Model-level dual learningModel-Level Dual Learning
ICML 2018 · Table 3
RNNs and normalization
1031.7DeepShallow w/ Selective KD
DeepShallow
Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation
AAAI 2023 · Main results table
Knowledge distillation
20 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.