We present Lumen, The open-source model is available at, our submission to the WMT 2026 General Machine Translation Shared Task. We focus on instruction-specialized translation, where systems must produce accurate translations while satisfying fine-grained requirements on style, terminology, and structured output. Lumen follows a four-stage pipeline. First, continued pre-training and supervised fine-tuning jointly strengthen multilingual translation competence and the ability to follow translation-specific instructions, such as terminology, style, and format constraints. Second, we extend the originally offline M^{2}PO preference-optimization framework into an online preference-optimization stage: the current policy samples candidate translations, an LLM judge assigns continuous direct-assessment scores, and the resulting multi-pair preferences are used to update the model. Third, on-policy distillation transfers stronger translation-instruction-following behavior from a larger teacher model to the Qwen3-14B student, improving translation-instruction adherence while retaining a 14B primary translation backbone. Finally, structure-aware inference and postprocessing preserve required formats, while selective repair addresses clear structural or decoding failures before submission. We participate in 23 translation directions. Under an absolute 1--5 LLM-judge rubric that evaluates translation-instruction following and translation quality separately, Lumen reaches an overall mean score of 4.60. Despite using a 14B translation backbone, it achieves performance comparable to leading proprietary systems in both translation quality and translation-instruction following.
Figures & tables
Figure 1: Overall pipeline of Lumen. Stage 1 (CPT+SFT) adapts a Qwen3-14B backbone to multilingual translation and translation-specific instruction following. Stage 2 (online M 2 PO) uses direct-assessment rewards from DeepSeek-V4-Pro to optimize the current policy from sampled candidates. Stage 3 (OPD) distills instruction-following behavior from a frozen Qwen3-32B-Instruct teacher into the 14B student. Stage 4 performs structure-aware decoding and conservative postchecking to preserve required formats and repair clear failures before submission.
Category
Definition
Literary (novel)
Preserve narrative voice, dialogue, and cultural nuance.
Game
Translate game dialogue and UI text under output constraints.
Medical
Preserve medical terminology, drug names, codes, and entities.
General-domain instruction MT
Follow content and formatting requirements in general-domain MT.
Structured output
Preserve tags, identifiers, and parseable output structure.
Style
Produce the translation in a specified tone or register.
Table 1: Instruction-bearing data used in SFT.
Instr. following
Quality
Overall
System
Avg
Pass%
Avg
Pass%
Avg
Pass%
Qwen3.7-Max-Think
4.50
83.8
4.76
94.0
4.63
88.9
GPT-5.5
4.49
83.4
4.77
94.0
4.63
88.7
Gemini-3.1-Pro
4.49
83.7
4.70
91.1
4.59
87.4
Qwen3.7-Max-NoThink
4.32
78.4
4.48
85.3
4.40
81.8
Ours (14B)
4.49
83.4
4.71
92.0
4.60
87.7
Table 2: Main results on the WMT26 test set (23 official directions). For each aspect we report the mean 1 – 5 rubric score (Avg) and the pass rate (Pass%, percentage of outputs scoring ≥4 ), both judged by DeepSeek-V4-Pro (Section 3.1 ); Overall Avg and Pass% are the unweighted averages of the corresponding values across the two aspects. Baseline rows are ordered by Overall Avg; our system is listed separately in the last row.
Instr. follow.
Quality
Dir.
Avg
Pass%
Avg
Pass%
cs → de
4.90
96.5
4.56
86.7
cs → uk
4.94
98.7
4.55
86.3
cs → vi
4.94
97.5
4.43
80.3
zh → ja
4.96
98.4
4.40
77.7
en → ar EG
4.92
97.1
4.66
89.7
Table 3: Per-direction results of our submitted 14B system on the 23 official WMT26 directions. For each aspect we report the mean 1 – 5 rubric score (Avg) and the pass rate (Pass%, percentage of outputs scoring ≥4 ), judged by DeepSeek-V4-Pro. Overall is the micro-average over all official test items.
Instr. following
Quality
Configuration
Avg
Pass%
Avg
Pass%
Base (14B)
1.14
0.6
1.09
1.0
+ CPT+SFT
4.08
69.5
4.23
74.8
+ Online M 2 PO
4.13
76.8
4.55
89.4
+ OPD
4.38
82.1
4.67
91.3
+ Postcheck
4.49
83.4
4.71
92.0
Table 4: Cumulative ablation on the WMT26 test set. For each aspect we report the mean 1 – 5 rubric score (Avg) and the pass rate (Pass%, percentage of outputs scoring ≥4 ), both judged by DeepSeek-V4-Pro (Section 3.1 ).
Machine translation develops computational methods for converting text, speech, and visual content between languages while preserving meaning and purpose.