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.
Modern translation workflows demand more than semantic equivalence. Users routinely require models to preserve JSON or HTML schemas, honor curated glossaries, disambiguate with provided context, and match prescribed registers, often several at once. Conventional metrics such as BLEU and xCOMET capture semantic fidelity but provide little signal on constraint adherence, while general instruction following benchmarks ignore the cross-lingual nature of translation. We introduce \bench, a benchmark for multilingual translation instruction following covering seven languages, with 4,506 single-constraint and 2,838 multi-constraint items spanning six constraint dimensions and five compositional patterns with instructions issued in all seven languages. Constraints are split into a gating subset verified by deterministic checkers and a continuous subset scored by a rubric-based LLM judge, combined under a multiplicative rule that resists reward hacking. Evaluating 15 models reveals systematic gaps that prior protocols miss: Instruction following scales with size more sharply than translation quality, glossary and structured-format constraints dominate the difficulty gradient, and general instruction following rankings correlate only weakly with translation behavior. Our benchmark are available at https://github.com/Tencent-Hunyuan/Hy-MT2/tree/main/IFMTBench.
Fine-tuning large language models on parallel data improves translation quality but can cause catastrophic forgetting. Mitigation methods are generally evaluated by retention on general benchmarks. We ask whether these findings transfer to machine translation (MT) fine-tuning and to MT-specific instruction following (MT-IF): instructions that modify a translation, such as formality, grammatical gender, and length control. We compare methods anchored to auxiliary data, to model outputs, and to the base model parameters, first in a screening study with Llama 3.2 1B Instruct, then on Llama 3.1 8B Instruct fine-tuned on bidirectional Arabic-English or Spanish-English data. Elastic Weight Consolidation preserves general capabilities best in both stages; on the 8B Spanish model the average score on general benchmarks drops 1.7 points versus 11.0 for standard fine-tuning, yet its scores for formality and grammatical gender control remain close to standard fine-tuning. Only data mixing with control-task examples preserves these controls, but its gains do not transfer to unseen prompts for the same task.
Niklas Scholz, David Thulke, Abdallah Nasir +3
AppTek GmbH, Aachen, Germany · Machine Learning and Human Language Technology, RWTH Aachen University, Germany · Applied Science Private University, Amman, Jordan
Translation quality depends on purpose: the same source text demands different translations depending on audience, tone, and communicative intent. Yet MT models and metrics treat translation as a fixed mapping from source to target. LLMs enable users to explicitly specify purpose alongside source text, yet this capability has not been evaluated at scale. We introduce a systematic evaluation of purpose-driven MT across 50 languages, 5 model sizes and 8 text domains. We find that (1) explicit instructions substantially improve translation adaptedness, with larger gains on informal domains (conversation, social media), for larger model sizes and for higher-resource languages; (2) instructions outperform semantically-matched few-shot examples and paragraph-level context; (3) traditional MT metrics fail to capture adaptation quality, often penalizing adapted translations; (4) when curated instructions are unavailable, models can self-generate them from surrounding document context, closing up to 80% of the adaptedness gap to curated instructions. Our results establish that purpose-adapted MT is a viable and measurable capability of LLMs, while highlighting the need for purpose-aware metrics.