Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation

arXiv:2603.12983 · cs.CL, cs.AI · Submitted 2026-03-13 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-03-13

Updated: 2026-09-01

Comments: EMNLP2026 Findings

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Machine Translation — 29× in this paper
• Distillation — 23× in this paper · explained in 2 episodes
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Error Span Detection — 7× in this paper
• Pseudo-labels — 6× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Minimum Bayes Risk — 5× in this paper
• Alignment — 3× in this paper · explained in 1 episode
• Calibration — 3× in this paper · explained in 7 episodes
• Direct Preference Optimization — 3× in this paper
• Loss Function — 3× in this paper · explained in 2 episodes
• Direct Preference Optimization (DPO) — 2× in this paper · explained in 9 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Soft Pairwise Accuracy — 2× in this paper
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Kahneman-Tversky Optimization — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multidimensional Quality Metrics — 1× in this paper
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning — 1× in this paper
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• Minimum Bayes Risk Decoding for Error Span Detection in Reference-Free Automatic Machine Translation Evaluation
• Enhancing Training Efficiency Using Packing with Flash Attention
• A Survey on Self-Evolution of Large Language Models
• Qwen3 Technical Report
• Efficient Guided Generation for Large Language Models
• SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering