Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?

arXiv:2606.03782 · cs.CL · Submitted 2026-06-02 · Read on arXiv

cs.CL

Submitted: 2026-06-02

Updated: 2026-08-29

Comments: EMNLP 2026 Findings

Project page: https://olaresearch.github.io/LingReason

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

Terminology

• Trace — 79× in this paper · explained in 2 episodes
• Reasoning Traces — 47× in this paper · explained in 3 episodes
• Fine-Tuning — 17× in this paper · explained in 5 episodes
• Low-Resource Languages — 9× in this paper · explained in 4 episodes
• In-Context Learning — 8× in this paper · explained in 4 episodes
• Universal Dependencies — 6× in this paper
• LLM-as-a-Judge — 4× in this paper · explained in 3 episodes
• Reward Function — 4× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Supervised Fine-Tuning (SFT) — 3× in this paper · explained in 8 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Thinking mode — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• In-Context Learning (ICL) — 1× in this paper · explained in 5 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Munich Center for Machine Learning — 1× in this paper
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Building Machine Translation Systems for the Next Thousand Languages
• R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
• Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation
• Unlocking Reasoning Capability on Machine Translation in Large Language Models
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Qwen3 Technical Report
• Hunyuan-MT Technical Report

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