{"slug": "translation-cot-a-human-inspired-chain-of-thought-framework-for-multilingual-llm", "title": "Translation-CoT: A Human-Inspired Chain-of-Thought Framework for Multilingual LLM Translation", "summary": "Researchers from the University of Vermont introduced Translation-CoT, a chain-of-thought prompting framework that breaks translation into lexical retrieval, grammatical analysis, and topic identification stages, followed by a refinement step. In evaluations across 14 languages and multiple LLMs including GPT-4o, GPT-4o-mini, LLaMA 3.1, and Gemma 2, Translation-CoT outperformed zero-shot prompting, in-context learning, Tree-of-Thought, and Learning-Oriented Prompting on BLEU, ChrF, and METEOR metrics, with GPT-4o performing best overall and strongest gains in English-to-non-English and low-resource settings. Human evaluation showed higher preference scores and lower MQM penalty scores, indicating fewer mistranslations, omissions, awkward phrasing, and hallucinations.", "body_md": "[Translation-CoT: A Human-Inspired Chain-of-Thought Framework for Multilingual LLM Translation](https://aclanthology.org/2026.amta-research.2.pdf)\n\n[Tabia Tanzin Prama](/people/tabia-tanzin-prama/),\n[Juniper L Lovato](/people/juniper-l-lovato/unverified/),\n[Chris Danforth](/people/chris-danforth/unverified/),\n[Peter Dodds](/people/peter-dodds/)\n\n##### Abstract\n\nLarge language models (LLMs) have transformed machine translation, yet mistranslations, hallucinations, and unnatural phrasing still limit their effectiveness, particularly for low-resource languages. We propose Translation-CoT, a chain-of-thought prompting strategy that breaks translation into structured stages (lexical retrieval, grammatical analysis, and topic identification), followed by a refinement step to improve fluency, tone, and idiomatic expression. We evaluate Translation-CoT across 14 languages from 14 language families and multiple LLMs (GPT-4o, GPT-4o-mini, LLaMA 3.1, and Gemma 2), with GPT-4o performing best overall, in both English ↔ non-English (X) translation settings. Compared with zero-shot prompting, in-context learning, and existing chain-of-thought prompting methods (Tree-of-Thought (ToT) and Learning-Oriented Prompting (LOT)), Translation-CoT outperforms these prompting strategies on multilingual machine translation across BLEU, ChrF, and METEOR, with especially strong gains in the more difficult English→non-English (X) setting and in low-resource languages. Human evaluation further shows higher preference scores and lower MQM penalty scores, indicating fewer mistranslations, omissions, awkward phrasing, and hallucinations with Translation-CoT. Overall, our results show that structured, task-aware prompting is an effective approach for improving multilingual translation quality and robustness in LLMs.- Anthology ID:\n- 2026.amta-research.2\n- Volume:\n[Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)](/volumes/2026.amta-research/)- Month:\n- August\n- Year:\n- 2026\n- Address:\n- Québec City, Canada\n- Editors:\n[Eleftheria Briakou](/people/eleftheria-briakou/unverified/),[Jeremy Gwinnup](/people/jeremy-gwinnup/),[Shivali Goel](/people/shivali-goel/unverified/)- Venue:\n[AMTA](/venues/amta/)- SIG:\n- Publisher:\n- Association for Machine Translation in the Americas\n- Note:\n- Pages:\n- 3–27\n- Language:\n- URL:\n[https://aclanthology.org/2026.amta-research.2/](https://aclanthology.org/2026.amta-research.2/)- DOI:\n- Cite (ACL):\n- Tabia Tanzin Prama, Juniper L Lovato, Chris Danforth, and Peter Dodds. 2026.\n[Translation-CoT: A Human-Inspired Chain-of-Thought Framework for Multilingual LLM Translation](https://aclanthology.org/2026.amta-research.2/). In*Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)*, pages 3–27, Québec City, Canada. Association for Machine Translation in the Americas. - Cite (Informal):\n[Translation-CoT: A Human-Inspired Chain-of-Thought Framework for Multilingual LLM Translation](https://aclanthology.org/2026.amta-research.2/)(Prama et al., AMTA 2026)- PDF:\n[https://aclanthology.org/2026.amta-research.2.pdf](https://aclanthology.org/2026.amta-research.2.pdf)", "url": "https://wpnews.pro/news/translation-cot-a-human-inspired-chain-of-thought-framework-for-multilingual-llm", "canonical_source": "https://aclanthology.org/2026.amta-research.2/", "published_at": "2026-09-01 00:00:00+00:00", "updated_at": "2026-09-02 11:53:39.659710+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "natural-language-processing", "ai-research"], "entities": ["University of Vermont", "Translation-CoT", "GPT-4o", "GPT-4o-mini", "LLaMA 3.1", "Gemma 2", "Tree-of-Thought", "Learning-Oriented Prompting"], "alternates": {"html": "https://wpnews.pro/news/translation-cot-a-human-inspired-chain-of-thought-framework-for-multilingual-llm", "markdown": "https://wpnews.pro/news/translation-cot-a-human-inspired-chain-of-thought-framework-for-multilingual-llm.md", "text": "https://wpnews.pro/news/translation-cot-a-human-inspired-chain-of-thought-framework-for-multilingual-llm.txt", "jsonld": "https://wpnews.pro/news/translation-cot-a-human-inspired-chain-of-thought-framework-for-multilingual-llm.jsonld"}}