# Improving LLM Abilities in Idiomatic Translation

arXiv: https://arxiv.org/abs/2407.03518 · HTML: https://mlsanity.com/paper/2407.03518/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 6 of 6)

- [Understanding Transformer Memorization Recall Through Idioms](https://mlsanity.com/paper/2210.03588/) (2022)
- [Examining the Tip of the Iceberg: A Data Set for Idiom Translation](https://mlsanity.com/paper/1802.04681/) (2018)
- [EPIE Dataset: A Corpus For Possible Idiomatic Expressions](https://mlsanity.com/paper/2006.09479/) (2020)
- [Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models](https://mlsanity.com/paper/2308.13961/) (2023)
- [Evaluating Machine Translation Performance on Chinese Idioms with a Blacklist Method](https://mlsanity.com/paper/1711.07646/) (2017)
- [Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting](https://mlsanity.com/paper/2310.07081/) (2023)

## Built on by (most cited first, 16 of 16)

- [NLP Datasets for Idiom and Figurative Language Tasks](https://mlsanity.com/paper/2511.16345/) (2025)
- [SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia](https://mlsanity.com/paper/2603.19931/) (2026)
- [MetaHOPE: A Metaphor-Oriented Evaluation Framework for Analysing MT and LLM Translation Errors](https://mlsanity.com/paper/2607.00848/) (2026)
- [Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages](https://mlsanity.com/paper/2505.21937/) (2025)
- [Evaluating the Impact of Verbal Multiword Expressions on Machine Translation](https://mlsanity.com/paper/2508.17458/) (2025)
- [Exploring and Mitigating Fawning Hallucinations in Large Language Models](https://mlsanity.com/paper/2509.00869/) (2025)
- [A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality](https://mlsanity.com/paper/2601.06307/) (2026)
- [MasalBench: A Benchmark for Contextual and Cross-Cultural Understanding of Persian Proverbs in LLMs](https://mlsanity.com/paper/2601.22050/) (2026)
- [SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speech](https://mlsanity.com/paper/2602.09866/) (2026)
- [Last Translation Benchmark](https://mlsanity.com/paper/2609.04173/) (2026)
- [Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation](https://mlsanity.com/paper/2510.00829/) (2025)
- [ItinBench: Benchmarking Planning Across Multiple Cognitive Dimensions with Large Language Models](https://mlsanity.com/paper/2603.19515/) (2026)
- [SiNFluD: Creating and Evaluating Figurative Language Dataset for Sindhi](https://mlsanity.com/paper/2605.01323/) (2026)
- [G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment](https://mlsanity.com/paper/2606.18989/) (2026)
- [Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark](https://mlsanity.com/paper/2608.04670/) (2026)
- [LLMs Get Smarter from Targeted Synthetic Multilingual Data](https://mlsanity.com/paper/2608.15964/) (2026)

## Abstract (arXiv)

For large language models (LLMs) like NLLB and GPT, translating idioms remains a challenge. Our goal is to enhance translation fidelity by improving LLM processing of idiomatic language while preserving the original linguistic style. This has a significant social impact, as it preserves cultural nuances and ensures translated texts retain their intent and emotional resonance, fostering better cross-cultural communication. Previous work has utilized knowledge bases like IdiomKB by providing the LLM with the meaning of an idiom to use in translation. Although this method yielded better results than a direct translation, it is still limited in its ability to preserve idiomatic writing style across languages. In this research, we expand upon the knowledge base to find corresponding idioms in the target language. Our research performs translations using two methods: The first method employs the SentenceTransformers model to semantically generate cosine similarity scores between the meanings of the original and target language idioms, selecting the best idiom (Cosine Similarity method). The second method uses an LLM to find a corresponding idiom in the target language for use in the translation (LLM-generated idiom method). As a baseline, we performed a direct translation without providing additional information. Human evaluations on the English -> Chinese, and Chinese -> English show the Cosine Similarity Lookup method out-performed others in all GPT4o translations. To further build upon IdiomKB, we developed a low-resource Urdu dataset containing Urdu idioms and their translations. Despite dataset limitations, the Cosine Similarity Lookup method shows promise, potentially overcoming language barriers and enabling the exploration of diverse literary works in Chinese and Urdu.(LoResLM @ COLING Preprint)