# SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models

arXiv: https://arxiv.org/abs/2507.18902 · HTML: https://mlsanity.com/paper/2507.18902/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [In-context Examples Selection for Machine Translation](https://mlsanity.com/paper/2212.02437/) (2022)
- [Self-Edit: Fault-Aware Code Editor for Code Generation](https://mlsanity.com/paper/2305.04087/) (2023)
- [Training Neural Machine Translation To Apply Terminology Constraints](https://mlsanity.com/paper/1906.01105/) (2019)
- [CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors](https://mlsanity.com/paper/2305.05711/) (2023)
- [Code-Switching for Enhancing NMT with Pre-Specified Translation](https://mlsanity.com/paper/1904.09107/) (2019)
- [Incorporating Discrete Translation Lexicons into Neural Machine Translation](https://mlsanity.com/paper/1606.02006/) (2016)
- [Using natural language prompts for machine translation](https://mlsanity.com/paper/2202.11822/) (2022)
- [Bridging Neural Machine Translation and Bilingual Dictionaries](https://mlsanity.com/paper/1610.07272/) (2016)
- [PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation](https://mlsanity.com/paper/2208.08110/) (2022)
- [Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References](https://mlsanity.com/paper/2305.15067/) (2023)

## Abstract (arXiv)

There are more than 7,000 languages around the world, and current Large Language Models (LLMs) only support hundreds of languages. Dictionary-based prompting methods can enhance translation on them, but most methods use all the available dictionaries, which could be expensive. Instead, it will be flexible to have a trade-off between token consumption and translation performance. This paper proposes a novel task called Automatic Dictionary Selection (ADS). The goal of the task is to automatically select which dictionary to use to enhance translation. We propose a novel and effective method which we call Select Low-frequency Words! (SLoW) which selects those dictionaries that have a lower frequency. Our methods have unique advantages. First, there is no need for access to the training data for frequency estimation (which is usually unavailable). Second, it inherits the advantage of dictionary-based methods, where no additional tuning is required on LLMs. Experimental results on 100 languages from FLORES indicate that SLoW surpasses strong baselines, and it can obviously save token usage, with many languages even surpassing the translation performance of the full dictionary baseline.footnoteA shocking fact is that there is no need to use the actual training data (often unobtainable) for frequency estimation, and an estimation frequency obtained using public resources is still apparently effective in improving translation with ChatGPT and Llama, and DeepSeek.footnoteCode and data available upon publication.