# Prompting LLMs: Length Control for Isometric Machine Translation

arXiv: https://arxiv.org/abs/2506.04855 · HTML: https://mlsanity.com/paper/2506.04855/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 5 Jun 2025.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [Prompting PaLM for Translation: Assessing Strategies and Performance](https://mlsanity.com/paper/2211.09102/) (2022)
- [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023)
- [Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability](https://mlsanity.com/paper/2305.10266/) (2023)
- [Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM](https://mlsanity.com/paper/2303.01911/) (2023)
- [Positional Encoding to Control Output Sequence Length](https://mlsanity.com/paper/1904.07418/) (2019)
- [Controlling the Output Length of Neural Machine Translation](https://mlsanity.com/paper/1910.10408/) (2019)
- [From Speech-to-Speech Translation to Automatic Dubbing](https://mlsanity.com/paper/2001.06785/) (2020)
- [Is 42 the Answer to Everything in Subtitling-oriented Speech Translation?](https://mlsanity.com/paper/2006.01080/) (2020)
- [Machine Translation Verbosity Control for Automatic Dubbing](https://mlsanity.com/paper/2110.03847/) (2021)
- [Isometric MT: Neural Machine Translation for Automatic Dubbing](https://mlsanity.com/paper/2112.08682/) (2021)
- [Isochrony-Aware Neural Machine Translation for Automatic Dubbing](https://mlsanity.com/paper/2112.08548/) (2021)
- [Explicit Sentence Compression for Neural Machine Translation](https://mlsanity.com/paper/1912.11980/) (2019)
- [Machine Translation with Unsupervised Length-Constraints](https://mlsanity.com/paper/2004.03176/) (2020)
- [AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task](https://mlsanity.com/paper/2205.05807/) (2022)

## Built on by (most cited first, 2 of 2)

- [Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs](https://mlsanity.com/paper/2508.13805/) (2025)
- [HOMURA: Taming the Sand-Glass for Time-Constrained LLM Translation via Reinforcement Learning](https://mlsanity.com/paper/2601.10187/) (2026)

## Abstract (arXiv)

In this study, we explore the effectiveness of isometric machine translation across multiple language pairs (En→De, En→Fr, and En→Es) under the conditions of the IWSLT Isometric Shared Task 2022. Using eight open-source large language models (LLMs) of varying sizes, we investigate how different prompting strategies, varying numbers of few-shot examples, and demonstration selection influence translation quality and length control. We discover that the phrasing of instructions, when aligned with the properties of the provided demonstrations, plays a crucial role in controlling the output length. Our experiments show that LLMs tend to produce shorter translations only when presented with extreme examples, while isometric demonstrations often lead to the models disregarding length constraints. While few-shot prompting generally enhances translation quality, further improvements are marginal across 5, 10, and 20-shot settings. Finally, considering multiple outputs allows to notably improve overall tradeoff between the length and quality, yielding state-of-the-art performance for some language pairs.