# Translate-and-Revise: Boosting Large Language Models for Constrained Translation

arXiv: https://arxiv.org/abs/2407.13164 · HTML: https://mlsanity.com/paper/2407.13164/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 52 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 9 of 9)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Inverse Scaling: When Bigger Isn't Better](https://mlsanity.com/paper/2306.09479/) (2023)
- [SelfEvolve: A Code Evolution Framework via Large Language Models](https://mlsanity.com/paper/2306.02907/) (2023)
- [Boosted Prompt Ensembles for Large Language Models](https://mlsanity.com/paper/2304.05970/) (2023)
- [PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine](https://mlsanity.com/paper/2308.12033/) (2023)
- [SYSTRAN's Pure Neural Machine Translation Systems](https://mlsanity.com/paper/1610.05540/) (2016)
- [Automatic Post-Editing for Machine Translation](https://mlsanity.com/paper/1910.08592/) (2019)
- [Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting](https://mlsanity.com/paper/2310.05824/) (2023)

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

- [ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.15543/) (2025)
- [ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance](https://mlsanity.com/paper/2502.17057/) (2025)

## Abstract (arXiv)

Imposing constraints on machine translation systems presents a challenging issue because these systems are not trained to make use of constraints in generating adequate, fluent translations. In this paper, we leverage the capabilities of large language models (LLMs) for constrained translation, given that LLMs can easily adapt to this task by taking translation instructions and constraints as prompts. However, LLMs cannot always guarantee the adequacy of translation, and, in some cases, ignore the given constraints. This is in part because LLMs might be overly confident in their predictions, overriding the influence of the constraints. To overcome this overiding behaviour, we propose to add a revision process that encourages LLMs to correct the outputs by prompting them about the constraints that have not yet been met. We evaluate our approach on four constrained translation tasks, encompassing both lexical and structural constraints in multiple constraint domains. Experiments show 15% improvement in constraint-based translation accuracy over standard LLMs and the approach also significantly outperforms neural machine translation (NMT) state-of-the-art methods.