# Leveraging Domain Knowledge at Inference Time for LLM Translation: Retrieval versus Generation

arXiv: https://arxiv.org/abs/2503.05010 · HTML: https://mlsanity.com/paper/2503.05010/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [Nearest Neighbor Machine Translation](https://mlsanity.com/paper/2010.00710/) (2020)
- [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)
- [To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation](https://mlsanity.com/paper/2107.10821/) (2021)
- [Unsupervised Domain Clusters in Pretrained Language Models](https://mlsanity.com/paper/2004.02105/) (2020)
- [Prompting PaLM for Translation: Assessing Strategies and Performance](https://mlsanity.com/paper/2211.09102/) (2022)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [Bidirectional Language Models Are Also Few-shot Learners](https://mlsanity.com/paper/2209.14500/) (2022)
- [Translating Step-by-Step: Decomposing the Translation Process for Improved Translation Quality of Long-Form Texts](https://mlsanity.com/paper/2409.06790/) (2024)
- [Fast Domain Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1612.06897/) (2016)
- [Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles](https://mlsanity.com/paper/2311.02310/) (2023)

## Built on by (most cited first, 4 of 4)

- [RASST: Retrieval-Augmented Simultaneous Speech Translation](https://mlsanity.com/paper/2601.22777/) (2026)
- [Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation](https://mlsanity.com/paper/2602.05694/) (2026)
- [Worlds Within Words: Translating Culture in Ancient Chinese Texts with Multi-Agent Coordination](https://mlsanity.com/paper/2606.01276/) (2026)
- [LLMs in the Real World: Evaluating "AI" in Emergency Contexts](https://mlsanity.com/paper/2607.00019/) (2026)

## Abstract (arXiv)

While large language models (LLMs) have been increasingly adopted for machine translation (MT), their performance for specialist domains such as medicine and law remains an open challenge. Prior work has shown that LLMs can be domain-adapted at test-time by retrieving targeted few-shot demonstrations or terminologies for inclusion in the prompt. Meanwhile, for general-purpose LLM MT, recent studies have found some success in generating similarly useful domain knowledge from an LLM itself, prior to translation. Our work studies domain-adapted MT with LLMs through a careful prompting setup, finding that demonstrations consistently outperform terminology, and retrieval consistently outperforms generation. We find that generating demonstrations with weaker models can close the gap with larger model's zero-shot performance. Given the effectiveness of demonstrations, we perform detailed analyses to understand their value. We find that domain-specificity is particularly important, and that the popular multi-domain benchmark is testing adaptation to a particular writing style more so than to a specific domain.