Summary of Large Language Models “ad Referendum”: How Good Are They at Machine Translation in the Legal Domain?, by Vicent Briva-iglesias et al.
Large Language Models “Ad Referendum”: How Good Are They at Machine Translation in the Legal Domain?
by Vicent Briva-Iglesias, Joao Lucas Cavalheiro Camargo, Gokhan Dogru
First submitted to arxiv on: 12 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper evaluates the machine translation quality of two large language models (LLMs) against a traditional neural machine translation system across four language pairs in the legal domain. It combines automatic evaluation metrics and human evaluation by professional translators to assess translation ranking, fluency, and adequacy. The results show that while Google Translate generally outperforms LLMs in automatic evaluation metrics, human evaluators rate LLMs, especially GPT-4, comparably or slightly better in terms of producing contextually adequate and fluent translations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper compares the machine translation quality of two big language models with a traditional method across four languages for legal texts. It uses special tools to check the translations automatically and also asks professional translators what they think. The results show that one model, GPT-4, is really good at translating legal texts in a way that makes sense. |
Keywords
* Artificial intelligence * Gpt * Translation
