Pith. sign in

REVIEW 3 cited by

Adaptive Machine Translation with Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2301.13294 v3 pith:5PTRU6DI submitted 2023-01-30 cs.CL

classification cs.CL
keywords translationespeciallyin-contextlanguagelearningmodelspairsadapt
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved significant progress in the area of domain adaptation. However, real-time adaptation remains challenging. Large-scale language models (LLMs) have recently shown interesting capabilities of in-context learning, where they learn to replicate certain input-output text generation patterns, without further fine-tuning. By feeding an LLM at inference time with a prompt that consists of a list of translation pairs, it can then simulate the domain and style characteristics. This work aims to investigate how we can utilize in-context learning to improve real-time adaptive MT. Our extensive experiments show promising results at translation time. For example, LLMs can adapt to a set of in-domain sentence pairs and/or terminology while translating a new sentence. We observe that the translation quality with few-shot in-context learning can surpass that of strong encoder-decoder MT systems, especially for high-resource languages. Moreover, we investigate whether we can combine MT from strong encoder-decoder models with fuzzy matches, which can further improve translation quality, especially for less supported languages. We conduct our experiments across five diverse language pairs, namely English-to-Arabic (EN-AR), English-to-Chinese (EN-ZH), English-to-French (EN-FR), English-to-Kinyarwanda (EN-RW), and English-to-Spanish (EN-ES).

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Preperiodic points, finiteness, and structures of semigroups of algebraic morphisms

    math.NT 2025-08 unverdicted novelty 6.0 of 10

    The paper proves finiteness and structural results for preperiodic points of algebraic morphisms, including Burnside-type and Northcott-type theorems.

  2. Quantum Graph Transformer for NLP Sentiment Classification

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A hybrid quantum-classical graph transformer for sentiment classification reports higher accuracy and better sample efficiency than a classical graph transformer on five small benchmark datasets.

  3. Demystifying ChatGPT: How It Masters Genre Recognition

    cs.CL 2025-07 reject novelty 3.0 of 10

    A benchmark reports that ChatGPT outperforms other LLMs and traditional classifiers on multi-label movie genre prediction, but the result is undermined by likely pretraining contamination and weak baselines.

Pith tools