REVIEW 7 cited by
From LLM to NMT: Advancing Low-Resource Machine Translation with Claude
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
read the original abstract
We show that Claude 3 Opus, a large language model (LLM) released by Anthropic in March 2024, exhibits stronger machine translation competence than other LLMs. Though we find evidence of data contamination with Claude on FLORES-200, we curate new benchmarks that corroborate the effectiveness of Claude for low-resource machine translation into English. We find that Claude has remarkable \textit{resource efficiency} -- the degree to which the quality of the translation model depends on a language pair's resource level. Finally, we show that advancements in LLM translation can be compressed into traditional neural machine translation (NMT) models. Using Claude to generate synthetic data, we demonstrate that knowledge distillation advances the state-of-the-art in Yoruba-English translation, meeting or surpassing strong baselines like NLLB-54B and Google Translate.
Forward citations
Cited by 7 Pith papers
-
Decoding Machine Translationese in English-Chinese News: LLMs vs. NMTs
Machine-translated English-to-Chinese news differs from original Chinese news in measurable ways, and LLM and NMT outputs can be partially but not fully distinguished by linguistic features.
-
Can Peter Pan Survive MT? A Stylometric Study of LLMs, NMTs, and HTs in Children's Literature Translation
LLM translations of Peter Pan sit stylistically closer to human translations than NMT outputs do on several child-literature features, but the prompting strategy and possible training-data overlap partly explain the c...
-
Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages
Generating several candidate translations per source sentence for knowledge distillation yields better small multilingual translators than standard single-hypothesis distillation, especially in low-resource settings.
-
Dysfluent WFST: A Framework for Zero-Shot Speech Dysfluency Transcription and Detection
A training-free WFST decoder that uses the reference text to constrain phoneme decoding reports large gains in dysfluent speech transcription and detection, though the baselines lack the same text information.
-
SHAMI-MT: A Syrian Arabic Dialect to Modern Standard Arabic Bidirectional Machine Translation System
A bidirectional MSA-Syrian Arabic translation system built by fine-tuning AraT5v2 on the Nabra corpus; only the MSA-to-Shami direction is evaluated, with a GPT-4.1 score of 4.01/5.
-
Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation
A two-stage pipeline combining human-curated Singlish examples with embedding-based LLM ranking selects GPT-4o mini for toxicity-preserving translation, reaching gold-level human scores for Chinese and Malay but not Tamil.
-
Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models
A survey of context-aware machine translation with large language models, categorizing prompting, fine-tuning, and agent-based approaches.
Discussion (0). Continue with ORCID to comment.