Pith. sign in

REVIEW 9 cited by

Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2302.07856 v1 pith:TZCEUNWK submitted 2023-02-15 cs.CL cs.LG

Marjan Ghazvininejad , Hila Gonen , Luke Zettlemoyer This is my paper · ORCID
classification cs.CLcs.LG
keywords promptingwordscontroldipmtevenlanguagelargellms
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large language models (LLMs) demonstrate remarkable machine translation (MT) abilities via prompting, even though they were not explicitly trained for this task. However, even given the incredible quantities of data they are trained on, LLMs can struggle to translate inputs with rare words, which are common in low resource or domain transfer scenarios. We show that LLM prompting can provide an effective solution for rare words as well, by using prior knowledge from bilingual dictionaries to provide control hints in the prompts. We propose a novel method, DiPMT, that provides a set of possible translations for a subset of the input words, thereby enabling fine-grained phrase-level prompted control of the LLM. Extensive experiments show that DiPMT outperforms the baseline both in low-resource MT, as well as for out-of-domain MT. We further provide a qualitative analysis of the benefits and limitations of this approach, including the overall level of controllability that is achieved.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 25 citations worldwide. Full citation record

  1. Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations

    cs.CL 2025-05 conditional novelty 7.0 of 10

    A new genderless-to-English benchmark shows that fine-tuning mBART-50 on carefully curated examples cuts gender stereotyping and pronoun-reasoning errors, beating larger proprietary systems on that benchmark.

  2. Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Representing grammar rules as code functions and retrieving them rule-by-rule improves LLM translation of extremely low-resource languages, yielding up to a 13.1% chrF++ gain over full grammar book prompting.

  3. LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context

    cs.SD 2025-05 conditional novelty 6.0 of 10

    An LLM-based ASR error corrector trained on synthetic rare-word speech and given simplified phonetic context lowers WER/CER and raises rare-word recall on English and Japanese benchmarks.

  4. A Context-aware Framework for Translation-mediated Conversations

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A context-aware translation model with minimum Bayes risk decoding improves automatic translation quality in bilingual customer-support and assistant conversations.

  5. Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A survey that categorizes multilingual prompting techniques by NLP task and language family, and designates potential state-of-the-art prompting methods for each dataset.

  6. Fine-Tuning LLMs for Low-Resource Dialect Translation: The Case of Lebanese

    cs.CL 2025-04 reject novelty 5.0 of 10

    Fine-tuning on 3,000 culturally authentic Lebanese sentences appears to beat 140,000 translated sentences, but the evidence is weakened by a potentially non-independent evaluation set and conflicting FLoRes results.

  7. From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation

    cs.CL 2024-12 conditional novelty 5.0 of 10

    In a low-resource domain adaptation setup, the simplest dictionary-based word-substitution method (DALI) beats more complex pretraining and copying methods, nearly doubling ChrF, but absolute translation quality remains low.

  8. Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis

    cs.CL 2024-12 conditional novelty 4.0 of 10

    For medical translation, NLLB-200 3.3B matches or beats 7-8B open-source LLMs in most directions, and fine-tuning it is often as good as fine-tuning much larger LLMs.

  9. Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach

    cs.CL 2024-11 reject novelty 4.0 of 10

    A multi-step prompting method using keyword extraction, dictionary retrieval, and iterative self-checking yields modest and inconsistent BLEU gains for LLM translation.

Pith tools