REVIEW 5 cited by
Prompting Large Language Model for Machine Translation: A Case Study
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
Signed reviews
read the original abstract
Research on prompting has shown excellent performance with little or even no supervised training across many tasks. However, prompting for machine translation is still under-explored in the literature. We fill this gap by offering a systematic study on prompting strategies for translation, examining various factors for prompt template and demonstration example selection. We further explore the use of monolingual data and the feasibility of cross-lingual, cross-domain, and sentence-to-document transfer learning in prompting. Extensive experiments with GLM-130B (Zeng et al., 2022) as the testbed show that 1) the number and the quality of prompt examples matter, where using suboptimal examples degenerates translation; 2) several features of prompt examples, such as semantic similarity, show significant Spearman correlation with their prompting performance; yet, none of the correlations are strong enough; 3) using pseudo parallel prompt examples constructed from monolingual data via zero-shot prompting could improve translation; and 4) improved performance is achievable by transferring knowledge from prompt examples selected in other settings. We finally provide an analysis on the model outputs and discuss several problems that prompting still suffers from.
Forward citations
Cited by 5 Pith papers
-
Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation
A learned source-feature decider routes each sentence to either an NMT model or an LLM, improving average translation quality over both single systems and a QE-based baseline while using the LLM for only about 20-30% ...
-
Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis
A two-stage framework uses LLM-generated text diagnoses plus contrastive and mask-reconstruction alignment to improve cognitive diagnosis models, with reported gains on four education datasets.
-
Evaluating Prompt Scope and Demonstration Similarity in Local LLM Machine Translation
Prompt scope and demonstration selection materially change local LLM translation quality and compliance, and dedicated MT systems still outperform them overall.
-
LLMs are Introvert
A psychology-inspired prompting method (SIP-CoT with emotion-guided memory) makes LLM agents reproduce human-like attitudes and behaviors more closely in social simulations, but the evaluation lacks error bars, a name...
-
Fine-Tuning LLMs for Low-Resource Dialect Translation: The Case of Lebanese
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.
Discussion (0). Continue with ORCID to comment.