Back to all available

Prompting large language models for translation quality evaluation: A systematic review of strategies, challenges, and future directions

artificial-intelligence
computational-linguistics
computer-education
data-mining-and-machine-learning

Abstract

Large-scale pre-trained language models are increasingly employed to evaluate machine translation quality, aiming to overcome the limitations of traditional metrics in capturing semantic nuance, discourse coherence, and cultural context. Despite recent advances, large language model-based evaluation systems continue to face persistent challenges in prompt formulation, scoring consistency, cross-linguistic adaptability, and interpretability. This systematic review analyzes 63 peer-reviewed studies published between 2020 and 2025, mapping the evolution of prompt-based strategies across multilingual and multi-domain translation evaluation tasks. Three core limitation are identified: lack of reproducibility, semantic misalignment, and insufficient cultural adaptability. To address these issues, this paper proposes a conceptual three-dimensional framework for prompt design, comprising semantic attribution for interpretability, cultural mapping for contextual adaptability, and prompt regularization for cross-task robustness. The proposed framework offers a foundation for constructing more transparent, generalizable, and culturally responsive evaluation systems, and supports the advancement of human–artificial intelligence collaboration in translation quality assessment and cross-cultural communication.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].