Skip to content
Open access

A Study on Prompt Engineering Strategies and Context-Enhanced Translation for Video Game Localization

Jul 2026 · Applied and Computational Engineering · Vol 231, pp. 133-145 · 0 citations

TL;DR

This study proposes a context-enhanced prompt-based translation framework for game localization that builds a local semantic knowledge base, retrieves relevant background information through contextual embeddings and cosine similarity, and inserts the retrieved context into structured translation prompts.

Abstract

Video game localization often depends on contextual understanding rather than sentence-level translation alone. This problem is especially evident in fragmented narrative games such as Elden Ring, where information about characters, places, factions, terminology, and world-building is scattered across item descriptions, equipment texts, skill explanations, and other isolated entries. When these entries are translated without sufficient background information, large language models may produce inconsistent terms, weakened narrative references, inaccurate interpretation of polysemous expressions, or a style that does not match the original atmosphere. To address this problem, this study proposes a context-enhanced prompt-based translation framework for game localization. The framework builds a local semantic knowledge base, retrieves relevant background information through contextual embeddings and cosine similarity, and inserts the retrieved context into structured translation prompts. Using Elden Ring item descriptions as the test corpus, this study compares Doubao, Gemini, and GPT-5.5 under four settings: baseline translation, prompt engineering, context enhancement, and the full method. The evaluation uses BERTScore F1, character-level BLEU-4, and the Global Terminology Enrichment Score (GTES). The results show that context retrieval is more effective than prompt engineering alone in improving domain terminology recall, and the full method achieves the strongest overall performance. This suggests that external knowledge retrieval can help reduce contextual loss in fragmented game text translation.

Read PDF

Similar papers

Jul 2026

Machine and AI translation for English-to-Korean game translation

This study examines the performance of various machine translation (MT) systems and a generative AI (GenAI) translation in the context of game text translation using data from the popular racing game Need for Speed: Unbound ( Criterion Games 2022 ). Focusing on factors such as ambiguity, contextual disambiguation, stylistic variations, domain specific knowledge, and technical entities (e.g. placeholders), the analysis compares human translations with outputs from Google Translate, DeepL, Papago, and ChatGPT. Three representative examples from a game script are examined, revealing that while MT and GenAI systems can preserve lexical content, they often fail to capture critical nuances and contextual meanings that are crucial for interactive gaming environments. The findings highlight the need for integrating additional contextual information and domain-specific post-editing to improve MT and GenAI translation quality for translated game texts, contributing to the broader discussion on enhancing interactive media translation.

J. Y. Kim, Eunjoo Kwak, Dong-mie Kim · 0 citations
Open access Aug 2026

Strategies and Challenges in Using Multimedia to Facilitate Language Acquisition in English Teaching

In non-native English classrooms, multimedia resources often produce a cognitive gap of high input but low output: visual contexts and target-language forms fail to form stable semantic connections. To address this problem, this study proposes a three-stage multimedia teaching strategy of context anchoring, modal verification, and output transfer. First, a micro-context video library is constructed using word-vector semantic association, with target vocabulary anchoring the semantic field while 12-second clips control cognitive load. Second, a semi-structured virtual dialogue agent dynamically triggers recast and clarification feedback according to learners’ spoken output, grammar breaks, and pragmatic deviations. Third, digital narrative reconstruction tasks require learners to convert video-based semantic information into written storyboards, promoting cross-modal syntactic transfer. Experiments show that the semantic priming effect size increases to 145.2 ms, speech-flow break density decreases to 12.3, and average clause nesting depth rises to 1.89. The framework turns multimedia into a cognitive scaffold and is compatible with networked multimedia transmission, wireless interactive classrooms, and electromagnetic-safe digital learning spaces.

Juan Wu, Yingying Du, Xiaohui Zhang et al. · 0 citations
Preprint Aug 2026

NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video

NARU, a benchmark designed to evaluate Narrative evolution and Reasoning on cultural Understanding in Japanese long-form video, is introduced, a hierarchical memory-based annotation pipeline that transforms raw video into structured event, narrative, and cultural annotations, then generates questions via task-oriented synthesis and iterative shortcut removal.

Yuheng Huang, Jianlang Chen, Jiayang Song et al. · 0 citations
Conference Jul 2026

Optimizing Context Injection for Educational Chatbots through Comparative Sentence and Recursive Chunking Strategies

This research addresses the common challenge of a lack of context in Question and Answer (QA) datasets in digital education, which limits the reasoning potential of Large Language Models (LLMs). To address this, we optimize an automated retrieval-based dataset generation system that systematically enriches QA pairs with relevant pedagogical context from authoritative digital textbooks. This study conducts a comparative analysis of two major text chunking strategies: sentence chunking and recursive chunking. Although these pipelines are designed for general education applications, they are evaluated here through a case study of Indonesian elementary education materials. To ensure the highest reliability, the workflow performance is measured against a ground truth dataset of 978 entries, manually curated and validated by education experts to ensure pedagogical accuracy, and 781 entries from other subjects. Quantitative evaluation using BERTScore shows that recursive chunking achieves a superior F1 score of 0.748 compared to 0.737 for sentence chunking, with peak performance observed on upper elementary school materials (Grades 5 and 6). These findings were corroborated by the final verification phase through User Acceptance Testing (UAT) with an elementary school educator, where recursive chunking achieved a 'Relevant' score of 22 compared to 17 for sentence chunking. A key contribution of this study is the development and validation of a standardized, automated workflow by experts that effectively overcomes the barriers of manual dataset construction for domain-specific tasks, providing a semantically robust foundation for context-aware educational AI.

V. C. Mawardi, Ayu Purwarianti, B. Trilaksono et al. · 0 citations
Open access Aug 2026

Context-Aware Large Language Model for Customer Support Chatbots

The results show that the RAG architecture provides a scalable alternative for creating precise, contextually grounded conversational agents, thereby mitigating some of the main drawbacks of LLMs.

Rabia Shabbir, K. Talpur, Shakeel Ahmad · 0 citations
Review Aug 2026

When paratexts become the text

Research on video game localization is typically written through the lens of shipped software, privileging translated in-game assets and professional production pipelines. Such accounts obscure how players in linguistically marginalized markets accessed games when official localization was rare or absent. This article reconceptualizes localization by examining the enabling role of translated paratextual labor in Saudi Arabia during the late 1990s and 2000s. Drawing on an archival corpus of thirty-nine surviving issues of Majalat Alaab Alcomputar ( MAAC , 1997–2011), widely regarded as the first dedicated Arabic video game magazine, and three interviews with former staff members, the study analyzes how Arabic translations of reviews, interface explanations, glossaries, and strategy guides mediated play. The article integrates paratext theory ( Genette 1997 ; Batchelor 2018 ), co-text and multimodal orchestration ( Adami and Ramos Pinto 2020 ), and gaming capital ( Consalvo 2007 ) to argue that under restricted linguistic access, MAAC ’s paratextual constellation did not remain peripheral to the game text but could become enabling co-text that was central to play. The article further traces functional continuities between print mediation and later digital practices in Arabic forums and YouTube walkthroughs. By foregrounding paratextual practices in print and their later continuities, this study expands localization historiography beyond product-centered models and proposes an access-oriented account of how translation makes play possible in marginalized language markets.

Amer Qobti · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.