Humans outperform large language models (LLMs) on sophisticated tasks because human cognition involves a range of cognitive functions and their dynamic interactions. This study explores how integrating human cognition through concept-guided instruction and few-shot teaching in the prompt can guide LLMs to improve translation outcomes. We first demonstrate that for simple and widely used concepts, concept-guided prompting approaches offer significant benefits. We then test prompt engineering with Chinese-to-English translation examples, using hypothetical spaces—generated by GPT4—to estimate the complexity of various concepts and Likert scores—generated by human experts—to evaluate the translation performance. Our findings show that LLM translation performance declines as concept complexity increases. We also identify additional challenges: LLMs struggle with continuity in explaining and practicing sophisticated concepts due to the lack of human-like cognitive functions, such as cognitive dissonance. Additionally, LLMs lack a graceful speed-accuracy tradeoff because they do not possess the dynamic information processing, response strategies, and performance assessment that humans do. However, LLMs can mitigate some of these challenges by using Chain-of-Thought (CoT) reasoning, which is especially effective for problems requiring consistent, well-structured reasoning steps. Despite this, LLMs can only represent the effects of complex human cognitive functions through (often) fragmented linguistic descriptions, whereas humans excel at understanding critical and broader contexts and the interconnections between cognitive aspects.

Idioms exhibit varying degrees of semantic transparency, making their translation challenging. Cross-language differences in idiom usage and connotations add complexity. Using a large language modeling (LLM) approach, we automate Chinese-to-English idiom translation in three steps: (1) Semantic analysis of Chinese idioms using ontology or FrameNet to identify key concepts/relationships like action, purpose, outcome, and context. (2) Generation of multi-word English expressions reflecting these concepts. (3) Selection of the top English idiom candidate that closely matches the Chinese idiom’s meaning. Applied to examples like ‘破釜沉舟’, ‘刀山火海’, and ‘抛砖引玉’, our method performs on par with human experts. The semantic reasoning approach enhances transparency in LLM decisions, simulating logical inferences over the semantic framework.

This presentation explores the use of Prompt-Tuning (PT) to improve brand and language consistency in localization by teaching Large Language Models (LLMs) to develop and apply style guides from minimal examples. PT allows for the automatic enforcement of style guides for specific projects, potentially enhancing translation quality across varied tasks. Our approach involves defining key style guide components such as domain, audience, and formatting standards for acronyms, dates, and measurements, and creating prompts that instruct LLMs to extract and apply these standards in new translation tasks. We conducted extensive tests to evaluate the effectiveness of PT, documenting the process to ensure replicability. The expected results include improved consistency and translation performance, advancing the use of AI in localization and setting a foundation for future innovation in the field.

Translation has been modeled as a multiple-phase process where pre-editing analyses guide meaning transfer and interlingual restructure. Present-day machine translation (MT) tools provide no means for source text analyses. Generative AI with Large language modeling (LLM), equipped with prompt engineering and fine-tuning capabilities, can enable augmented MT solutions by explicitly including AI or human generated analyses/instruction, and/or human-generated reference translation as pre-editing or interactive inputs. Using an English-to-Chinese translation piece that had been carefully studied during a translator slam event, Four types of translation outputs on 20 text segments were evaluated: human-generated translation, Google Translate MT, instruction-augmented MT using GPT4-LLM, and Human-Machine-Teaming (HMT)-augmented translation based on both human reference translation and instruction using GPT4-LLM. While human translation had the best performance, both augmented MT approaches performed better than un-augmented MT. The HMT-augmented MT performed better than instruction-augmented MT because it combined the guidance and knowledge provided by both human reference translation and style instruction. However, since it is unrealistic to generate sentence-by-sentence human translation as MT input, better approaches to HMT-augmented MT need to be invented. The evaluation showed that generative AI with LLM can enable new MT workflow facilitating pre-editing analyses and interactive restructuring and achieving better performance.