Chapter 7 · 2025
Cognitive Reasoning in Translation: Evaluating Chain-of-Thought, Explaining, Metacognition, and Critique in Humans and General-Purpose vs. Advanced-Reasoning Large Language Models
Herman Cappelen, Josh Dever
Abstract
This chapter explores the cognitive reasoning processes involved in translation, comparing human capabilities with those of large language models (LLMs). We evaluate the effectiveness of various reasoning paradigms, including Chain-of-Thought (CoT), explaining, metacognition, and critique, in both human translators and different types of LLMs. Our analysis focuses on understanding how these approaches contribute to accuracy, fluency, and the overall quality of translated output, particularly in complex and nuanced linguistic tasks.
Topics
cognitive reasoningtranslationchain-of-thoughtmetacognitionLLM evaluation
Relevance Scores
Long-Horizon Score65
Enterprise Score60
Completeness75
Paper Info
Year2025
Venue
Type
ChapterCh. 7
Authors2
Zone III Analysis
Related Papers
LLM-as-a-Judge: Large Language Models as Evaluators
2023 · Ch.5
Auditing Large Language Models: A Three-Layer Approach
2023 · Ch.3
Attention Is All You Need
2017 · Ch.7
Emergent Abilities of Large Language Models
2022 · Ch.7
View all Chapter 7 papers →