AI translation of literary texts is "fine", but readers still prefer human translations

arXiv:2606.26040 · cs.CL · Submitted 2026-06-24 · Read on arXiv

cs.CL

Submitted: 2026-06-24

Updated: 2026-09-09

Comments: Accepted for publication in Findings of the Association for Computational Linguistics: EMNLP 2026. Longer version of the camera-ready paper, with material moved into the main text (which extends to page 15). 53 pages total, including references and appendices

Code: https://github.com/Yves575/lait

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 23× in this paper · explained in 1 episode
• Adaptation — 11× in this paper · explained in 1 episode
• Consistency — 9× in this paper · explained in 3 episodes
• Alignment — 7× in this paper · explained in 1 episode
• LLM-as-a-Judge — 5× in this paper · explained in 3 episodes
• Redundancy — 4× in this paper · explained in 2 episodes
• Annotator Agreement — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations
• Technical Report on the Pangram AI-Generated Text Classifier
• Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection
• A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering