EMNLP study: AI literary translation reads fine but varies more, even within one book
tuvllms · x · 2026-10-27
Presented at EMNLP2026: AI-translated literature into English is readable and often "fine," but human translation is valued more for clarity and immersion on closer reading. Both vary in quality — yet AI varies more, even within a single book. The work examines how quietly widespread AI literary translation shapes readers' experience of an author's work.
More from Research
- Jacobian Lens explained: a 'lie detector' for reading the mind of an LLM — huopak · 2026-10-27
- Preprint reframes enzyme function prediction as conditional generation with Fluxion — LeoTZ03 · 2026-10-27
- No bins needed: new method estimates model calibration error as a drop in risk — BlackHC · 2026-10-27
- AnyRank ranks robot policies reliably with far fewer real-robot trials — pappasg69 · 2026-10-27
- Cohere Labs releases Qwen investigation traces dataset with repro script — cohere · 2026-10-27
- OpenAI claims models helped falsify the Exponential Time Hypothesis — Environmental_Mix22 · 2026-10-27