4 papers
Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing
Antonio Castaldo, Johanna Monti, Sheila Castilho
This paper investigates whether LLM translations exhibit identifiable emotional profiles and how post-editing reshapes them toward human-like norms. We compare LLM translations of…
Translating Under Pressure: Domain-Aware LLMs for Crisis Communication
Antonio Castaldo, Maria Carmen Staiano, Johanna Monti +2
Timely and reliable multilingual communication is critical during natural and human-induced disasters, but developing effective solutions for crisis communication is limited by the…
Data-Efficient Domain Adaptation for LLM-based MT using Contrastive Preference Optimization
Inacio Vieira, Antonio Castaldo, James O'Doherty +1
LLMs often require adaptation to domain-specific requirements, a process that can be expensive when relying solely on SFT. We present an empirical study on applying CPO to simulate…
Extending CREAMT: Leveraging Large Language Models for Literary Translation Post-Editing
Antonio Castaldo, Sheila Castilho, Joss Moorkens +1
Post-editing machine translation (MT) for creative texts, such as literature, requires balancing efficiency with the preservation of creativity and style. While neural MT systems s…