Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation
While large language models (LLMs) pre-trained on massive amounts of unpaired language
data have reached the state-of-the-art in machine translation (MT) of general domain texts …
data have reached the state-of-the-art in machine translation (MT) of general domain texts …
Post-edits Are Preferences Too
Preference Optimization (PO) techniques are currently one of the state of the art techniques
for fine-tuning large language models (LLMs) on pairwise preference feedback from human …
for fine-tuning large language models (LLMs) on pairwise preference feedback from human …