4 papers
Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA
Raphael Schumann, Stefan Riezler
Reasoning quality in large language models depends not only on producing correct answers but also on generating valid intermediate steps. We study this through multiple-choice ques…
Learning to Translate Ambiguous Terminology by Preference Optimization on Post-Edits
Nathaniel Berger, Johannes Eschbach-Dymanus, Miriam Exel +2
In real world translation scenarios, terminology is rarely one-to-one. Instead, multiple valid translations may appear in a terminology dictionary, but correctness of a translation…
Post-edits Are Preferences Too
Nathaniel Berger, Miriam Exel, Matthias Huck +1
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…
Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation
Nathaniel Berger, Stefan Riezler, Miriam Exel +1
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, p…