DPO and RLHF preference training give inconsistent gains for Icelandic legal summarization, and ROUGE scores clash with expert human evaluation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Aligning Language Models for Icelandic Legal Text Summarization
DPO and RLHF preference training give inconsistent gains for Icelandic legal summarization, and ROUGE scores clash with expert human evaluation.