Applying LD-DPO to the DeepDistill-32B model improves average benchmark scores by 3.3 points, but the gains are uneven, the tables are inconsistent, and the evidence is preliminary.
Aime_1983_2024 (revision 6283828), 2025
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
-
Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study
Applying LD-DPO to the DeepDistill-32B model improves average benchmark scores by 3.3 points, but the gains are uneven, the tables are inconsistent, and the evidence is preliminary.