SoLoPO decouples long-context preference optimization into short-context preference learning plus a reward-consistency term that transfers the behavior to long contexts.
CItruS: Chunked instruction-aware state eviction for long sequence modeling
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
-
SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
SoLoPO decouples long-context preference optimization into short-context preference learning plus a reward-consistency term that transfers the behavior to long contexts.