LCPO reduces average LRM output length by over 50% across benchmarks via targeted preference optimization while preserving reasoning performance.
Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
LCPO reduces average LRM output length by over 50% across benchmarks via targeted preference optimization while preserving reasoning performance.