Combining LoRAs generally fails to compose knowledge across disjoint tasks; reliable gains appear only when the target reasoning pattern or familiar entities are present in fine-tuning data.
Building machine learning models like open source software
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness
Combining LoRAs generally fails to compose knowledge across disjoint tasks; reliable gains appear only when the target reasoning pattern or familiar entities are present in fine-tuning data.