BADIT decomposes LLM parameters into orthogonal high-singular-value LoRA experts for basic abilities and applies spherical clustering of rank-1 components to reduce cross-task interference, outperforming prior methods on the SuperNI benchmark.
DoRA: Weight-Decomposed Low-Rank Adaptation , booktitle =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
BADIT decomposes LLM parameters into orthogonal high-singular-value LoRA experts for basic abilities and applies spherical clustering of rank-1 components to reduce cross-task interference, outperforming prior methods on the SuperNI benchmark.