SubmissionNumber#=%=#34
FinalPaperTitle#=%=#PEFT Gains Need Hidden Baselines: Rank and Optimizer Sweeps Change LoRA Conclusions
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Ding Wu
JobTitle#==#
Organization#==#Independent Researcher
Abstract#==#New parameter-efficient fine-tuning (PEFT) methods are often credited with gains against a single default LoRA configuration, even though inexpensive tuning of vanilla LoRA may change the comparison. We present a deliberately small, descriptive case study of two claims: adaptive rank allocation with AdaLoRA and LoRA-specific optimization with LoRA-RITE. Using RoBERTa-base on capped subsets of three GLUE classification tasks, we compare each method with a pre-specified vanilla LoRA control sweep. AdaLoRA beats fixed LoRA at rank 8 in 4 of 7 dataset-seed cells, but beats the best tested fixed rank in only 1 of 7. LoRA-RITE beats default AdamW in 3 of 6 cells, but tuned AdamW in only 1 of 6. Several SST-2 runs collapse to the majority label, so these counts are illustrative rather than population-level estimates. The practical contribution is an attribution protocol: report modest vanilla rank/learning-rate sweeps, per-cell margins, instability checks, and budget accounting before attributing gains to a specialized PEFT mechanism.
Author{1}{Firstname}#=%=#Ding
Author{1}{Lastname}#=%=#Wu
Author{1}{Username}#=%=#dingwu
Author{1}{Orcid}#=%=#
Author{1}{Email}#=%=#dingwucs@gmail.com
Author{1}{Affiliation}#=%=#Independent Researcher

==========
èéáğö