SubmissionNumber#=%=#2
FinalPaperTitle#=%=#The Architecture Was Doing the Work: Why NLI Debiasing Results Do Not Generalise
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Prabhjot Singh
JobTitle#==#
Organization#==#The University of Texas at Austin
Abstract#==#NLI debiasing research evaluates interventions on single architectures and datasets, leaving a critical assumption untested: do improvements reflect method quality or model capacity? We run 44 controlled experiments: eleven debiasing strategies across two architecturally distinct models (ELECTRA-small, RoBERTa-base) and two corpora (SNLI, MNLI), under identical conditions with Wilson 95% confidence intervals throughout. On ELECTRA-small, which achieves 87.4% in-domain accuracy, debiasing fails completely: all ten debiasing interventions fall within the baseline confidence interval on HANS (CoV = 0.75%). On RoBERTa-base, methods show genuine sensitivity (CoV = 10.76%, approximately 14x higher), yet the median intervention trends toward degrading OOD accuracy on SNLI, short of conventional significance (Wilcoxon p = 0.065), and method rankings across corpora are anti-correlated for ELECTRA (Spearman ρ = -0.42) but stable for RoBERTa (ρ = 0.75). Contrastive augmentation swings 5.6 pp across corpora (+3.59 pp MNLI, -2.02 pp SNLI). The positive robustness-accuracy correlation on RoBERTa (r = 0.848) inverts the assumed tradeoff: methods that improve HANS also preserve in-domain accuracy, while aggressive debiasers collapse both. The ELECTRA failure is not a pipeline artefact; the same codebase produces real gains on RoBERTa. It is a capacity failure: debiasing presupposes representational capacity that small architectures lack, a precondition the literature neither states nor tests.
Author{1}{Firstname}#=%=#Prabhjot
Author{1}{Lastname}#=%=#Singh
Author{1}{Username}#=%=#prabhjotschugh
Author{1}{Orcid}#=%=#
Author{1}{Email}#=%=#prabhjotchugh0805@gmail.com
Author{1}{Affiliation}#=%=#University of Texas at Austin

==========
èéáğö