Abstract:Local XAI audits compare a finite block of learned vectors with a weak side signal. Baselines such as nearest-neighbor lookup, low-rank coordinate models, and relation factorization expose different parts of this audit. We introduce Relational Semantic Decomposition, abbreviated as RSD, as a local triangulation audit for learned vector blocks. Given coordinates X and a declared bounded weak affinity proxy A, RSD fits simplex memberships S and coordinate poles C. It reuses S in a relation decoder for A and reports the coordinate residual R=X-SC. This yields a scoped audit unit: compatibility for the chosen block, proxy, decoder class, and loss budget, plus component mass and residual readouts. Synthetic controls check simplex reconstruction, proxy decoding, and fixed-S residual decomposition. The theorem-statement, month, and dog/wolf blocks illustrate why low proxy loss should be read with component mass, residual readouts, and block size.
| Comments: | 8 pages, 1 figure. Revised version with clarified scope, experiments, and limitations |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.17482 [cs.CL] |
| (or arXiv:2605.17482v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.17482 arXiv-issued DOI via DataCite |
From: Seungmin Jin [view email]
[v1]
Sun, 17 May 2026 14:44:13 UTC (90 KB)
[v2]
Tue, 26 May 2026 17:55:28 UTC (59 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。