Paper

SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths

Unreadunread

AI summary

arXiv:2606. 09404v1 Announce Type: new Abstract: Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their functional form, or visualize only restricted interaction types.

Reading status

Priority

About this paper

Authors: Timo Hei{\ss}, Julia Herbinger, Bernd Bischl, Giuseppe Casalicchio
Released: 2026-06-09 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: strong, fill, under, line, control, without, alone, test. Source: arxiv stat.ML (Machine Learning).
arXiv: 2606.09404

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to SAILS: Surrogate-based Analysis of Interactions via Local Effect Smooths. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.