Paper

idSCD: Identifying Training Datasets through Semantic Correlation Descriptors

Unreadunread

AI summary

arXiv:2605. 30462v1 Announce Type: new Abstract: Can a dataset be recognized from the spurious correlations it induces during training?

Reading status

Priority

About this paper

Authors: Andrada Gobeaja, Ionut Hodoroaga, Elena Burceanu, Marius Leordeanu
Released: 2026-06-01 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because idSCD: Identifying Training Datasets through Semantic Correlation Descriptors 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: text, word, class, under, distributional, line, rate, control. Source: arxiv cs.LG (Machine Learning).
arXiv: 2605.30462

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to idSCD: Identifying Training Datasets through Semantic Correlation Descriptors. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.