Can Data Attribution Filter Out Subliminal Learning? Not Reliably
arXiv:2609.20027v1 Announce Type: new Abstract: Subliminal learning allows language models to transmit behavioral traits through training data with no obvious semantic relationship to those traits, undermining content-based data filtering as a…
Read the full story at arXiv cs.AI ↗
ImpactNotable 31/100
Why it mattersRule-based estimate: event keywords (+4); trust 6/10.
RegionsGlobal
Published1 d ago (Fri, 18 Sep 2026 04:00:00 GMT)
RetrievedFri, 18 Sep 2026 08:00:48 GMT via rss
ClassifiedFri, 18 Sep 2026 08:01:04 GMT by heuristic
AuthorMoritz Weckbecker, Sweta Jena, Jonas M\"uller, Ponnurangam Kumaraguru, Sebastian Lapuschkin, Wojciech Samek, Louis…