Paper

Can In-Context Learning Support Intrinsic Curiosity?

Unreadunread

AI summary

arXiv:2606. 19476v1 Announce Type: new Abstract: Effective machine learning depends not only on how we model data, but also on what data we choose to collect.

Reading status

Priority

About this paper

Authors: Eric Elmoznino, Sangnie Bhardwaj, Johannes von Oswald, Rajai Nasser, Blaise Ag\"uera y Arcas, Jo\~ao Sacramento, Rif A. Saurous, Guillaume Lajoie
Released: 2026-06-19 (20d ago)
Topic: Related to current project
Relation to my work: Read next because Can In-Context Learning Support Intrinsic Curiosity? 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, class, eval, rate, implement, control, full, trained. Source: arxiv cs.LG (Machine Learning).
arXiv: 2606.19476

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Can In-Context Learning Support Intrinsic Curiosity?. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.