Paper

Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion

Unreadunread

AI summary

arXiv:2605. 24064v1 Announce Type: new Abstract: Hyper-relational knowledge graphs (HKGs) effectively represent complex facts.

Reading status

Priority

About this paper

Authors: Jaejun Lee, Seheon Kim, Joyce Jiyoung Whang
Released: 2026-05-26 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion 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, fill, rect, correct, line, contexts, model. Source: arxiv cs.LG (Machine Learning).
arXiv: 2605.24064

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.