The paper investigates a parametric approach to knowledge graph memory by compiling each entity into a LoRA adapter, enabling zero‑cost query-time retrieval via weight injection. On the MetaQA dataset, these adapters encode context‑free factual knowledge, improving exact‑match scores by up to +0.243 over a base model and achieving an oracle gap of +0.283. However, the stored knowledge is not recoverable through similarity or embedding‑based methods, indicating that knowledge is stored locally and does not transfer across semantically neighboring entities.
By Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov, Volker Tresp
arXiv:2607. 10034v1 Announce Type: new Abstract: Large language models (LLMs) store factual knowledge in their parameters.
By Roberto Garcia, Jerry Liu, Ronny Junkins, Sabri Eyuboglu, Atri Rudra, Christopher R\'e
arXiv:2607. 10248v1 Announce Type: cross Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical.
By Oliver Steele, Jiangtao Wen, Yuxing Han
arXiv:2602. 02834v4 Announce Type: replace-cross Abstract: What structural inductive bias helps transformers reason over knowledge graphs?
By Jonas Petersen, Camilla Mazzoleni, Gian-Alessandro Lombardi, Federico Martelli, Riccardo Maggioni
The paper investigates how the choice of graph tokenization affects transformer expressivity. It analyzes three tokenization families—spectral, random‑walk, and adjacency—showing that each induces different depth requirements and that some tokenizations are inherently lossy or ill‑conditioned for certain tasks. The authors prove lower bounds and impossibility results for converting between tokenizations and validate these findings with experiments on synthetic and real‑world data.
By Maya Bechler-Speicher, Gilad Yehudai, Gil Harari, Clayton Sanford, Amir Globerson, Joan Bruna
arXiv:2609.24209v1 Announce Type: new
Abstract: The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent wor...
By Chenming Shang, Yujin Tang, Jun Jie Ou Yang, Ruize Xu, Adam Breuer, Nikhil Singh
arXiv:2606. 27967v1 Announce Type: new Abstract: Real-world knowledge graphs are often incomplete, lacking many valid facts.
By Yike Liu, Peijia Xie, Chao He, Huiling Zhu
The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent work finds only weak pointwise similarity between mo...
arXiv:2506.05626v3 Announce Type: replace
Abstract: Real-world knowledge can take various forms, including structured, semi-structured, and unstructured data. Among these, Knowledge Graphs (KGs) are...
By Xiaohua Lu, Liubov Tupikina, Mehwish Alam
arXiv:2607. 17570v1 Announce Type: new Abstract: Graph foundation models (GFMs) with global attention are increasingly used to represent mixed-integer linear programs (MILPs), aiming to capture structure beyond the locality of standard graph neural networks.
By Md Abrar Jahin, Craig A. Knoblock, Jay Pujara
arXiv:2608. 08118v1 Announce Type: new Abstract: There are several methods for searching for graphs with prescribed properties, such as SAT solvers and specialized generators.
By David Seka, Stefan Szeider
arXiv:2606. 18520v1 Announce Type: cross Abstract: Computing geometric representations of data is a cornerstone of modern machine learning, typically achieved by training dual encoders which map queries and documents into a shared embedding space.
By Prashant Gokhale, Piotr Indyk, Yuhao Liu, Sandeep Silwal, Tony Chang Wang, Haike Xu