The Structure of Relation Decoding Linear Operators in Large Language Models

NeurIPSSpotlight2025

Authors: Miranda Anna Christ, Adrián Csiszárik, Gergely Becsó, Dániel Varga
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

This paper investigates the structure of linear operators introduced in Hernandez et al…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

large language model language model

← All NeurIPS 2025 Spotlight papers · Browse the whole archive