Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: De Sabbata, Stef, Baiju, Rahul, Mizzaro, Stefano, Roitero, Kevin
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.14535
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917494536536064
author De Sabbata, Stef
Baiju, Rahul
Mizzaro, Stefano
Roitero, Kevin
author_facet De Sabbata, Stef
Baiju, Rahul
Mizzaro, Stefano
Roitero, Kevin
contents The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide range of processes and analyses, given our very limited understanding of their inner workings. In this extended abstract, we examine how LLMs process relative geographic space using activation patching, an emerging tool for mechanistic interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14535
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Exploring Geographic Relative Space in Large Language Models through Activation Patching
De Sabbata, Stef
Baiju, Rahul
Mizzaro, Stefano
Roitero, Kevin
Machine Learning
The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide range of processes and analyses, given our very limited understanding of their inner workings. In this extended abstract, we examine how LLMs process relative geographic space using activation patching, an emerging tool for mechanistic interpretability.
title Exploring Geographic Relative Space in Large Language Models through Activation Patching
topic Machine Learning
url https://arxiv.org/abs/2605.14535