Saved in:
Bibliographic Details
Main Authors: Todorovikj, Sara, Meyer, Lars-Peter, Martin, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.19347
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912601769771008
author Todorovikj, Sara
Meyer, Lars-Peter
Martin, Michael
author_facet Todorovikj, Sara
Meyer, Lars-Peter
Martin, Michael
contents Large Language Models (LLMs) are increasingly used for tasks involving Knowledge Graphs (KGs), whose evaluation typically focuses on accuracy and output correctness. We propose a complementary task characterization approach using three complexity frameworks from cognitive psychology. Applying this to the LLM-KG-Bench framework, we highlight value distributions, identify underrepresented demands and motivate richer interpretation and diversity for benchmark evaluation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19347
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Characterizing Knowledge Graph Tasks in LLM Benchmarks Using Cognitive Complexity Frameworks
Todorovikj, Sara
Meyer, Lars-Peter
Martin, Michael
Computation and Language
Large Language Models (LLMs) are increasingly used for tasks involving Knowledge Graphs (KGs), whose evaluation typically focuses on accuracy and output correctness. We propose a complementary task characterization approach using three complexity frameworks from cognitive psychology. Applying this to the LLM-KG-Bench framework, we highlight value distributions, identify underrepresented demands and motivate richer interpretation and diversity for benchmark evaluation tasks.
title Characterizing Knowledge Graph Tasks in LLM Benchmarks Using Cognitive Complexity Frameworks
topic Computation and Language
url https://arxiv.org/abs/2509.19347