Saved in:
Bibliographic Details
Main Authors: Klein, Jan-Felix, Ohnemus, Lars
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.18063
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911168857112576
author Klein, Jan-Felix
Ohnemus, Lars
author_facet Klein, Jan-Felix
Ohnemus, Lars
contents Large Language Models (LLMs) show strong reasoning abilities but rely on internalized knowledge that is often insufficient, outdated, or incorrect when trying to answer a question that requires specific domain knowledge. Knowledge Graphs (KGs) provide structured external knowledge, yet their complexity and multi-hop reasoning requirements make integration challenging. We present ARK-V1, a simple KG-agent that iteratively explores graphs to answer natural language queries. We evaluate several not fine-tuned state-of-the art LLMs as backbones for ARK-V1 on the CoLoTa dataset, which requires both KG-based and commonsense reasoning over long-tail entities. ARK-V1 achieves substantially higher conditional accuracies than Chain-of-Thought baselines, and larger backbone models show a clear trend toward better coverage, correctness, and stability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18063
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning
Klein, Jan-Felix
Ohnemus, Lars
Computation and Language
Large Language Models (LLMs) show strong reasoning abilities but rely on internalized knowledge that is often insufficient, outdated, or incorrect when trying to answer a question that requires specific domain knowledge. Knowledge Graphs (KGs) provide structured external knowledge, yet their complexity and multi-hop reasoning requirements make integration challenging. We present ARK-V1, a simple KG-agent that iteratively explores graphs to answer natural language queries. We evaluate several not fine-tuned state-of-the art LLMs as backbones for ARK-V1 on the CoLoTa dataset, which requires both KG-based and commonsense reasoning over long-tail entities. ARK-V1 achieves substantially higher conditional accuracies than Chain-of-Thought baselines, and larger backbone models show a clear trend toward better coverage, correctness, and stability.
title ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning
topic Computation and Language
url https://arxiv.org/abs/2509.18063