Saved in:
Bibliographic Details
Main Authors: Dwivedi, Satyam, Ghosh, Sanjukta, Dwivedi, Shivam, Kumari, Nishi, Thakur, Anil, Purushottam, Anurag, Alok, Deepak, Gatla, Praveen, B, Manjuprasad, Patgiri, Bipasha
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.06446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918325800402944
author Dwivedi, Satyam
Ghosh, Sanjukta
Dwivedi, Shivam
Kumari, Nishi
Thakur, Anil
Purushottam, Anurag
Alok, Deepak
Gatla, Praveen
B, Manjuprasad
Patgiri, Bipasha
author_facet Dwivedi, Satyam
Ghosh, Sanjukta
Dwivedi, Shivam
Kumari, Nishi
Thakur, Anil
Purushottam, Anurag
Alok, Deepak
Gatla, Praveen
B, Manjuprasad
Patgiri, Bipasha
contents Large Language Models (LLMs) perform well on many reasoning benchmarks, yet existing evaluations rarely assess their ability to distinguish between meaningful semantic relations and genuine unrelatedness. We introduce CORE (Comprehensive Ontological Relation Evaluation), a dataset of 225K multiple-choice questions spanning 74 disciplines, together with a general-domain open-source benchmark of 203 rigorously validated questions (Cohen's Kappa = 1.0) covering 24 semantic relation types with equal representation of unrelated pairs. A human baseline from 1,000+ participants achieves 92.6% accuracy (95.1% on unrelated pairs). In contrast, 29 state-of-the-art LLMs achieve 48.25-70.9% overall accuracy, with near-ceiling performance on related pairs (86.5-100%) but severe degradation on unrelated pairs (0-41.35%), despite assigning similar confidence (92-94%). Expected Calibration Error increases 2-4x on unrelated pairs, and a mean semantic collapse rate of 37.6% indicates systematic generation of spurious relations. On the CORE 225K MCQs dataset, accuracy further drops to approximately 2%, highlighting substantial challenges in domain-specific semantic reasoning. We identify unrelatedness reasoning as a critical, under-evaluated frontier for LLM evaluation and safety.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06446
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CORE: Comprehensive Ontological Relation Evaluation for Large Language Models
Dwivedi, Satyam
Ghosh, Sanjukta
Dwivedi, Shivam
Kumari, Nishi
Thakur, Anil
Purushottam, Anurag
Alok, Deepak
Gatla, Praveen
B, Manjuprasad
Patgiri, Bipasha
Computation and Language
Artificial Intelligence
Machine Learning
Large Language Models (LLMs) perform well on many reasoning benchmarks, yet existing evaluations rarely assess their ability to distinguish between meaningful semantic relations and genuine unrelatedness. We introduce CORE (Comprehensive Ontological Relation Evaluation), a dataset of 225K multiple-choice questions spanning 74 disciplines, together with a general-domain open-source benchmark of 203 rigorously validated questions (Cohen's Kappa = 1.0) covering 24 semantic relation types with equal representation of unrelated pairs. A human baseline from 1,000+ participants achieves 92.6% accuracy (95.1% on unrelated pairs). In contrast, 29 state-of-the-art LLMs achieve 48.25-70.9% overall accuracy, with near-ceiling performance on related pairs (86.5-100%) but severe degradation on unrelated pairs (0-41.35%), despite assigning similar confidence (92-94%). Expected Calibration Error increases 2-4x on unrelated pairs, and a mean semantic collapse rate of 37.6% indicates systematic generation of spurious relations. On the CORE 225K MCQs dataset, accuracy further drops to approximately 2%, highlighting substantial challenges in domain-specific semantic reasoning. We identify unrelatedness reasoning as a critical, under-evaluated frontier for LLM evaluation and safety.
title CORE: Comprehensive Ontological Relation Evaluation for Large Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.06446