Abstract:The rise of Large Language Models (LLMs) has sparked debate about whether these systems exhibit human-level cognition. In this debate, little attention has been paid to a structural component of human cognition: core beliefs, truths that provide a foundation around which we can build a worldview. These commitments usually resist debunking, as abandoning them would represent a fundamental shift in how we see reality. In this paper, we ask whether LLMs hold anything akin to core commitments. Using a probing framework we call Adversarial Dialogue Trees (ADTs) over five domains (science, history, geography, biology, and mathematics), we find that most LLMs fail to maintain a stable worldview. Though some recent models showed improved stability, they still eventually failed to maintain key commitments under conversational pressure. These results document an improvement in argumentative skills across model generations but indicate that all current models lack a key component of human-level cognition.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.03255 [cs.LG] |
| (or arXiv:2605.03255v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.03255 arXiv-issued DOI via DataCite (pending registration) |
From: Anna Sokol [view email]
[v1]
Tue, 5 May 2026 01:06:20 UTC (402 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。