Hallucinations Undermine Trust; Metacognition is a Way Forward

View PDF HTML (experimental) Abstract:Despite significant strides in factual reliability, errors -- often termed hallucinations -- remain a major concern for generative AI, especially as LLMs are increasingly expected to be helpful in more complex or nuanced setups. Yet even in the simplest setting -- factoid question-answering with clear ground truth-frontier models without external tools continue to hallucinate. We argue that most factuality gains in this domain have come from expanding the model's knowledge boundary (encoding more facts) rather than improving awareness of that boundary (distinguishing known from unknown). We conjecture that the latter is inherently difficult: models may lack the discriminative power to perfectly separate truths from errors, creating an unavoidable tradeoff between eliminating hallucinations and preserving utility. This tradeoff dissolves under a different framing. If we understand hallucinations as confident errors -- incorrect information delivered without appropriate qualification -- a third path emerges beyond the answer-or-abstain dichotomy: expressing uncertainty. We propose faithful uncertainty: aligning linguistic uncertainty with intrinsic uncertainty. This is one facet of metacognition -- the ability to be aware of one's own uncertainty and to act on it. For direct interaction, acting on uncertainty means communicating it honestly; for agentic systems, it becomes the control layer governing when to search and what to trust. Metacognition is thus essential for LLMs to be both trustworthy and capable; we conclude by highlighting open problems for progress towards this objective. Comments: To appear in ICML 2026 (Position Track)

Subjects: Computation and Language (cs.CL) Cite as: arXiv:2605.01428 [cs.CL]   (or arXiv:2605.01428v1 [cs.CL] for this version)   https://doi.org/10.48550/arXiv.2605.01428 arXiv-issued DOI via DataCite (pending registration) Submission history From: Gal Yona [view email] [v1] Sat, 2 May 2026 12:59:14 UTC (680 KB)