Quantum Brain
← Back to papers

Grounded verification of chemical and materials reasoning: detection is the bottleneck

Can Polat, Mustafa Kurban, Erchin Serpedin, Hasan Kurban·July 19, 2026
cs.LGphysics.chem-phphysics.comp-phQuantum Physics

AI Breakdown

Get a structured breakdown of this paper — what it's about, the core idea, and key takeaways for the field.

Abstract

Large language models confabulate chemical objects (molecular formulas, space groups, formation energies) in fluent reasoning traces, concentrated on long-tail entities where confidence is least trustworthy. Deterministic, database-grounded verification can catch and repair such errors without the coverage cost of blanket retrieval; the binding constraint, we find, is detection, not repair. Our tiered verifier extracts each checkable claim, checks it against authoritative databases and physics, and feeds the reference into a gated correction loop. Across four models and 528 condition-pinned prompts, gated correction cuts committed-formula error from 22% to 4% at $3.2\times$ fewer retrievals than blanket augmentation, beating a conversational oracle. Repair succeeds wherever a flag fires (80--97%); the bottleneck is in-loop detection recall. Grounding improves the final answer only when the verifier's scope reaches the deliverable (83% to 90%), and the lift appears only where extractable long-tail error exists: absent on near-ceiling physical constants, large on isotope half-lives (11% to 0%).

Related Research

Quantum Intelligence

Ask about quantum research, companies, or market developments.