Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists

arXiv cs.AIAugust 15, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2608.12345v1 Announce Type: new Abstract: Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasured. We introduce IntegrityBench, a benchmark evaluating misconduct classification, ethical action reasoning and artifact-grounded decision making across 36 paired tasks under a 5-level implicit-explicit pressure protocol spanning 3 domains and 4 research stages. Evaluating 18 frontier model variants, we find that under peak pressure, models fail roughly 1 in 3 integrity-critical decisions, and neither scale nor reasoning ability reliably mitigates this. Explicit pressures induce compliance with

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning