PaperScope
LIVE · 2026-09-09 05:40 UTC

The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs

Eric So

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.07731 v1
Category
Submitted
2026-09-07

Abstract

We show that ordinary business language --- "maximize profitability" --- induces profit-oriented ambiguity resolution: LLMs systematically dismiss ambiguous signals of potential safety violations to serve business objectives. In 3,600 controlled trials across eight reasoning-capable LLMs, adding a profit mandate to otherwise identical prompts increases risk-dismissing judgments by 6.8 percentage points (p < 0.0001), suppresses board escalation recommendations by 13.9pp (p < 0.0001), and shifts severity assessments downward (p < 0.0001). The mandate never instructs models to downplay risks; instead, chain-of-thought traces reveal motivated reasoning: models acknowledge concerns, then invoke profit logic to justify dismissing them. We characterize these findings as the Profit Alignment Problem: when AI systems are given ordinary business objectives, they develop systematic strategies for suppressing inconvenient information that no designer intended or specified.

arXiv abs page · PDF · same-day batch