AI ethics evidence index Search
Source-linked daily record
Evidence record 5485 · automatically gathered

Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models

Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain limited. Prior diagnostics rely on highly toxic and clearly harmful scenarios, causing most models to refuse immediately. As a result, models never deliberate over developer policy, monitoring conditions, or the consequences of non-compliance, making these diagnost

Record details

Published: 22 April 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment · Healthcare
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Regulation · Shared topic: Safety & alignment

Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents

arXiv · 21 April 2026

Shared topic: Regulation · Shared topic: Safety & alignment

Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents

arXiv · 28 April 2026

Shared topic: Regulation · Shared topic: Safety & alignment

A Proposed Biomedical Data Policy Framework to Reduce Fragmentation, Improve Quality, and Incentivize Sharing in Indian Healthcare in the era of Artificial Intelligence and Digital Health

arXiv · 13 April 2026

Shared topic: Regulation · Shared topic: Safety & alignment

AI Integrity: A New Paradigm for Verifiable AI Governance

arXiv · 13 April 2026

Shared topic: Regulation · Shared topic: Safety & alignment

Physiological and Semantic Patterns in Medical Teams Using an Intelligent Tutoring System

arXiv · 31 March 2026

Shared topic: Regulation · Shared topic: Safety & alignment

Behavioural feasible set: Value alignment constraints on AI decision support

arXiv · 22 March 2026

How to cite this record

ethics.ai (22 April 2026), “Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models,” evidence record 5485, https://ethics.ai/record/5485 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.