Incoherent by Design? On the Moral Self-Consistency of LLMs
Quick summary
arXiv:2608.15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A model that can state a moral principle may still violate it when the same scenario is rephrased or reframed. This inconsistency is a problem for any system whose outputs are used to inform moral decisions. If generative systems exhibit internal inconsistency, then the epistemic integrity of AI-mediated systems becomes uncertain. To study this concern, we investigate the stability of moral reasoning in
Key takeaways
- arXiv:2608.15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations.
- A model that can state a moral principle may still violate it when the same scenario is rephrased or reframed.
- This inconsistency is a problem for any system whose outputs are used to inform moral decisions.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments