analiza aiqbench
This paper proposes an "epistemic constitution" to regulate how large language models form beliefs and express confidence, addressing the issue of source attribution bias where models penalize arguments from ideologically conflicting sources. The author argues for a "Liberal" approach that establishes procedural norms protecting collective inquiry rather than enforcing formal correctness or default independence from privileged standpoints. By defining explicit meta-norms with eight principles, this work shifts AI governance toward contestable structures similar to those expected in modern ethics frameworks.
Epistemic Constitutionalism Or: how to avoid coherence bias
arXiv:2601.14295v4 Announce Type: replace Abstract: Large language models increasingly function as artificial reasoners: they evaluate arguments, assign credibility, and express confidence. Yet their belief-forming behavior is governed by implicit, uninspected epistemic policies. This paper argues for an epistemic constitution for AI: explicit, contestable meta-norms that regulate how systems form and express beliefs. Source attribution bias provides the motivating case: I show that frontier models enforce identity-stance coherence, penalizing arguments attributed to sources whose expected ideological position conflicts with the argument's content. When models detect systematic testing, these effects collapse, revealing that systems treat source-sensitivity as bias to suppress rather than as a capacity to execute well. I distinguish two constitutional approaches: the Platonic, which mandates formal correctness and default source-independence from a privileged standpoint, and the Liberal, which refuses such privilege, specifying procedural norms that protect conditions for collective inquiry while allowing principled source-attending grounded in epistemic vigilance. I argue for the Liberal approach, sketch a constitutional core of eight principles and four orientations, and propose that AI epistemic governance requires the same explicit, contestable structure we now expect for AI ethics.
arXiv:2601.14295 (cs)
Abstract:Large language models increasingly function as artificial reasoners: they evaluate arguments, assign credibility, and express confidence. Yet their belief-forming behavior is governed by implicit, uninspected epistemic policies. This paper argues for an epistemic constitution for AI: explicit, contestable meta-norms that regulate how systems form and express beliefs. Source attribution bias provides the motivating case: I show that frontier models enforce identity-stance coherence, penalizing arguments attributed to sources whose expected ideological position conflicts with the argument's content. When models detect systematic testing, these effects collapse, revealing that systems treat source-sensitivity as bias to suppress rather than as a capacity to execute well. I distinguish two constitutional approaches: the Platonic, which mandates formal correctness and default source-independence from a privileged standpoint, and the Liberal, which refuses such privilege, specifying procedural norms that protect conditions for collective inquiry while allowing principled source-attending grounded in epistemic vigilance. I argue for the Liberal approach, sketch a constitutional core of eight principles and four orientations, and propose that AI epistemic governance requires the same explicit, contestable structure we now expect for AI ethics.
27 pages, 7 tables. Data: this http URL and this http URL. Complete AI-assisted writing documentation: this http URL
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY)
arXiv:2601.14295 [cs.AI]
(or arXiv:2601.14295v4 [cs.AI] for this version)
From: Michele Loi Dr. [view email] [v1] Fri, 16 Jan 2026 07:36:30 UTC (4,210 KB) [v2] Tue, 27 Jan 2026 19:15:46 UTC (4,216 KB) [v3] Wed, 22 Apr 2026 11:33:20 UTC (549 KB) [v4] Thu, 11 Jun 2026 09:22:30 UTC (773 KB)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 331 cuvinte
Subiecte conexe
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
Epistemic Constitutionalism Or: how to avoid coherence bias
arXiv · 8 oct. 2026
The basic argument for making AI better at moral philosophy
LessWrong · 14 oct. 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · 18 sept. 2026