analiza aiqbench
This paper is a philosophy-of-causation argument, drawing on Hume, that Bayesian causal models need more than belief updating to explain how causal content is acquired, made generally usable, and held as belief. Its AI relevance is mainly conceptual: it challenges the assumption that correct posterior prediction shows a model has learned causal structure. Readers building or evaluating causal-learning systems, including language models, should note its distinction between predicting well and actually grounding causal knowledge, though the paper offers no empirical results or system benchmarks.
What Bayesian Updating Presupposes: Hume's Representational Conditions and Causal Learning
arXiv:2604.03387v2 Announce Type: replace Abstract: Bayesian causal models explain how expectations change, but they leave a further question open: how does the learner acquire the causal content whose probability changes? I argue that updating alone leaves three conditions of causal judgment unexplained: experiential grounding, general organization, and belief. Hume links these conditions through a felt customary transition, which arises from discriminating resembling cases and supplies the idea of necessary connexion. His arguments against deriving necessity directly from a single interaction or from an act of will support this account of the source. Contemporary causal-theory learning uses perceptual and agency cues to acquire an intervention role. The resulting disagreement is about what that role explains about experienced causal necessity, not about whether the model learns anything. Three elementary constructions distinguish acquisition from assisted execution, lost distinctions from failed access, and posterior agreement from usable deployment. Sampling theories and stable-belief accounts supply further components beyond updating. For models that learn about external events solely through a text corpus and written reports, the evidence is report-mediated rather than firsthand; whether their own transitions are felt is a separate, open question, and the update rule settles neither matter. The paper identifies what a complete explanation must connect: the acquisition of causal content, its availability for general use, and its role in belief. Correct posterior prediction alone establishes none of these connections.
Abstract:Bayesian causal models explain how expectations change, but they leave a further question open: how does the learner acquire the causal content whose probability changes? I argue that updating alone leaves three conditions of causal judgment unexplained: experiential grounding, general organization, and belief. Hume links these conditions through a felt customary transition, which arises from discriminating resembling cases and supplies the idea of necessary connexion. His arguments against deriving necessity directly from a single interaction or from an act of will support this account of the source. Contemporary causal-theory learning uses perceptual and agency cues to acquire an intervention role. The resulting disagreement is about what that role explains about experienced causal necessity, not about whether the model learns anything. Three elementary constructions distinguish acquisition from assisted execution, lost distinctions from failed access, and posterior agreement from usable deployment. Sampling theories and stable-belief accounts supply further components beyond updating. For models that learn about external events solely through a text corpus and written reports, the evidence is report-mediated rather than firsthand; whether their own transitions are felt is a separate, open question, and the update rule settles neither matter. The paper identifies what a complete explanation must connect: the acquisition of causal content, its availability for general use, and its role in belief. Correct posterior prediction alone establishes none of these connections.
Artificial Intelligence (cs.AI)
arXiv:2604.03387 [cs.AI]
(or arXiv:2604.03387v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2604.03387 Focus to learn more arXiv-issued DOI via DataCite
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 · 314 cuvinte
Subiecte conexe
Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Frozen LLMs
arXiv · 2 sept. 2026
When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents
arXiv · 1 sept. 2026
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
arXiv · 5 aug. 2026
Attractor-Vascular Coupling Theory: Formal Grounding and Empirical Validation for AAMI-Standard Cuffless Blood Pressure Estimation from Smartphone Photoplethysmography
arXiv · 27 oct. 2026