Abstract:Are certain cognitive biases mathematically inevitable consequences of sequential information processing? We prove that primacy effects, anchoring, and order-dependence are architecturally necessary in autoregressive language models due to causal masking constraints. Our three impossibility theorems establish: (1) primacy bias arises from asymmetric attention accumulation; (2) anchoring emerges from sequential conditioning with provable information bounds; and (3) exact debiasing by permutation marginalization requires factorial-time computation, with Monte Carlo approximation feasible at constant per-tolerance overhead. We validate these bounds across 12 frontier LLMs ($R^2 = 0.89$; $\Delta$BIC $= 16.6$ vs. next-best alternative). We then derive quantitative predictions from the framework and test them in two pre-registered human experiments ($N = 464$ analyzed). Study 1 confirms anchor position modulates anchoring magnitude ($d = 0.52$, BF$_{10} = 847$). Study 2 shows working memory load amplifies primacy bias ($d = 0.41$, BF$_{10} = 156$), with WM capacity predicting bias reduction ($r = -.38$). These convergent findings reframe cognitive biases as resource-rational responses to sequential processing.
| Comments: | 6 pages, 3 figures, 5 tables. Accepted to CogSci 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| ACM classes: | I.2.7; I.2.6; J.4; F.1.3 |
| Cite as: | arXiv:2605.08716 [cs.AI] |
| (or arXiv:2605.08716v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08716 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jikun Wu [view email]
[v1]
Sat, 9 May 2026 05:56:12 UTC (31 KB)