认知偏差是顺序处理的数学必然结果，非错误而是系统性产物。
Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation
- 从因果掩码约束出发，证明了语言模型中存在不可消除的首因效应与锚定效应。
- 12个前沿大模型验证显示，理论预测与实测偏差高度吻合（R²=0.89）。
- 适用于认知科学、AI可解释性研究者，理解人类与模型共有的思维局限。
某些认知偏差是否是顺序信息处理的数学必然？我们证明了首因效应、锚定效应和顺序依赖性在自回归语言模型中是架构上的必然结果。三个不可能性定理表明：(1) 首因偏见源于不对称注意力积累；(2) 锚定效应由顺序条件化及信息上限引发；(3) 精确去偏需阶乘时间复杂度，蒙特卡洛近似可在恒定容差开销下实现。我们在12个前沿大模型上验证了这些边界（R²=0.89；ΔBIC=16.6 vs. 次优模型）。随后基于框架提出量化预测，并在两项预注册人类实验中检验（共464人分析）。实验1确认锚点位置调节锚定强度（d=0.52，BF₁₀=847）；实验2显示工作记忆负荷加剧首因偏见（d=0.41，BF₁₀=156），且工作记忆容量可预测偏见降低（r=-.38）。这些收敛证据将认知偏差重新定义为对顺序处理资源的理性响应。
原文摘要 · Abstract (English)
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 ($R^2 = 0.89$; $Δ$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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。