跳到正文
arXiv cs.AI· Mark Nowak (Conflux Laboratory)·· 1 小时前AI 评分35

AllotNet:面向人道主义援助分配道德判断的可解释 MoE 选择模型,经植入合成人群验证

AllotNet: an Interpretable Mixture-of-Experts Choice Model for Moral Judgement in Humanitarian Aid Allocation, Validated against a Planted Synthetic Population

AI 导读

AllotNet 是一个可解释的 mixture-of-experts 条件 logit 模型,用于人道主义援助分配中的道德判断,包含八个覆盖七项伦理准则的线性专家和从不拒绝任何人的预算约束规划器。

正文 · 原文

View PDF HTML (experimental)

Abstract:Official development assistance fell by 23.1 per cent in 2025, and the decision of who is helped first when there is not enough for everyone is moving into software. A leading published machine-learning targeting system excluded 53 per cent of eligible households as deployed. If the rule of distribution ends up in code, it should carry the judgement of many cultures, and the machine should execute while a person judges. AllotNet is an interpretable mixture-of-experts conditional logit for the allocation judgements elicited by Allot, a pre-registered six-language instrument: eight linear taste experts over seven ethical criteria, weighted by a gate over participant context, with a damped residual, an encoder for household intake, an outcome head and a budget-constrained planner that builds a review queue and never rejects anyone. A model of human judgement has no answer key on real data, so we wrote one first: a planted synthetic population of 5.6 million sessions and 104 million responses (98 million usable choices), generated by the production code path from a ground truth hidden from the loss. All sixteen pre-specified checks passed: criterion ranking $\rho = 1.000$, hidden segments recovered (ARI 0.671), outcome head at 99 per cent of the noise ceiling, planner at 99.4 per cent of oracle. The caveats are reported with them: two checks are weaker than their titles, and a live-generation failure cost 260,712 seeds. The model has 23,550 parameters, is trained quantisation-aware for NVFP4 with its interpretable core in fp32 (welfare-rank parity $\rho = 0.9937$ at W4A16 on the shipped bundle; one parity threshold was relaxed post hoc), and ships as a 125 KB bundle with C11, Java, Rust and Python runtimes. Nothing has been trained on real data yet; at the study's real scale a hierarchical Bayesian mixed logit is the registered comparator.
Comments: 83 pages, 16 figures, 36 tables. Public version: the elicitation instrument's scoring specification, the planted ground truth and per-criterion results are withheld under the study's pre-registration embargo (until 1 August 2030). A companion paper reports the designed-society simulation of allocation rules
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
ACM classes: I.2.6; K.4.1
Cite as: arXiv:2611.23474 [cs.LG]
  (or arXiv:2611.23474v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.23474

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mark Nowak Mr [view email]
[v1] Tue, 17 Nov 2026 20:25:51 UTC (247 KB)

来源:arXiv cs.AI · arxiv.org