arXiv cs.CL· Sebastian Cochinescu·· 2 天前AI 评分22
面向可信 AI 的“偏爱”：人工偏私与关系持久性作为一种可工程化的立场
Love for Believable AI: Artificial Partiality and Relationship Persistence as an Engineerable Stance
AI 导读
研究提出一种对话智能体的“人工偏私”行为机制，由“关怀”（在每用户保底服务之上分配有限交互盈余）与“特殊性”（基于关系历史累积的每用户状态估计）两部分构成，并在一个开放权重基座模型上以持久层实现。
正文 · 原文
Abstract:We study a behavioral mechanism for artificial partiality in conversational agents. The paper reports no human-subjects data and makes no claim about attachment, trust, perceived mind, or machine interiority. Partiality has two components: caring, defined as allocation of a finite interaction surplus above a guaranteed per-user service floor, and particularity, defined as a per-user state estimate accumulated from relationship history on fixed inference machinery. We implement both as a persistence layer over one open-weight base model and evaluate them on constructed multi-session relationships with known hidden-state schedules. A four-channel divergence compares known-user and stranger conditions on identical probes with paired generation seeds; the stranger prompt is not length-matched, and one channel (initiative) is an allocator output rather than generated behavior. The full mechanism reproduces the ordinal shape, but not the magnitude, of an analytically specified curve and is the only arm satisfying the protocol-defined joint signature on the calibrated battery. The initial mechanism fails probe-quality equivalence because relationship content reduces topical relevance. A guarded revision satisfies equivalence on the calibrated battery but not on a second battery not used in calibration, where it scores higher than the unmodified baseline. On that second battery, the specificity margin is 0.0198, below the 0.02 protocol threshold. The paired mean right-user--wrong-user estimation-accuracy contrast is 0.375 but is not positive in every run. The mechanism is therefore a candidate for a later perception study, not evidence that users perceive love. The versioned protocol record is not independently time-stamped and is not described as a preregistration. Ethical constraints include a stranger-treatment floor, a bounded surplus, disclosure, and de-intensification.
| Comments: | 16 pages, 1 figure, 4 tables. Companion framework paper: arXiv:2607.15883 Code and data archived at doi:https://doi.org/10.5281/zenodo.21462976 |
| Subjects: | Human-Computer Interaction (cs.HC); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.09895 [cs.HC] |
| (or arXiv:2610.09895v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09895 arXiv-issued DOI via DataCite |
Submission history
From: Sebastian Cochinescu PhD (ABD) [view email]
[v1]
Wed, 7 Oct 2026 11:54:46 UTC (117 KB)
来源：arXiv cs.CL · arxiv.org