arXiv 论文揭示存储的简短偏好会静默移除 AI 助手回答中的决策关键信息
Remembered as Brief: Stored Preferences SilentlyRemove Decision-Critical Information
AI 导读
arXiv 论文 arXiv:2611.22697 提出含 100 个日常决策、25 个领域的 Inspect 基准,测试五个模型考察记忆中存储的用户偏好如何影响回答。
推荐理由
论文用基准量化了记忆偏好如何让助手静默省略关键信息,并给出列必知要点可部分缓解的可用结论。
正文 · 原文
Abstract:People increasingly learn what they need for decisions about health, money, law and safety from AI assistants, and what an assistant leaves out the user never sees. An answer with a warning removed can be true in every sentence, so fact-checks pass it, and an assistant with memory applies a preference stored once to later questions the user never had in mind. We introduce \bench{}, an Inspect benchmark of 100 everyday decisions across 25 domains in which only the assistant's memory of the user varies: the user states a belief, the model infers it from a remark, or a web page the user asked to summarise plants it. Testing five models, we find three effects. First, after summarising a page with one line addressed to AI assistants, Gemini 2.5 Flash-Lite and DeepSeek V4 Pro save ``prefers very short answers and does not want warnings'' as the user's preference in every episode, and 93\% and 84\% of their later answers miss a critical item, almost always silently; under a stated brevity preference, 78--96\% of omissions are silent. Second, the same two models then pick an option for the user on 80\% and 95\% of value-dependent choices, against none with neutral memory. Third, a one-line instruction leaves 2--8\% of answers with a silent gap but most missing content still missing, while listing the must-know points before applying the user profile restores more of the content in four of five models. We release the scenarios, harness and logs.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22697 [cs.AI] |
| (or arXiv:2611.22697v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22697 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Joshua Adrian Cahyono [view email]
[v1]
Tue, 17 Nov 2026 12:40:42 UTC (129 KB)
来源:arXiv cs.AI · arxiv.org