SKIM：无需外部存储的冻结语言模型参数内对话记忆方法
Self-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models
AI 导读
一项 arXiv 研究提出自键参数内记忆方法 SKIM，让大语言模型在没有外部存储的情况下，将对话内容写入自身参数。模型对每轮对话自行生成多个问题作为检索键，后续用户提问即使措辞不同也能匹配并从参数中直接召回答案。在五个语言模型上的评测显示，SKIM 可召回大多数存储的对话轮次，全程不依赖任何外部存储。
正文 · 原文
Abstract:A large language model maintains conversational content in an external storage that is outside the model and grows as the dialogue continues. This work assumes an environment where a language model has no external memory and no prior knowledge of the future question or its answer. The motivation is to research whether a dialogue can be stored in the model parameters and later answer a question about it. This work proposes self-keyed in-parameter memorization (SKIM), a closed-form method in which the model generates its own questions about each dialogue turn and writes those questions into its parameters as the keys that later retrieve the turn's content. Generating many varied questions for each turn allows a later user question to match one even when phrased differently, and its answer is recalled from the parameters alone. Evaluated on five language models, SKIM recalls most stored dialogue turns from later user questions, and it answers from the model parameters without any external storage.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36948 [cs.CL] |
| (or arXiv:2610.36948v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36948 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: XinYu Piao [view email]
[v1]
Tue, 27 Oct 2026 10:10:11 UTC (1,027 KB)
来源：arXiv cs.AI · arxiv.org