用动态LSTM记忆模块实现长对话中用户偏好的轻量级建模
Dynamic Long Short-Term Memory Based Memory Storage For Long Horizon LLM Interaction
- 结合BERT分类器与LSTM记忆模块，生成可注入的软提示嵌入
- 在合成数据集上，BERT分类器准确识别显性和隐性用户偏好
- 无需微调模型，适合需要高效个性化长对话的应用
大型语言模型（LLMs）的记忆存储正成为研究热点，尤其在长对话中实现个性化。我们提出Pref-LSTM，一种动态且轻量的框架，结合基于BERT的分类器与LSTM记忆模块，生成记忆嵌入并以软提示形式注入冻结的LLM。我们合成构建了包含偏好与非偏好对话回合的数据集用于训练BERT分类器。尽管基于LSTM的记忆编码器表现一般，但BERT分类器在识别用户显性和隐性偏好方面表现可靠。研究表明，结合偏好过滤与LSTM门控机制，是一种无需大量开销和微调即可实现可扩展用户偏好建模的有效路径。
原文摘要 · Abstract (English)
Memory storage for Large Language models (LLMs) is becoming an increasingly active area of research, particularly for enabling personalization across long conversations. We propose Pref-LSTM, a dynamic and lightweight framework that combines a BERT-based classifier with a LSTM memory module that generates memory embedding which then is soft-prompt injected into a frozen LLM. We synthetically curate a dataset of preference and non-preference conversation turns to train our BERT-based classifier. Although our LSTM-based memory encoder did not yield strong results, we find that the BERT-based classifier performs reliably in identifying explicit and implicit user preferences. Our research demonstrates the viability of using preference filtering with LSTM gating principals as an efficient path towards scalable user preference modeling, without extensive overhead and fine-tuning.
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。