发表机构
University of Science and Technology of China; iFLYTEK Research Group（中国科学技术大学; 讯飞研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对个性化语言模型跨会话整合不足与循环更新削弱早期证据的问题，提出双路径参数记忆（DPPM），其含证据路径与增量路径，生成LoRA适配器，在PersonaMem-v2、PrefEval数据集上优于基线。
AI 中文摘要
长期个性化要求语言模型利用交互历史跟踪用户跨会话的偏好。参数记忆将该交互历史编码为模型参数或适配器，减少了推理上下文中对其的需求。然而，独立的上下文编译未指定跨会话整合，而循环更新可能削弱早期证据。为解决这些挑战，我们提出双路径参数记忆（DPPM）：其证据路径直接汇集交互历史的表示以保留早期证据，而其增量路径顺序更新关联状态以捕捉变化；融合两者的输出生成历史条件LoRA适配器，结合证据积累与有序修正。在多个主干模型上，DPPM优于所有评估的基线，在PersonaMem-v2上达到54.22%，在PrefEval上达到86.79%。这些结果表明，DPPM为跨会话个性化参数记忆提供了一种简单有效的设计选择。
英文摘要
Long-term personalization requires language models to use interaction history to track users' preferences across sessions. Parametric memory encodes this interaction history into model parameters or adapters, reducing the need to include it in the inference context. However, independent context compilation leaves cross-session integration unspecified, while recurrent updates can attenuate earlier evidence. To address these challenges, we propose Dual-Path Parametric Memory (DPPM). Its Evidence path directly pools representations of the interaction history to preserve earlier evidence, while its Delta path sequentially updates an associative state to capture changes. Fusing both outputs produces history-conditioned LoRA adapters that combine evidence accumulation with ordered revision. Across multiple backbones, DPPM outperforms the evaluated baselines, achieving 54.22% on PersonaMem-v2 and 86.79% on PrefEval. These results suggest that DPPM provides a simple and effective design choice for cross-session personalized parametric memory.
Comments12 pages, 5 figures
