提出分层负样本采样框架，提升记忆检索模型的精准度。
HiNS: Hierarchical Negative Sampling for More Comprehensive Memory Retrieval Embedding Model
- 按难度分层构建负样本，模拟对话中真实分布
- 在LoCoMo和PERSONAMEM上显著提升检索效果
- 适合需要精细记忆检索的智能对话系统
记忆增强型语言代理依赖嵌入模型实现高效记忆检索。然而现有训练数据构建忽略了负样本的层级难度及其在人机交互中的自然分布：部分负样本语义接近，部分则明显无关，且自然对话中存在结构化的比例关系。当前方法使用合成或均匀采样的负样本无法反映这种多样性，限制了嵌入模型学习细微区分能力，影响记忆检索的鲁棒性。本文提出一种原理性的数据构建框架HiNS，显式建模负样本难度层级，并引入基于对话数据的实证负样本比例，使嵌入模型在记忆密集型任务中实现显著提升的检索保真度与泛化能力。实验表明，在LoCoMo数据集上，MemoryOS和Mem0分别获得3.27%和1.95%的F1提升，以及3.30%和1.78%的BLEU-1提升；在PERSONAMEM上，总分分别提升1.19%（MemoryOS）和2.55%（Mem0）。
原文摘要 · Abstract (English)
Memory-augmented language agents rely on embedding models for effective memory retrieval. However, existing training data construction overlooks a critical limitation: the hierarchical difficulty of negative samples and their natural distribution in human-agent interactions. In practice, some negatives are semantically close distractors while others are trivially irrelevant, and natural dialogue exhibits structured proportions of these types. Current approaches using synthetic or uniformly sampled negatives fail to reflect this diversity, limiting embedding models' ability to learn nuanced discrimination essential for robust memory retrieval. In this work, we propose a principled data construction framework HiNS that explicitly models negative sample difficulty tiers and incorporates empirically grounded negative ratios derived from conversational data, enabling the training of embedding models with substantially improved retrieval fidelity and generalization in memory-intensive tasks. Experiments show significant improvements: on LoCoMo, F1/BLEU-1 gains of 3.27%/3.30%(MemoryOS) and 1.95%/1.78% (Mem0); on PERSONAMEM, total score improvements of 1.19% (MemoryOS) and 2.55% (Mem0).
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。