arXiv cs.CL· Mingzhe Lu, Jian Qin, Ruize Qin, Jinhao Liu, Yunpeng Li, Hang Su·· 13 小时前AI 评分24
PDG-F：用有向无环图建模偏好依赖的叙事驱动推荐框架
Modeling Preference Dependencies with Directed Acyclic Graphs for Narrative-Driven Recommendation
AI 导读
研究者提出叙事驱动推荐框架 PDG-F，其 PDG-Agent 先将自由文本请求解析为有向无环的偏好依赖图（PDG），再通过有向路径检索获取开放网络候选证据，并按拓扑路径排序确定推荐结果。在覆盖中英文语境的三个领域实验中，PDG-F 的推荐表现优于竞争基线、开放域检索智能体和前沿语言模型。诊断分析显示，依赖引导的检索显著提升了候选池的可达上限。
正文 · 原文
Abstract:Narrative-driven recommendation allows users to express multifaceted needs through free-form text where stated preferences naturally qualify and condition one another. Existing methods typically treat narratives as flat keyword combinations or unconstrained generative queries, failing to capture how complex preferences hierarchically refine and contextualize each other. We propose the Preference Dependency Graph Framework (PDG-F), a narrative-driven recommendation framework centered on explicit preference dependencies. Specifically, PDG-A (PDG-Agent) first parses unstructured requests to organize user preferences and their mutual qualifications into a directed acyclic Preference Dependency Graph (PDG). Through this graph, candidate evidence from the open Web is acquired via directed path retrieval, and final recommendations are determined by topological path ranking. Comprehensive experiments across three diverse domains spanning English and Chinese contexts confirm that PDG-F consistently achieves superior recommendation performance over competitive baselines, open-domain retrieval agents, and frontier language models. Further diagnostic analyses show that our dependency-guided retrieval markedly raises the attainable candidate-pool ceiling, demonstrating the fundamental value of modeling preference dependencies in narrative-driven recommendation.
| Comments: | 9 pages, 5 figures, 3 tables |
| Subjects: | Information Retrieval (cs.IR); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.37280 [cs.IR] |
| (or arXiv:2610.37280v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37280 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mingzhe Lu [view email]
[v1]
Tue, 27 Oct 2026 14:08:30 UTC (581 KB)
来源：arXiv cs.CL · arxiv.org