Nov 16, 2024 · Recent works have explored combining the impressive capabilities of Large Language Models (LLMs) with the domain-specific knowledge of Knowledge Graphs (KGs) to …

Mar 7, 2025 · MCTS simulates human-like reasoning by exploring multiple inference paths in knowledge graphs, generating interpretable reasoning chains and rich hop-level preferences.

Mar 16, 2019 · In this article, we consider the knowledge graph (KG) as the source of side information. To address the limitations of existing embedding-based and path-based methods for …

Nov 16, 2024 · Specifically, preference learning is used to alleviate semantic dissonance in knowledge embeddings by exploring intent correlations in user-item interaction history, while the …

Feb 6, 2025 · To effectively complete the personalized dialogue recommendation task, this paper proposes a new algorithmic framework—KGCR (knowledge graph-based user preference …

Knowledgeable Preference AlignmenT (KnowPAT) is a new pipeline to align LLMs with human's knowledge preference. KnowPAT incorporates domain knowledge graphs to construct preference …

May 21, 2025 · Every knowledge graph is a graph, but not every graph is a knowledge graph. So, how do you tell them apart? ... the graph retrieves only the top 5 connected products based on …

In this paper, we propose COMPASS, a plug-and-play framework that synergizes LLMs and KGs to unveil user preferences, enhancing the performance and explainability of existing CRSs.

In this paper, we propose COMPASS (Compact Preference Analyzer and Summarization System), a plug-and-play framework that synergizes LLMs and KGs to unveil user preferences, enhanc-ing …

Mar 1, 2024 · To tackle these, a novel model named Knowledge Graph Preference Migration Network (KGPM) is proposed by us, aiming to address the lack of information in cold-start users’ …