4 citations · 5 across the 11 of their papers we have counts for
Showing cs.IRShow all
2 papers · 1 filter
cs.IR2026
From "Strings" to "Things" for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems
Abhirup Dasgupta, Fernando Spadea, Oshani Seneviratne
Personal Knowledge Graphs (PKGs) offer a privacy-preserving framework for modeling user preferences, yet constructing them from unstructured, decentralized conversational data rema…
cs.IR2025
Avoiding Over-Personalization with Rule-Guided Knowledge Graph Adaptation for LLM Recommendations
Fernando Spadea, Oshani Seneviratne
We present a lightweight neuro-symbolic framework to mitigate over-personalization in LLM-based recommender systems by adapting user-side Knowledge Graphs (KGs) at inference time.…