A late-fusion model of CF, RL bandit, and TOPSIS achieves NDCG@5=0.3040 on JobHop (outperforming baselines) but remains competitive without significant gains on Karrierewege, with the bandit branch deactivating in persistence-dominated data.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
SGDA generates synthetic faults in the frequency domain from healthy signals to augment training data for ML-based induction motor diagnostics, claiming superior accuracy.
Proposes a modular architecture for LLM-based wellbeing recommenders using explicit constraints on guidance, explanations, directness, and user control to address trust calibration, intent alignment, and consequence awareness.
Introduces semantic Pareto-DQN for multi-objective recommendation that sustains trajectory variance to improve diversity and fairness on MovieLens with limited engagement loss.
citing papers explorer
-
Designing Trustworthy LLM-based Wellbeing Recommendation through Controllable Interaction
Proposes a modular architecture for LLM-based wellbeing recommenders using explicit constraints on guidance, explanations, directness, and user control to address trust calibration, intent alignment, and consequence awareness.