2 papers
cs.IR2026
Neighborhood-Aware Unlearning for Generative Recommendation
Pierre Lubitzsch, Yubao Tang, Maarten de Rijke +1
Generative recommendation predicts items by autoregressively generating semantic identifiers (SIDs), whose tokens are shared across semantically related items. With this paradigm g…
cs.AI2025
Ask WhAI:Probing Belief Formation in Role-Primed LLM Agents
Keith Moore, Jun W. Kim, David Lyu +2
We present Ask WhAI, a systems-level framework for inspecting and perturbing belief states in multi-agent interactions. The framework records and replays agent interactions, suppor…