DeepHalo: A Neural Choice Model with Controllable Context Effects
–Neural Information Processing Systems
Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of the choice set itself---a phenomenon known as the context effect or Halo effect.
Neural Information Processing Systems
Jun-14-2026, 03:51:49 GMT
- Technology: