Skip to yearly menu bar Skip to main content


Oral
in
Workshop: 2nd Workshop on Models of Human Feedback for AI Alignment (MoFA)

Deep Context-Dependent Choice Model

Shuhan Zhang · Zhi Wang · Rui Gao · Shuang Li

[ ] [ Project Page ]
Fri 18 Jul 11:15 a.m. PDT — 11:30 a.m. PDT

Abstract:

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.Recent models that attempt to capture such effects either focus on the featureless setting or, in the feature-based setting, rely on restrictive interaction structures or entangle interactions across all orders, limiting interpretability. In this work, we propose DeepHalo, a neural modeling framework that incorporates features while enabling explicit control over interaction complexity and principled interpretation of context effects.Our model enables systematic identification of interaction effects by order and serves as a universal approximator of context-dependent choice functions when specialized to featureless setting.Experiments on synthetic and real-world datasets demonstrate strong predictive performance while providing greater transparency into the drivers of choice.

Chat is not available.