DeepHalo: A Neural Choice Model with Controllable Context Effects

Zhi Wang (SIGS, Tsinghua University) · Shuhan Zhang (The Chinese University of Hong Kong, Shenzhen) · Rui Gao (University of Texas at Austin) · Shuang Li (The Chinese University of Hong Kong (Shenzhen))
context effectcontext-dependent choice functionsdecision-makingdeephalofeature-based settinghalo effecthigher-order interactionshuman-ai alignmentinteraction structuresinterpretabilityneural modeling frameworkpairwise interactionspredictive performancepreference learningrecommendationuniversal approximator

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