Modeling Human-Like Color Naming Behavior in Context

TL;DR

This paper improves computational models of human-like color naming by combining supervised and reinforcement learning, introducing upsampling and multi-listener interactions to produce more convex and human-like color categories.

Contribution

It introduces a novel combination of upsampling rare terms and multi-listener reinforcement learning to generate more human-like, convex color lexicons in neural agent models.

Findings

Upsampling enhances lexical diversity and informativeness.

Multi-listener setups promote convex color categories.

Combining upsampling with multiple listeners yields the most human-like lexicons.

Abstract

Modeling the emergence of human-like lexicons in computational systems has advanced through the use of interacting neural agents, which simulate both learning and communicative pressures. The NeLLCom-Lex framework (Zhang et al., 2025) allows neural agents to develop pragmatic color naming behavior and human-like lexicons through supervised learning (SL) from human data and reinforcement learning (RL) in referential games. Despite these successes, the lexicons that emerge diverge systematically from human color categories, producing highly non-convex regions in color space, which contrast with the convexity typical of human categories. To address this, we introduce two factors, upsampling rare color terms during SL and multi-listener RL interactions, and adopt a convexity measure to quantify geometric coherence. We find that upsampling improves lexical diversity and system-level informativeness of the color lexicon, while many-listener setups promote more convex color categories. The combination of moderate upsampling and multiple listeners produces lexicons most similar to human systems.