Implicit Bias-Like Patterns in Reasoning Models (2503.11572v2)

Abstract: Implicit bias refers to automatic mental processes that shape perceptions, judgments, and behaviors. Previous research on "implicit bias" in LLMs focused primarily on outputs rather than the processes underlying the outputs. We present the Reasoning Model Implicit Association Test (RM-IAT) to study implicit bias-like processing in reasoning models, which are LLMs using step-by-step reasoning for complex tasks. Using RM-IAT, we find o3-mini and DeepSeek R1 require more tokens when processing association-incompatible information, mirroring human implicit bias patterns. Conversely, Claude 3.7 Sonnet displays reversed patterns for race and gender tests, requiring more tokens for association-compatible information. This reversal appears linked to differences in safety mechanism activation, increasing deliberation in sensitive contexts. These findings suggest AI systems can exhibit processing patterns analogous to both human implicit bias and bias correction mechanisms.