Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues
It is found that sensitivity to demographic cues is distributed across internal units and varies substantially across models, suggesting that effective mitigation requires understanding distributed, task-specific mechanisms rather than manipulating a small set of identified neurons alone.
Shiyue Hu, Ruizhe Li, Yanjun Gao
· 1 citation
· ⚡1