SAE 能否揭示并缓解医疗 LLM 的种族偏差？

ICLR 2026 Poster accepted paper at ICLR 2026. LLMs are increasingly being used in healthcare. This promises to free physicians from drudgery, enabling better care to be delivered at scale. But the use of LLMs in this space also brings risks; for example, such models may worsen existing biases. How can we spot when LLMs are (spuriously) relying on patient race to inform predictions? In this work we assess the degree to which Sparse Autoencoders (SAEs) can reveal (and control) associations the model has made between race and stigmatizing concepts. We first identify SAE latents in gemma-2 models which appear to correlate with Black individuals.