Hiba Ahsan

2 accepted papers

2026

Can SAEs reveal and mitigate racial biases of LLMs in healthcare?

ICLR 2026poster

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…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare

Hiba Ahsan, Arnab Sen Sharma, Silvio Amir, David Bau, Byron C Wallace

EMNLP 2025

We know from prior work that LLMs encode social biases, and that this manifests in clinical tasks. In this work we adopt tools from mechanistic interpretability to unveil sociodemographic representations and biases within LLMs in the context of healthcare. Specifically, we ask: Can we identify activ

Cited by 0 Source ↗PDF ↗Scholar ↗