@kaijie-mo.bsky.social
Hello world 👋
My first paper at UT Austin!
We ask: what happens when medical “evidence” fed into an LLM is wrong? Should your AI stay faithful, or should it play it safe when the evidence is harmful?
We show that frontier LLMs accept counterfactual medical evidence at face value.🧵
My first paper at UT Austin!
We ask: what happens when medical “evidence” fed into an LLM is wrong? Should your AI stay faithful, or should it play it safe when the evidence is harmful?
We show that frontier LLMs accept counterfactual medical evidence at face value.🧵
January 21, 2026 at 6:45 PM
Hello world 👋
My first paper at UT Austin!
We ask: what happens when medical “evidence” fed into an LLM is wrong? Should your AI stay faithful, or should it play it safe when the evidence is harmful?
We show that frontier LLMs accept counterfactual medical evidence at face value.🧵
My first paper at UT Austin!
We ask: what happens when medical “evidence” fed into an LLM is wrong? Should your AI stay faithful, or should it play it safe when the evidence is harmful?
We show that frontier LLMs accept counterfactual medical evidence at face value.🧵