Sid

Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence In high-stakes domains like medicine, it may be generally desirable for models to faithfully adhere to the context provided. But what happens if the context does not align with model priors or safety ...

📎Paper: arxiv.org/abs/2601.11886
🧑‍💻Code/data: github.com/KaijieMo-kj/...

w/
@kaijie-mo.bsky.social @sidvenkatayogi.bsky.social
@chantalsh.bsky.social @ramezkouzy.bsky.social
@cocoweixu.bsky.social @byron.bsky.social @jessyjli.bsky.social

21.01.2026 19:07 — 👍 1    🔁 1    💬 0    📌 0

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.🧵

21.01.2026 18:45 — 👍 14    🔁 6    💬 3    📌 2

GitHub - sidvenkatayogi/pixie Contribute to sidvenkatayogi/pixie development by creating an account on GitHub.

Github:
github.com/sidvenkatayo...
Process:
sidvenkatayogi.github.io/posts/2025/0...
Download PIXIE:

21.07.2025 19:03 — 👍 1    🔁 0    💬 0    📌 0

just released PIXIE, a novel, intuitive visual tool for visual creatives to browse/search for inspiration and reference. The better way to view your Pinterest boards.

Here’s the demo:

21.07.2025 19:02 — 👍 1    🔁 0    💬 1    📌 0