Reposted by Sid
📎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
arxiv.org
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 ...
