at://
/
app.bsky.feed.post
/
3mcxelhuga22m
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
📎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
4mo
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 ...
arxiv.org
Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence
