Swims and Dives
Our #EMNLP2025 paper reveals that crafting thoughtful refusals rather than detecting intent is the key to human-centered AI safety.
📄 arxiv.org/abs/2506.00195
🧵[1/9]
Our #EMNLP2025 paper reveals that crafting thoughtful refusals rather than detecting intent is the key to human-centered AI safety.
📄 arxiv.org/abs/2506.00195
🧵[1/9]
Pareto.ai @sfu.ca @ai2.bsky.social ♥️
📂 github.com/EEElisa/LLM-Guardrails
Pareto.ai @sfu.ca @ai2.bsky.social ♥️
📂 github.com/EEElisa/LLM-Guardrails
Sound right to you?
#askingforafriend
First, here is the high-level community structure with some labels. Hi res w/ zoom here: https://www.easyzoom.com/imageaccess/884cb1c001cd48e79aca92232bd24a04
The code that turns the graph data into the Atlas visualization at https://bsky.jazco.dev is available here: https://github.com/ericvolp12/bsky-graph