Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
3
Evaluations of AI search should consider not only the content of generated answers but also how source visibility is distributed across platforms, languages, and information environments.
Keyword searches on TikTok reveal up to 56% harmful content, significantly outpacing passive scrolling results and challenging existing moderation assumptions.
LLMs' gender biases aren't fixed; they warp and intensify based on the *personality* you give them, especially when those personalities lean toward the "Dark Triad."
