Search papers, labs, and topics across Lattice.
4
0
6
9
GEO-optimized content is more prevalent than expected, with nearly 9% of web pages showing signs of manipulation, raising alarms about the integrity of information in generative search engines.
Identity drift in generative agents reveals that anti-self-deception is a dominant modification behavior, challenging assumptions about agent fidelity under pressure.
Existing moderation systems miss over 65% of hateful narratives in multi-turn visual stories, underscoring a critical gap in AI safety.
LLM safety is a cat-and-mouse game: ORPO excels at breaking alignment, while DPO is best at restoring it, but at the cost of overall usefulness.
