Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
0
LLMs excel at game rules but falter in social reasoning, revealing a crucial disconnect in Theory of Mind capabilities.
LLM safety guardrails are surprisingly more about parsing JSON than preventing jailbreaks, and general-purpose LLMs often outperform specialized safety models in multi-step tool-use scenarios.