Search papers, labs, and topics across Lattice.
State Key Laboratory for Novel Software Technology
2
0
5
1
LLMs can bootstrap their code generation abilities without external supervision by leveraging semantic entropy to identify learnable tasks and behavioral consensus to filter noisy self-generated training signals.
LLMs' chain-of-thought explanations often fail to reflect the true drivers of their decisions, and this benchmark reveals that closed-source models are particularly opaque, with monitorability dropping by up to 30% under stress.
