Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
The topological geometry of an LLM's attention maps reveals whether code is hallucinated before a single line is executed, outperforming traditional pre-execution heuristics across models up to 34B parameters.
Settling operators can significantly boost accuracy on unseen tasks, transforming additional iterations into a performance advantage rather than a risk of degradation.