Search papers, labs, and topics across Lattice.
Max Planck Institute for Intelligent Systems, ELLIS Institute Tübingen, AI Center Tübingen, University of Tübingen
2
0
5
Sequence probability can signal correctness in LLM outputs, but tweaking decoding methods often fails to enhance accuracy.
Deterministic decoding can outperform stochastic self-consistency in constrained domains by systematically exploring high-probability reasoning traces, leading to better performance with less computation.
