Search Results for author:
Found 2 papers, 2 papers with code
Flows: Building Blocks of Reasoning and Collaborating AI
To support rapid and rigorous research, we introduce the aiFlows library embodying Flows.
Language Model Decoding as Likelihood-Utility Alignment
Specifically, by analyzing the correlation between the likelihood and the utility of predictions across a diverse set of tasks, we provide empirical evidence supporting the proposed taxonomy and a set of principles to structure reasoning when choosing a decoding algorithm.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
