Search Results for author:
Found 2 papers, 2 papers with code
Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries
In this paper, we present measures for quantification of error in the response of a large language model based on the diversity of responses to a given prompt - hence independent of the underlying application.
An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)
We study the performance of a commercially available large language model (LLM) known as ChatGPT on math word problems (MWPs) from the dataset DRAW-1K.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
