11 citations · 11 across the 2 of their papers we have counts for
2 papers
cs.CL2023★ 11 cited
FinanceBench: A New Benchmark for Financial Question Answering
Pranab Islam, Anand Kannappan, Douwe Kiela +3
FinanceBench is a first-of-its-kind test suite for evaluating the performance of LLMs on open book financial question answering (QA). It comprises 10,231 questions about publicly t…
cs.CL2022
Analyzing Bagging Methods for Language Models
Pranab Islam, Shaan Khosla, Arthur Lok +1
Modern language models leverage increasingly large numbers of parameters to achieve performance on natural language understanding tasks. Ensembling these models in specific configu…