all AI news
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning
March 13, 2024, 4:43 a.m. | Jiashuo Sun, Hang Zhang, Chen Lin, Xiangdong Su, Yeyun Gong, Jian Guo
cs.LG updates on arXiv.org arxiv.org
Abstract: Long-form numerical reasoning in financial analysis aims to generate a reasoning program to calculate the correct answer for a given question. Previous work followed a retriever-generator framework, where the retriever selects key facts from a long-form document, and the generator generates a reasoning program based on retrieved facts. However, they treated all facts equally without considering the different contributions of facts with and without numbers. Meanwhile, the program consistency were ignored under supervised training, resulting …
abstract analysis apollo arxiv cs.cl cs.lg document facts financial form framework generate generator key numerical question reasoning training type work
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote