Branch-solve-merge improves large language model evaluation and generation

S Saha, O Levy, A Celikyilmaz, M Bansal… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) are frequently used for multi-faceted language generation
and evaluation tasks that involve satisfying intricate user constraints or taking into account …

Language models are weak learners

H Manikandan, Y Jiang… - Advances in Neural …, 2023 - proceedings.neurips.cc
A central notion in practical and theoretical machine learning is that of a weak learner,
classifiers that achieve better-than-random performance (on any given distribution over …

A Survey of Table Reasoning with Large Language Models

X Zhang, D Wang, L Dou, Q Zhu, W Che - arXiv preprint arXiv:2402.08259, 2024 - arxiv.org
Table reasoning, which aims to generate the corresponding answer to the question
following the user requirement according to the provided table, and optionally a text …

Prompting for Numerical Sequences: A Case Study on Market Comment Generation

M Kawarada, T Ishigaki, H Takamura - arXiv preprint arXiv:2404.02466, 2024 - arxiv.org
Large language models (LLMs) have been applied to a wide range of data-to-text
generation tasks, including tables, graphs, and time-series numerical data-to-text settings …