ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
ACSESS automatically combines 23 sample selection strategies to outperform individual strategies in few-shot learning on text and image datasets.
citing papers explorer
-
ART: Automatic multi-step reasoning and tool-use for large language models
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
-
Automatic Combination of Sample Selection Strategies for Few-Shot Learning
ACSESS automatically combines 23 sample selection strategies to outperform individual strategies in few-shot learning on text and image datasets.