From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Prompting
December 18, 2023 Β· Declared Dead Β· π NLRSE
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Nuo Chen, Hongguang Li, Baoyuan Wang, Jia Li
arXiv ID
2401.05384
Category
math.HO
Cross-listed
cs.AI
Citations
11
Venue
NLRSE
Last Checked
1 month ago
Abstract
This paper investigates the performance of Large Language Models (LLMs) and Tool-augmented LLMs in tackling complex mathematical reasoning tasks. We introduce IMP-TIP: Improving Math Reasoning with Tool-augmented Interleaf Prompting, a framework that combines the strengths of both LLMs and Tool-augmented LLMs. IMP-TIP follows the ``From Good to Great" concept, collecting multiple potential solutions from both LLMs and their Tool-Augmented counterparts for the same math problem, and then selecting or re-generating the most accurate answer after cross-checking these solutions via tool-augmented interleaf prompting. The framework incorporates two key aspects: self-prompt and tool-augmented interleaf prompting (TIP). The former allows LLMs to autonomously refine and improve an initial prompt related to tool usage, while the latter enables LLMs to derive the final answer by dynamically analyzing the problem, cross-checking potential solutions, and revising previous reasoning hints in an interleaved manner. Experimental analysis shows that IMP-TIP achieves enhanced mathematical capabilities and outperforms traditional LLMs and tool-augmented LLMs in accuracy and reasoning diversity on math reasoning tasks. For instance, IMP-TIP can improve Tool-augmented ChatGPT on GSM8K-Hard from 56.0% to 65.2%.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β math.HO
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Quantum GestART: Identifying and Applying Correlations between Mathematics, Art, and Perceptual Organization
R.I.P.
π»
Ghosted
The Mathematical Intelligencer flunks the Olympics
R.I.P.
π»
Ghosted
Non-Euclidean Virtual Reality IV: Sol
R.I.P.
π»
Ghosted
Elitism in Mathematics and Inequality
R.I.P.
π»
Ghosted
CAT(0) geometry, robots, and society
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Language Models are Few-Shot Learners
R.I.P.
π»
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
π»
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
π»
Ghosted