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%.
LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
Shanghai Business School(上海商学院);Learnable.AI Inc.(Learnable.AI公司);Centre for Frontier AI Research, A*STAR(前沿人工智能研究中心,A*STAR);Institute of High-Performance Computing, A*STAR(高性能计算研究所,A*STAR);The Hong Kong Polytechnic University(香港理工大学);Microsoft Research Asia(微软亚洲研究院)
PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability
Posts and Telecommunications Institute of Technology(邮电技术研究所);Hanoi Architectural University(河内建筑大学)
AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));City University of Hong Kong(香港城市大学);Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区);The Hong Kong University of Science and Technology(香港科技大学);University of California, Merced(加州大学默塞德分校);Chongqing University(重庆大学);MBZUAI(穆罕默德·本·扎耶德人工智能大学)
How to Ask the AI: A User Perspective Survey for Large Language Model Prompting
School of Computer Science and Technology, Guangdong University of Technology(广东工业大学计算机科学与技术学院);Department of Computer Science, Hong Kong Baptist University(香港浸会大学计算机科学系)
SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding
College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部);The Hong Kong Polytechnic University(香港理工大学);College of Software Engineering, Zhengzhou University of Light Industry(郑州轻工业大学软件学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Information Technology, Halmstad University(哈尔姆斯塔德大学信息技术学院)
RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning
Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization
Data Science Department, Princess Sumaya University for Technology(普里姆斯萨大学技术学院数据科学系);Electrical and Computer Engineering Department, Virginia Tech(弗吉尼亚理工大学电气与计算机工程系);Computer Science Department, Princess Sumaya University for Technology(普里姆斯萨大学技术学院计算机科学系);Computer Science Department, King Fahd University of Petroleum and Minerals(国王法赫德石油与矿物大学计算机科学系)
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
AI Safety of Chinese Academy of Sciences, Institute of Computing Technology, CAS(中国科学院人工智能安全研究院,中国科学院计算技术研究所);University of California, Merced(加州大学默塞德分校);Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);University of Chinese Academy of Sciences(中国科学院大学)