SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models

• URL: http://arxiv.org/abs/2404.03887v4
• Date: Wed, 02 Oct 2024 11:56:35 GMT
• Title: SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models
• Authors: Hyeonwoo Kim, Gyoungjin Gim, Yungi Kim, Jihoo Kim, Byungju Kim, Wonseok Lee, Chanjun Park,
• Abstract summary: We focus on integrating the Chain-of-Thought (CoT) and the Program-of-Thought (PoT) learning. We propose a sequential learning approach, named SAAS (Solving Ability Amplification Strategy), which strategically transitions from CoT learning to PoT learning.
• Score: 4.090307917818891
• License:
• Abstract: This study presents a novel learning approach designed to enhance both mathematical reasoning and problem-solving abilities of Large Language Models (LLMs). We focus on integrating the Chain-of-Thought (CoT) and the Program-of-Thought (PoT) learning, hypothesizing that prioritizing the learning of mathematical reasoning ability is helpful for the amplification of problem-solving ability. Thus, the initial learning with CoT is essential for solving challenging mathematical problems. To this end, we propose a sequential learning approach, named SAAS (Solving Ability Amplification Strategy), which strategically transitions from CoT learning to PoT learning. Our empirical study, involving an extensive performance comparison using several benchmarks, demonstrates that our SAAS achieves state-of-the-art (SOTA) performance. The results underscore the effectiveness of our sequential learning approach, marking a significant advancement in the field of mathematical reasoning in LLMs.

Related papers

• Improving Math Problem Solving in Large Language Models Through Categorization and Strategy Tailoring [0.0]
  We develop a machine learning model for problem categorization and show that its accuracy can be significantly improved through the creation of well-designed training datasets. We believe that our approach works by helping reduce hallucinations in LLMs, which is a critical step toward unlocking their potential to tackle advanced mathematical problems.
  arXiv  Detail & Related papers  (2024-10-29T16:06:26Z)
• BloomWise: Enhancing Problem-Solving capabilities of Large Language Models using Bloom's-Taxonomy-Inspired Prompts [59.83547898874152]
  We introduce BloomWise, a new prompting technique, inspired by Bloom's taxonomy, to improve the performance of Large Language Models (LLMs) The decision regarding the need to employ more sophisticated cognitive skills is based on self-evaluation performed by the LLM. In extensive experiments across 4 popular math reasoning datasets, we have demonstrated the effectiveness of our proposed approach.
  arXiv  Detail & Related papers  (2024-10-05T09:27:52Z)
• Benchmarking Large Language Models for Math Reasoning Tasks [12.91916443702145]
  We compare seven state-of-the-art in-context learning algorithms for mathematical problem solving across five widely used mathematical datasets on four powerful foundation models. Our results indicate that larger foundation models like GPT-4o and LLaMA 3-70B can solve mathematical reasoning independently from the concrete prompting strategy. We open-source our benchmark code to support the integration of additional models in future research.
  arXiv  Detail & Related papers  (2024-08-20T13:34:17Z)
• Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering [53.56653281752486]
  This study explores Large Language Models' mathematical reasoning on four financial question-answering datasets. We focus on sensitivity to table complexity and performance variations with an increasing number of arithmetic reasoning steps. We introduce a novel prompting technique tailored to semi-structured documents, matching or outperforming other baselines in performance.
  arXiv  Detail & Related papers  (2024-02-17T05:10:18Z)
• SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving [64.38649623473626]
  Large Language Models (LLMs) have driven substantial progress in artificial intelligence. We propose a novel framework called textbfSEquential subtextbfGoal textbfOptimization (SEGO) to enhance LLMs' ability to solve mathematical problems.
  arXiv  Detail & Related papers  (2023-10-19T17:56:40Z)
• No Train Still Gain. Unleash Mathematical Reasoning of Large Language Models with Monte Carlo Tree Search Guided by Energy Function [3.0299876288833345]
  Large language models (LLMs) demonstrate impressive language understanding and contextual learning abilities. LLMs often struggle to generate correct reasoning steps and answers despite having high probabilities for the solutions. We propose a method that incorporates Monte Carlo Tree Search (MCTS) and a lightweight energy function to rank decision steps.
  arXiv  Detail & Related papers  (2023-09-01T13:10:54Z)
• Auxiliary Learning as an Asymmetric Bargaining Game [50.826710465264505]
  We propose a novel approach, named AuxiNash, for balancing tasks in auxiliary learning. We describe an efficient procedure for learning the bargaining power of tasks based on their contribution to the performance of the main task. We evaluate AuxiNash on multiple multi-task benchmarks and find that it consistently outperforms competing methods.
  arXiv  Detail & Related papers  (2023-01-31T09:41:39Z)
• Importance Weighted Policy Learning and Adaptation [89.46467771037054]
  We study a complementary approach which is conceptually simple, general, modular and built on top of recent improvements in off-policy learning. The framework is inspired by ideas from the probabilistic inference literature and combines robust off-policy learning with a behavior prior. Our approach achieves competitive adaptation performance on hold-out tasks compared to meta reinforcement learning baselines and can scale to complex sparse-reward scenarios.
  arXiv  Detail & Related papers  (2020-09-10T14:16:58Z)
• Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning [96.78504087416654]
  Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems, we investigate when this paradigm is provably efficient. We present a general algorithmic framework that is built upon two components: an unsupervised learning algorithm and a noregret tabular RL algorithm.
  arXiv  Detail & Related papers  (2020-03-15T19:23:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.