Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

• URL: http://arxiv.org/abs/2407.20311v1
• Date: Mon, 29 Jul 2024 17:52:40 GMT
• Title: Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
• Authors: Tian Ye, Zicheng Xu, Yuanzhi Li, Zeyuan Allen-Zhu,
• Abstract summary: Recent advances in language models have demonstrated their capability to solve mathematical reasoning problems. Our study uncovers many hidden mechanisms by which language models solve mathematical questions.
• Score: 47.753284211200665
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in language models have demonstrated their capability to solve mathematical reasoning problems, achieving near-perfect accuracy on grade-school level math benchmarks like GSM8K. In this paper, we formally study how language models solve these problems. We design a series of controlled experiments to address several fundamental questions: (1) Can language models truly develop reasoning skills, or do they simply memorize templates? (2) What is the model's hidden (mental) reasoning process? (3) Do models solve math questions using skills similar to or different from humans? (4) Do models trained on GSM8K-like datasets develop reasoning skills beyond those necessary for solving GSM8K problems? (5) What mental process causes models to make reasoning mistakes? (6) How large or deep must a model be to effectively solve GSM8K-level math questions? Our study uncovers many hidden mechanisms by which language models solve mathematical questions, providing insights that extend beyond current understandings of LLMs.

Related papers

• MathScale: Scaling Instruction Tuning for Mathematical Reasoning [70.89605383298331]
  Large language models (LLMs) have demonstrated remarkable capabilities in problem-solving. However, their proficiency in solving mathematical problems remains inadequate. We propose MathScale, a simple and scalable method to create high-quality mathematical reasoning data.
  arXiv  Detail & Related papers  (2024-03-05T11:42:59Z)
• GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers [68.77382332826167]
  Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. One essential and frequently occurring evidence is that when the math questions are slightly changed, LLMs can behave incorrectly. This motivates us to evaluate the robustness of LLMs' math reasoning capability by testing a wide range of question variations.
  arXiv  Detail & Related papers  (2024-02-29T15:26:14Z)
• Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes [6.512667145063511]
  We propose a novel approach, named Brain, to imitate human thought processes to enhance mathematical reasoning abilities. First, we achieve SOTA performance in comparison with Code LLaMA 7B based models through this method. Secondly, we find that plans can be explicitly extracted from natural language, code, or formal language.
  arXiv  Detail & Related papers  (2024-02-23T17:40:31Z)
• InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning [98.53491178426492]
  We open-source our math reasoning LLMs InternLM-Math which is continue pre-trained from InternLM2. We unify chain-of-thought reasoning, reward modeling, formal reasoning, data augmentation, and code interpreter in a unified seq2seq format. Our pre-trained model achieves 30.3 on the MiniF2F test set without fine-tuning.
  arXiv  Detail & Related papers  (2024-02-09T11:22:08Z)
• ALERT: Adapting Language Models to Reasoning Tasks [43.8679673685468]
  ALERT is a benchmark and suite of analyses for assessing language models' reasoning ability. ALERT provides a test bed to asses any language model on fine-grained reasoning skills. We find that language models learn more reasoning skills during finetuning stage compared to pretraining state.
  arXiv  Detail & Related papers  (2022-12-16T05:15:41Z)
• Solving Quantitative Reasoning Problems with Language Models [53.53969870599973]
  We introduce Minerva, a large language model pretrained on general natural language data and further trained on technical content. The model achieves state-of-the-art performance on technical benchmarks without the use of external tools. We also evaluate our model on over two hundred undergraduate-level problems in physics, biology, chemistry, economics, and other sciences.
  arXiv  Detail & Related papers  (2022-06-29T18:54:49Z)
• Making Large Language Models Better Reasoners with Step-Aware Verifier [49.16750018427259]
  DIVERSE (Diverse Verifier on Reasoning Step) is a novel approach that further enhances the reasoning capability of language models. We evaluate DIVERSE on the latest language model code-davinci and show that it achieves new state-of-the-art results on six of eight reasoning benchmarks.
  arXiv  Detail & Related papers  (2022-06-06T03:38:36Z)
• Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems [4.309840398782996]
  We inspect non-neural and neural methods to solve math word problems narrated in a natural language. We highlight the ability of these methods to be generalizable, mathematically reasonable, interpretable, and explainable. We discuss technological approaches, review the evolution of intuitive design choices to solve MWPs, and examine them for mathematical reasoning ability.
  arXiv  Detail & Related papers  (2021-10-29T05:20:31Z)

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.