InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
- URL: http://arxiv.org/abs/2402.06332v2
- Date: Fri, 24 May 2024 07:09:21 GMT
- Title: InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
- Authors: Huaiyuan Ying, Shuo Zhang, Linyang Li, Zhejian Zhou, Yunfan Shao, Zhaoye Fei, Yichuan Ma, Jiawei Hong, Kuikun Liu, Ziyi Wang, Yudong Wang, Zijian Wu, Shuaibin Li, Fengzhe Zhou, Hongwei Liu, Songyang Zhang, Wenwei Zhang, Hang Yan, Xipeng Qiu, Jiayu Wang, Kai Chen, Dahua Lin,
- Abstract summary: 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.
- Score: 98.53491178426492
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: The math abilities of large language models can represent their abstract reasoning ability. In this paper, we introduce and 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 and supervise our model to be a versatile math reasoner, verifier, prover, and augmenter. These abilities can be used to develop the next math LLMs or self-iteration. InternLM-Math obtains open-sourced state-of-the-art performance under the setting of in-context learning, supervised fine-tuning, and code-assisted reasoning in various informal and formal benchmarks including GSM8K, MATH, Hungary math exam, MathBench-ZH, and MiniF2F. Our pre-trained model achieves 30.3 on the MiniF2F test set without fine-tuning. We further explore how to use LEAN to solve math problems and study its performance under the setting of multi-task learning which shows the possibility of using LEAN as a unified platform for solving and proving in math. Our models, codes, and data are released at \url{https://github.com/InternLM/InternLM-Math}.
Related papers
- Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes [10.314228434999924]
We introduce Math Neurosurgery (MathNeuro), a method for isolating math-specific parameters in Large Language Model (LLM) models.
MathNeuro identifies deletes a LLM's math reasoning ability without destroying its general language ability.
MathNeuro highlights the potential for future work to intervene on math-specific parameters.
arXiv Detail & Related papers (2024-10-22T12:00:58Z) - Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist [46.670206614087334]
We argue that if a model really understands a problem, it should be robustly applied across a diverse array of tasks.
MathCheck is a well-designed checklist for testing task generalization and reasoning.
MathCheck better reflects true mathematical abilities and represents mathematical intelligence more linearly.
arXiv Detail & Related papers (2024-07-11T17:58:58Z) - MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark [82.64129627675123]
MathBench is a new benchmark that rigorously assesses the mathematical capabilities of large language models.
MathBench spans a wide range of mathematical disciplines, offering a detailed evaluation of both theoretical understanding and practical problem-solving skills.
arXiv Detail & Related papers (2024-05-20T17:52:29Z) - 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) - MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning [2.9104279358536647]
We present MathSensei, a tool-augmented large language model for mathematical reasoning.
We study the complementary benefits of the tools - knowledge retriever (Bing Web Search), program generator + executor (Python), and symbolic equation solver (Wolfram-Alpha API)
arXiv Detail & Related papers (2024-02-27T05:50:35Z) - Large Language Models for Mathematicians [53.27302720305432]
Large language models (LLMs) have received immense interest for their general-purpose language understanding and, in particular, their ability to generate high-quality text or computer code.
In this note, we discuss to what extent they can aid professional mathematicians.
arXiv Detail & Related papers (2023-12-07T18:59:29Z) - Llemma: An Open Language Model For Mathematics [46.557804525919785]
We present Llemma, a large language model for mathematics.
On the MATH benchmark Llemma outperforms all known open base models.
Llemma is capable of tool use and formal theorem proving without any further finetuning.
arXiv Detail & Related papers (2023-10-16T17:54:07Z) - MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical
Reasoning [52.97768001837269]
We present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations.
We propose a method of generating novel and high-quality datasets with math problems and their code-based solutions.
This approach yields the MathCoder models, a family of models capable of generating code-based solutions for solving challenging math problems.
arXiv Detail & Related papers (2023-10-05T17:52:09Z) - WizardMath: Empowering Mathematical Reasoning for Large Language Models
via Reinforced Evol-Instruct [128.89645483139236]
We present WizardMath, which enhances the mathematical reasoning abilities of Llama-2, by applying our proposed Reinforcement Learning from Evol-Instruct Feedback (RLEIF) method to the domain of math.
Our model even surpasses ChatGPT-3.5, Claude Instant-1, PaLM-2 and Minerva on GSM8k, simultaneously surpasses Text-davinci, PaLM-1 and GPT-3 on MATH.
arXiv Detail & Related papers (2023-08-18T14:23:21Z)
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.