MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time
- URL: http://arxiv.org/abs/2405.16265v4
- Date: Wed, 26 Jun 2024 14:01:15 GMT
- Title: MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time
- Authors: Jikun Kang, Xin Zhe Li, Xi Chen, Amirreza Kazemi, Qianyi Sun, Boxing Chen, Dong Li, Xu He, Quan He, Feng Wen, Jianye Hao, Jun Yao,
- Abstract summary: MindStar is a purely inference-based searching method for large language models.
It formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths.
It significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1.
- Score: 51.5039731721706
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Although Large Language Models (LLMs) achieve remarkable performance across various tasks, they often struggle with complex reasoning tasks, such as answering mathematical questions. Recent efforts to address this issue have primarily focused on leveraging mathematical datasets through supervised fine-tuning or self-improvement techniques. However, these methods often depend on high-quality datasets that are difficult to prepare, or they require substantial computational resources for fine-tuning. Inspired by findings that LLMs know how to produce the right answer but struggle to select the correct reasoning path, we propose a purely inference-based searching method -- MindStar (M*). This method formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths. We evaluate the M* framework on both the GSM8K and MATH datasets, comparing its performance with existing open and closed-source LLMs. Our results demonstrate that M* significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1, but with substantially reduced model size and computational costs.
Related papers
- Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving [55.895917967408586]
Existing approaches to mathematical reasoning with large language models rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation.
We propose TATA (Teaching LLMs According to Their Aptitude), an adaptive framework that enables LLMs to personalize their reasoning strategy spontaneously.
arXiv Detail & Related papers (2025-02-17T16:56:23Z) - Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs [76.43407125275202]
o1-like models can emulate human-like long-time thinking during inference.
This paper presents the first comprehensive study on the prevalent issue of overthinking in these models.
We propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy.
arXiv Detail & Related papers (2024-12-30T18:55:12Z) - System-2 Mathematical Reasoning via Enriched Instruction Tuning [13.672967091915181]
Enriched Instruction Tuning (EIT) is a method that enriches existing human-annotated mathematical datasets by synergizing human and AI feedback.
EIT achieves an accuracy of 84.1% on GSM8K and 32.5% on MATH, surpassing state-of-the-art fine-tuning and prompting methods.
arXiv Detail & Related papers (2024-12-22T10:49:27Z) - MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks.
Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales.
We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
arXiv Detail & Related papers (2024-12-06T18:14:24Z) - EVOLvE: Evaluating and Optimizing LLMs For Exploration [76.66831821738927]
Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty.
We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications.
Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
arXiv Detail & Related papers (2024-10-08T17:54:03Z) - 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) - AlphaMath Almost Zero: Process Supervision without Process [6.318873143509028]
We propose an innovative framework, AlphaMath, that bypasses the need for process annotations by leveraging Monte Carlo Tree Search (MCTS)
This framework focuses on unleashing the potential of a well-pretrained LLM to autonomously enhance its mathematical reasoning.
The experimental results on both in-domain and out-of-domain datasets demonstrate that even without GPT-4 or human-annotated process supervision, our AlphaMath framework achieves comparable or superior results to previous state-of-the-art methods.
arXiv Detail & Related papers (2024-05-06T15:20:30Z) - Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions [47.83142414018448]
We focus on two popular reasoning tasks: arithmetic reasoning and code generation.
We introduce (i) a general ontology of perturbations for math and coding questions, (ii) a semi-automatic method to apply these perturbations, and (iii) two datasets.
We show a significant performance drop across all the models against perturbed questions.
arXiv Detail & Related papers (2024-01-17T18:13:07Z) - Improving Large Language Model Fine-tuning for Solving Math Problems [20.417053742869403]
A large gap exists between large language models' pass-at-one and pass-at-N performance in solving math problems.
Using the challenging MATH dataset, we investigate three fine-tuning strategies.
We design a fine-tuning recipe that yields approximately 58.8% accuracy on the MATH dataset with fine-tuned PaLM 2-L models.
arXiv Detail & Related papers (2023-10-16T04:11:19Z)
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.