pith. sign in

arxiv: 2405.16265 · v4 · pith:R4HL42AJnew · submitted 2024-05-25 · 💻 cs.LG

MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time

Jikun Kang , Xin Zhe Li , Xi Chen , Amirreza Kazemi , Qianyi Sun , Boxing Chen , Dong Li , Xu He
show 4 more authors
Quan He Feng Wen Jianye Hao Jun Yao
This is my paper
classification 💻 cs.LG
keywords reasoningllmsdatasetsperformancetaskscomputationalfine-tuningmath
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration

    cs.LG 2026-05 unverdicted novelty 7.0

    UTTSI selectively scales test-time compute for CTR prediction by triggering stochastic feature-path exploration only on high-uncertainty instances, yielding gains on four datasets and a 5.3% online CTR lift.

  2. Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

    cs.LG 2024-07 unverdicted novelty 6.0

    Repeated sampling scales problem coverage log-linearly with sample count, improving SWE-bench Lite performance from 15.9% to 56% using 250 samples.

  3. Improve Mathematical Reasoning in Language Models by Automated Process Supervision

    cs.CL 2024-06 conditional novelty 6.0

    OmegaPRM automates collection of 1.5 million process supervision labels via binary-search MCTS, raising Gemini Pro math accuracy from 51% to 69.4% on MATH500 and Gemma2 27B from 42.3% to 58.2%.

  4. Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

    cs.LG 2026-04 unverdicted novelty 5.0

    Introduces IBPO, a counterfactual credit assignment method that turns sparse terminal rewards into process-level advantage estimates for more stable LLM reasoning training.

  5. From System 1 to System 2: A Survey of Reasoning Large Language Models

    cs.AI 2025-02 accept novelty 3.0

    The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.