LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

• URL: http://arxiv.org/abs/2410.02884v2
• Date: Thu, 21 Nov 2024 07:07:59 GMT
• Title: LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning
• Authors: Di Zhang, Jianbo Wu, Jingdi Lei, Tong Che, Jiatong Li, Tong Xie, Xiaoshui Huang, Shufei Zhang, Marco Pavone, Yuqiang Li, Wanli Ouyang, Dongzhan Zhou,
• Abstract summary: The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
• Score: 56.273799410256075
• License:
• Abstract: This paper presents an advanced mathematical problem-solving framework, LLaMA-Berry, for enhancing the mathematical reasoning ability of Large Language Models (LLMs). The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path and utilizes a pairwise reward model to evaluate different paths globally. By leveraging the self-critic and rewriting capabilities of LLMs, Self-Refine applied to MCTS (SR-MCTS) overcomes the inefficiencies and limitations of conventional step-wise and greedy search algorithms by fostering a more efficient exploration of solution spaces. Pairwise Preference Reward Model~(PPRM), inspired by Reinforcement Learning from Human Feedback (RLHF), is then used to model pairwise preferences between solutions, utilizing an Enhanced Borda Count (EBC) method to synthesize these preferences into a global ranking score to find better answers. This approach addresses the challenges of scoring variability and non-independent distributions in mathematical reasoning tasks. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability compared to existing methods like ToT and rStar, particularly in complex Olympiad-level benchmarks, including GPQA, AIME24 and AMC23.

Related papers

• Self-Calibrated Listwise Reranking with Large Language Models [137.6557607279876]
  Large language models (LLMs) have been employed in reranking tasks through a sequence-to-sequence approach. This reranking paradigm requires a sliding window strategy to iteratively handle larger candidate sets. We propose a novel self-calibrated listwise reranking method, which aims to leverage LLMs to produce global relevance scores for ranking.
  arXiv  Detail & Related papers  (2024-11-07T10:31:31Z)
• Optimized Monte Carlo Tree Search for Enhanced Decision Making in the FrozenLake Environment [0.0]
  Monte Carlo Tree Search (MCTS) is a powerful algorithm for solving complex decision-making problems. This paper presents an optimized MCTS implementation applied to the FrozenLake environment, a classic reinforcement learning task.
  arXiv  Detail & Related papers  (2024-09-25T05:04:53Z)
• Solving General Natural-Language-Description Optimization Problems with Large Language Models [34.50671063271608]
  We propose a novel framework called OptLLM that augments LLMs with external solvers. OptLLM accepts user queries in natural language, convert them into mathematical formulations and programming codes, and calls the solvers to calculate the results. Some features of OptLLM framework have been available for trial since June 2023.
  arXiv  Detail & Related papers  (2024-07-09T07:11:10Z)
• Step-level Value Preference Optimization for Mathematical Reasoning [6.318873143509028]
  We introduce a novel algorithm called Step-level Value Preference Optimization (SVPO) Our method achieves state-of-the-art performance on both in-domain and out-of-domain mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-06-16T09:06:17Z)
• Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B [48.45472563225202]
  This paper introduces the MCT Self-Refine (MCTSr) algorithm, an innovative integration of Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS) The algorithm constructs a Monte Carlo search tree through iterative processes of Selection, self-refine, self-evaluation, and Backpropagation. Extensive experiments demonstrate MCTSr's efficacy in solving Olympiad-level mathematical problems.
  arXiv  Detail & Related papers  (2024-06-11T16:01:07Z)
• MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time [51.5039731721706]
  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.
  arXiv  Detail & Related papers  (2024-05-25T15:07:33Z)
• Let's reward step by step: Step-Level reward model as the Navigators for Reasoning [64.27898739929734]
  Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase. We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs. To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
  arXiv  Detail & Related papers  (2023-10-16T05:21:50Z)
• Sample-Efficient Multi-Agent RL: An Optimization Perspective [103.35353196535544]
  We study multi-agent reinforcement learning (MARL) for the general-sum Markov Games (MGs) under the general function approximation. We introduce a novel complexity measure called the Multi-Agent Decoupling Coefficient (MADC) for general-sum MGs. We show that our algorithm provides comparable sublinear regret to the existing works.
  arXiv  Detail & Related papers  (2023-10-10T01:39:04Z)

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.