Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models

• URL: http://arxiv.org/abs/2403.02178v2
• Date: Wed, 10 Jul 2024 19:15:24 GMT
• Title: Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
• Authors: Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li,
• Abstract summary: In reasoning tasks, even a minor error can cascade into inaccurate results. We develop a method that avoids introducing external resources, relying instead on perturbations to the input. Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks.
• Score: 102.72940700598055
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise supervisory signals from human labeling, larger models, or self-sampling, although at a high cost. Conversely, we develop a method that avoids external resources, relying instead on introducing perturbations to the input. Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks. When applied to fine-tuning with GSM8K on Llama-2-7B, this method achieved a 5\% improvement in GSM8K accuracy and a 10\% improvement in GSM-IC accuracy over standard supervised fine-tuning with a few codes modified. Furthermore, it is complementary to existing methods. When integrated with related explicit data augmentation methods, it leads to improvements across five datasets of various augmentation methods, as well as two different base models. We further investigate the mechanisms behind this improvement through case studies and quantitative analysis, suggesting that our approach may provide superior support for the model in capturing long-distance dependencies, especially those related to questions. This enhancement could deepen understanding of the premises in questions and prior steps. Our code is available at Github.

Related papers

• Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning [7.702162381335683]
  Step-by-step Chain-of-Thought (CoT) inference has advanced the mathematical capabilities of large language models (LLMs) We propose a novel method called Step Guidance Reasoning without involving further model fine-tuning. Our method significantly improved the math performance, raising the accuracy on the AMC23 dataset from 30% to 57.5%, a relative improvement of 91.7%, and on the sampled level 5 problem of the MATH dataset, we achieved a relative accuracy improvement of 55.8%, increasing from 43% to 67%.
  arXiv  Detail & Related papers  (2024-10-18T01:38:24Z)
• Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization [50.485788083202124]
  Reinforcement Learning (RL) plays a crucial role in aligning large language models with human preferences and improving their ability to perform complex tasks. We introduce Direct Q-function Optimization (DQO), which formulates the response generation process as a Markov Decision Process (MDP) and utilizes the soft actor-critic (SAC) framework to optimize a Q-function directly parameterized by the language model. Experimental results on two math problem-solving datasets, GSM8K and MATH, demonstrate that DQO outperforms previous methods, establishing it as a promising offline reinforcement learning approach for aligning language models.
  arXiv  Detail & Related papers  (2024-10-11T23:29:20Z)
• Building Math Agents with Multi-Turn Iterative Preference Learning [56.71330214021884]
  This paper studies the complementary direct preference learning approach to further improve model performance. Existing direct preference learning algorithms are originally designed for the single-turn chat task. We introduce a multi-turn direct preference learning framework, tailored for this context.
  arXiv  Detail & Related papers  (2024-09-04T02:41:04Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models [15.50128790503447]
  We propose a novel and theoretically motivated methodology for pre-training data detection, named Min-K%++. Specifically, we present a key insight that training samples tend to be local maxima of the modeled distribution along each input dimension through likelihood training.
  arXiv  Detail & Related papers  (2024-04-03T04:25:01Z)
• Large-Scale Meta-Learning with Continual Trajectory Shifting [76.29017270864308]
  We show that allowing the meta-learners to take a larger number of inner gradient steps better captures the structure of heterogeneous and large-scale tasks. In order to increase the frequency of meta-updates, we propose to estimate the required shift of the task-specific parameters. We show that the algorithm largely outperforms the previous first-order meta-learning methods in terms of both generalization performance and convergence.
  arXiv  Detail & Related papers  (2021-02-14T18:36:33Z)
• Logic-Guided Data Augmentation and Regularization for Consistent Question Answering [55.05667583529711]
  This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions. Our method leverages logical and linguistic knowledge to augment labeled training data and then uses a consistency-based regularizer to train the model.
  arXiv  Detail & Related papers  (2020-04-21T17:03:08Z)

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.