REVIEW 5 cited by
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Mathematical reasoning is an important capability of large language models~(LLMs) for real-world applications. To enhance this capability, existing work either collects large-scale math-related texts for pre-training, or relies on stronger LLMs (\eg GPT-4) to synthesize massive math problems. Both types of work generally lead to large costs in training or synthesis. To reduce the cost, based on open-source available texts, we propose an efficient way that trains a small LLM for math problem synthesis, to efficiently generate sufficient high-quality pre-training data. To achieve it, we create a dataset using GPT-4 to distill its data synthesis capability into the small LLM. Concretely, we craft a set of prompts based on human education stages to guide GPT-4, to synthesize problems covering diverse math knowledge and difficulty levels. Besides, we adopt the gradient-based influence estimation method to select the most valuable math-related texts. The both are fed into GPT-4 for creating the knowledge distillation dataset to train the small LLM. We leverage it to synthesize 6 million math problems for pre-training our JiuZhang3.0 model, which only needs to invoke GPT-4 API 9.3k times and pre-train on 4.6B data. Experimental results have shown that JiuZhang3.0 achieves state-of-the-art performance on several mathematical reasoning datasets, under both natural language reasoning and tool manipulation settings. Our code and data will be publicly released in \url{https://github.com/RUCAIBox/JiuZhang3.0}.
Forward citations
Cited by 5 Pith papers
-
Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation
Step-Opt, a LLaMA-3-8B model fine-tuned on iteratively evolved and stepwise-validated data, reports state-of-the-art accuracy on NL4OPT, MAMO, and IndustryOR.
-
Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks
PIE, a code-generation framework with pseudocode injection and interpreter execution, outperforms five text-based LLM graph-reasoning baselines in accuracy and cost.
-
YuLan-Mini: An Open Data-efficient Language Model
A 2.42B-parameter base model trained on 1.08T tokens matches or beats several industry baselines trained on 7T to 18T tokens across math, code, and general benchmarks.
-
Enhancing LLM Reasoning with Reward-guided Tree Search
A reward-guided tree search framework improves LLaMA-3.1-8B math reasoning accuracy on four benchmarks over CoT and best-of-N baselines.
-
A Survey on Large Language Models for Mathematical Reasoning
Recent advances in LLM mathematical reasoning are organized into comprehension and generation phases, covering methods from prompting to test-time scaling.
Discussion (0). Continue with ORCID to comment.