paper-with-me

홈 › Papers

Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention

2025-08-03 · Xinhan Di, JoyJiaoW arxiv

Reinforcement learning scaling enhances the reasoning capabilities of large language models, with reinforcement learning serving as the key technique to draw out complex reasoning. However, key technical details of state-of-the-art reasoning LLMs, such as those in the OpenAI O series, Claude 3 series, DeepMind's Gemini 2.5 series, and Grok 3 series, remain undisclosed, making it difficult for the research community to replicate their reinforcement learning training results. Therefore, we start our study from an Early Preview Reinforcement Learning (EPRLI) algorithm built on the open-source GRPO framework, incorporating difficulty-aware intervention for math problems. Applied to a 1.5B-parameter LLM, our method achieves 50.0% on AIME24, 89.2% on Math500, 77.1% on AMC, 35.3% on Minerva, and 51.9% on OBench, superpass O1-Preview and is comparable to O1-mini within standard school-lab settings.

📄 PDF Abstract BibTeX arXiv:2508.01604

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language Models

2025-07-03 · Boyang Xue, Qi Zhu, Rui Wang, Sheng Wang 외 arxiv

Although demonstrating remarkable performance on reasoning tasks, Large Language Models (LLMs) still tend to fabricate unreliable responses when confronted with problems that are unsolvable or beyond their capability, se…

Mathematical Reasoning

JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation

2025-11-20 · Zhenyu Bi, Gaurav Srivastava, Yang Li, Meng Lu 외 arxiv

While small language models (SLMs) have shown promise on various reasoning tasks, their ability to judge the correctness of answers remains unclear compared to large language models (LLMs). Prior work on LLM-as-a-judge f…

Mathematical Reasoning

CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning

2024-10-03 · Huimu Yu, Xing Wu, Weidong Yin, Debing Zhang 외

Large language models (LLMs) have made significant progress in natural language understanding and generation, driven by scalable pretraining and advanced finetuning. However, enhancing reasoning abilities in LLMs, partic…

GSM8KLanguage ModelingLanguage ModellingLarge Language Model+5

Weaker LLMs' Opinions Also Matter: Mixture of Opinions Enhances LLM's Mathematical Reasoning

2025-02-26 · Yanan Chen, Ali Pesaranghader, Tanmana Sadhu

Recent advances in Large Language Models (LLMs) have raised interest in their formal reasoning capabilities, particularly in mathematics. While closed LLMs like GPT-4 perform well on mathematical benchmarks, e.g., GSM8K,…

GSM8KMathematical Reasoning

Cascaded Self-Evaluation Augmented Training for Efficient Multimodal Large Language Models

2025-01-10 · Zheqi Lv, Wenkai Wang, Jiawei Wang, Shengyu Zhang 외

Efficient Multimodal Large Language Models (EMLLMs) have rapidly advanced recently. Incorporating Chain-of-Thought (CoT) reasoning and step-by-step self-evaluation has improved their performance. However, limited paramet…

Math