大模型推理能力 - arXivDaily 专题

2501.04425 2025-01-09 cs.CL 57%

End-to-End Bangla AI for Solving Math Olympiad Problem Benchmark: Leveraging Large Language Model Using Integrated Approach

H. M. Shadman Tabib, Jaber Ahmed Deedar

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Journal ref IJNLC,vol:13, Issue:5/6, page 49-59,2024

2501.01433 2025-01-09 cs.AI math.HO 57%

Mathematical Definition and Systematization of Puzzle Rules

Itsuki Maeda, Yasuhiro Inoue

专题命中数学推理：reasoning(abstract)；分类 cs.AI

Comments 16pages

2501.02803 2025-01-07 cs.RO cs.AI 57%

Enhancing Lifelong Multi-Agent Path Finding with Cache Mechanism

Yimin Tang, Zhenghong Yu, Yi Zheng, T. K. Satish Kumar, Jiaoyang Li, Sven Koenig

专题命中数学推理：planning(abstract)；分类 cs.AI

Comments arXiv admin note: substantial text overlap with arXiv:2403.13421

2412.15115 2025-01-06 cs.CL 57%

Qwen2.5 Technical Report

Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei Zhang, Qin Zhu, Rui Men, Runji Lin, Tianhao Li, Tianyi Tang, Tingyu Xia, Xingzhang Ren, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yu Wan, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zihan Qiu

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2501.00747 2025-01-03 cs.CL 57%

DIVE: Diversified Iterative Self-Improvement

Yiwei Qin, Yixiu Liu, Pengfei Liu

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2312.07622 2025-01-03 cs.CL 57%

Mathematical Language Models: A Survey

Wentao Liu, Hanglei Hu, Jie Zhou, Yuyang Ding, Junsong Li, Jiayi Zeng, Mengliang He, Qin Chen, Bo Jiang, Aimin Zhou, Liang He

专题命中数学推理：CoT(abstract)；分类 cs.CL

Comments arXiv admin note: text overlap with arXiv:1705.04146, arXiv:2304.10977, arXiv:2112.00114, arXiv:1905.13319, arXiv:2304.12244, arXiv:2206.01347, arXiv:2006.09265 by other authors

2412.20996 2024-12-31 cs.CL 57%

Plug-and-Play Training Framework for Preference Optimization

Jingyuan Ma, Rui Li, Zheng Li, Lei Sha, Zhifang Sui

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments 12 pages, 9 figures

2410.07985 2024-12-25 cs.CL 57%

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Bofei Gao, Feifan Song, Zhe Yang, Zefan Cai, Yibo Miao, Qingxiu Dong, Lei Li, Chenghao Ma, Liang Chen, Runxin Xu, Zhengyang Tang, Benyou Wang, Daoguang Zan, Shanghaoran Quan, Ge Zhang, Lei Sha, Yichang Zhang, Xuancheng Ren, Tianyu Liu, Baobao Chang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments 30 pages

2410.17413 2024-12-24 cs.CL 57%

Scalable Influence and Fact Tracing for Large Language Model Pretraining

Tyler A. Chang, Dheeraj Rajagopal, Tolga Bolukbasi, Lucas Dixon, Ian Tenney

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2412.15594 2024-12-23 cs.CL 57%

Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation

Xiaoqiang Kang, Zimu Wang, Xiaobo Jin, Wei Wang, Kaizhu Huang, Qiufeng Wang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments Accepted at AAAI 2025, extended version with appendix

2311.09459 2024-12-20 cs.MA cs.LG 57%

On Convex Optimal Value Functions For POSGs

Rafael F. Cunha, Jacopo Castellini, Johan Peralez, Jilles S. Dibangoye

专题命中数学推理：planning(abstract)；分类 cs.LG

Comments Currently under review at JAIR

2412.11699 2024-12-17 cs.CL 57%

CoinMath: Harnessing the Power of Coding Instruction for Math LLMs

Chengwei Wei, Bin Wang, Jung-jae Kim, Guimei Liu, Nancy F. Chen

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2412.09827 2024-12-16 cs.CL cs.CV 57%

Low-Rank Adaptation with Task-Relevant Feature Enhancement for Fine-tuning Language Models

Changqun Li, Chaofan Ding, Kexin Luan, Xinhan Di

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments 6 Pages, 3 figures accepted by AAAI 2025 CoLoRAI - Connecting Low-Rank Representations in AI Workshop

2407.00894 2024-12-12 cs.CL 57%

How to Leverage Digit Embeddings to Represent Numbers?

Jasivan Alex Sivakumar, Nafise Sadat Moosavi

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments Accepted at COLING 2025

2411.18708 2024-12-02 cs.HC cs.AI 57%

Embracing AI in Education: Understanding the Surge in Large Language Model Use by Secondary Students

Tiffany Zhu, Kexun Zhang, William Yang Wang

专题命中数学推理：reasoning(abstract)；分类 cs.AI

Comments 6 main pages, 5 figures

2411.16454 2024-11-26 cs.CL 57%

Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval

Xiaocong Yang, Jiacheng Lin, Ziqi Wang, Chengxiang Zhai

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2411.00406 2024-11-04 cs.LG 57%

MoD: A Distribution-Based Approach for Merging Large Language Models

Quy-Anh Dang, Chris Ngo

专题命中数学推理：reasoning(abstract)；分类 cs.LG

2410.22340 2024-10-31 cs.CY cs.AI 57%

Testing GPT-4-o1-preview on math and science problems: A follow-up study

Ernest Davis

专题命中数学推理：reasoning(abstract)；分类 cs.AI

2405.15179 2024-10-30 cs.CL 57%

VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks

Yang Li, Shaobo Han, Shihao Ji

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments NeurIPS 2024

2406.18853 2024-10-29 cs.LG 57%

Decoding-Time Language Model Alignment with Multiple Objectives

Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hannaneh Hajishirzi, Noah A. Smith, Simon S. Du

专题命中数学推理：CoT(abstract)；分类 cs.LG

Comments NeurIPS accepted version

2410.04834 2024-10-28 cs.CL 57%

As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss

Xin Mao, Feng-Lin Li, Huimin Xu, Wei Zhang, Wang Chen, Anh Tuan Luu

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments 20 pages, 9 figures

2408.05541 2024-10-21 cs.CL 57%

P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training

Yingxuan Yang, Huayi Wang, Muning Wen, Xiaoyun Mo, Qiuying Peng, Jun Wang, Weinan Zhang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

2405.20192 2024-10-18 cs.CL 57%

TAIA: Large Language Models are Out-of-Distribution Data Learners

Shuyang Jiang, Yusheng Liao, Ya Zhang, Yanfeng Wang, Yu Wang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments 29 pages. Accepted as a 2024 NeurIPS paper

2410.07896 2024-10-11 cs.AI 57%

Executing Arithmetic: Fine-Tuning Large Language Models as Turing Machines

Junyu Lai, Jiahe Xu, Yao Yang, Yunpeng Huang, Chun Cao, Jingwei Xu

专题命中数学推理：reasoning(abstract)；分类 cs.AI

Comments 30 pages

2409.12917 2024-10-07 cs.LG 57%

Training Language Models to Self-Correct via Reinforcement Learning

Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal Behbahani, Aleksandra Faust

专题命中数学推理：self-correction(abstract)；分类 cs.LG

2405.14092 2024-10-04 cs.CL 57%

Large Language Models Can Self-Correct with Key Condition Verification

Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, Zhaoxuan Tan, Chao Shen, Meng Jiang

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments EMNLP 2024 - Camera Ready

2410.01748 2024-10-03 cs.LG 57%

Not All LLM Reasoners Are Created Equal

Arian Hosseini, Alessandro Sordoni, Daniel Toyama, Aaron Courville, Rishabh Agarwal

专题命中数学推理：reasoning(abstract)；分类 cs.LG

2404.18384 2024-10-02 cs.CL 57%

Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions

Jordan Meadows, Tamsin James, Andre Freitas

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments EMNLP 2024 (Findings)

2404.09486 2024-09-27 cs.CL cs.CV cs.SE 57%

MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems

Kaixin Li, Yuchen Tian, Qisheng Hu, Ziyang Luo, Zhiyong Huang, Jing Ma

专题命中数学推理：reasoning(abstract)；分类 cs.CL

Comments EMNLP 2024

2409.16779 2024-09-26 cs.AI 57%

LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ

Marc-Antoine Allard, Matin Ansaripour, Maria Yuffa, Paul Teiletche

专题命中数学推理：reasoning(abstract)；分类 cs.AI

1. 数学推理 3246 篇

End-to-End Bangla AI for Solving Math Olympiad Problem Benchmark: Leveraging Large Language Model Using Integrated Approach

Mathematical Definition and Systematization of Puzzle Rules

Enhancing Lifelong Multi-Agent Path Finding with Cache Mechanism

Qwen2.5 Technical Report

DIVE: Diversified Iterative Self-Improvement

Mathematical Language Models: A Survey

Plug-and-Play Training Framework for Preference Optimization

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Scalable Influence and Fact Tracing for Large Language Model Pretraining

Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation

On Convex Optimal Value Functions For POSGs

CoinMath: Harnessing the Power of Coding Instruction for Math LLMs

Low-Rank Adaptation with Task-Relevant Feature Enhancement for Fine-tuning Language Models

How to Leverage Digit Embeddings to Represent Numbers?

Embracing AI in Education: Understanding the Surge in Large Language Model Use by Secondary Students

Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval

MoD: A Distribution-Based Approach for Merging Large Language Models

Testing GPT-4-o1-preview on math and science problems: A follow-up study

VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks

Decoding-Time Language Model Alignment with Multiple Objectives

As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss

P3: A Policy-Driven, Pace-Adaptive, and Diversity-Promoted Framework for data pruning in LLM Training

TAIA: Large Language Models are Out-of-Distribution Data Learners

Executing Arithmetic: Fine-Tuning Large Language Models as Turing Machines

Training Language Models to Self-Correct via Reinforcement Learning

Large Language Models Can Self-Correct with Key Condition Verification

Not All LLM Reasoners Are Created Equal

Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions

MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems

LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ