English
Related papers

Related papers: MathMixup: Boosting LLM Mathematical Reasoning wit…

200 papers

In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstration examples. Previous methods typically relied on simple…

Computation and Language · Computer Science 2026-01-06 Xuetao Ma , Wenbin Jiang , Hua Huang

Exceptional mathematical reasoning ability is one of the key features that demonstrate the power of large language models (LLMs). How to comprehensively define and evaluate the mathematical abilities of LLMs, and even reflect the user…

Computation and Language · Computer Science 2024-10-10 Zihao Zhou , Shudong Liu , Maizhen Ning , Wei Liu , Jindong Wang , Derek F. Wong , Xiaowei Huang , Qiufeng Wang , Kaizhu Huang

Enhancing the ability of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) to interpret sheet music is a crucial step toward building AI musicians. However, current research lacks both evaluation benchmarks and…

Computation and Language · Computer Science 2025-09-29 Zhilin Wang , Zhe Yang , Yun Luo , Yafu Li , Xiaoye Qu , Ziqian Qiao , Haoran Zhang , Runzhe Zhan , Derek F. Wong , Jizhe Zhou , Yu Cheng

How can "weak teacher models" such as average human annotators or existing AI systems, effectively supervise LLMs to improve performance on hard reasoning tasks, especially those that challenge and requires expertise or daily practice from…

Machine Learning · Computer Science 2025-02-26 Xuan He , Da Yin , Nanyun Peng

Ensuring large language model (LLM) reliability requires distinguishing objective unsolvability (inherent contradictions) from subjective capability limitations (tasks exceeding model competence). Current LLMs often conflate these…

Computation and Language · Computer Science 2026-02-03 Dengyun Peng , Qiguang Chen , Bofei Liu , Jiannan Guan , Libo Qin , Zheng Yan , Jinhao Liu , Jianshu Zhang , Wanxiang Che

Large Language Models (LLMs) exhibit strong potential in mathematical reasoning, yet their effectiveness is often limited by a shortage of high-quality queries. This limitation necessitates scaling up computational responses through…

Artificial Intelligence · Computer Science 2025-05-20 Jingyue Gao , Runji Lin , Keming Lu , Bowen Yu , Junyang Lin , Jianyu Chen

Existing approaches typically rely on large-scale fine-tuning to adapt LLMs for information reranking tasks, which is computationally expensive. In this work, we demonstrate that modern LLMs can be effectively adapted using only minimal,…

Computation and Language · Computer Science 2025-10-28 Tingyu Song , Yilun Zhao , Siyue Zhang , Chen Zhao , Arman Cohan

Large Language Models (LLMs) with extended context windows promise direct reasoning over long documents, reducing the need for chunking or retrieval. Constructing annotated resources for training and evaluation, however, remains costly.…

Computation and Language · Computer Science 2025-11-13 Mohamed Elaraby , Jyoti Prakash Maheswari

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…

Artificial Intelligence · Computer Science 2025-11-11 Jinhao Chen , Zhen Yang , Jianxin Shi , Tianyu Wo , Jie Tang

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced recipe that begins with instruct models and applies…

Computation and Language · Computer Science 2025-10-13 Changjiang Gao , Zixian Huang , Jingyang Gong , Shujian Huang , Lei Li , Fei Yuan

Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited. To address this, we propose a novel framework HDFlow…

Computation and Language · Computer Science 2024-09-27 Wenlin Yao , Haitao Mi , Dong Yu

Increasing interest in reasoning models has led math to become a prominent testing ground for algorithmic and methodological improvements. However, existing open math datasets either contain a small collection of high-quality, human-written…

Despite the impressive performance of large language models (LLMs) in general domains, they often underperform in specialized domains. Existing approaches typically rely on data synthesis methods and yield promising results by using…

Computation and Language · Computer Science 2025-07-25 Xiaopeng Ke , Hexuan Deng , Xuebo Liu , Jun Rao , Zhenxi Song , Jun Yu , Min Zhang

This study focuses on improving the performance of lightweight Large Language Models (LLMs) in mathematical reasoning tasks. We introduce a novel method for measuring mathematical logic similarity and design an automatic screening mechanism…

Computation and Language · Computer Science 2024-09-04 Ding Kai , Ma Zhenguo , Yan Xiaoran

Mathematical reasoning is an important research direction in the field of artificial intelligence. This article proposes a novel multi tool application framework for mathematical reasoning, aiming to achieve more comprehensive and accurate…

Artificial Intelligence · Computer Science 2024-08-23 Zhihua Duan , Jialin Wang

The Mixup method (Zhang et al. 2018), which uses linearly interpolated data, has emerged as an effective data augmentation tool to improve generalization performance and the robustness to adversarial examples. The motivation is to curtail…

Machine Learning · Computer Science 2020-12-25 Minjin Kim , Young-geun Kim , Dongha Kim , Yongdai Kim , Myunghee Cho Paik

Large-scale, high-quality data is essential for advancing the reasoning capabilities of large language models (LLMs). As publicly available Internet data becomes increasingly scarce, synthetic data has emerged as a crucial research…

Computation and Language · Computer Science 2025-09-23 Jiankang Wang , Jianjun Xu , Xiaorui Wang , Yuxin Wang , Mengting Xing , Shancheng Fang , Hongtao Xie

Instruction tuning improves the reasoning abilities of large language models (LLMs), with data quality and scalability being the crucial factors. Most instruction tuning data come from human crowd-sourcing or GPT-4 distillation. We propose…

Computation and Language · Computer Science 2024-05-24 Xiang Yue , Tuney Zheng , Ge Zhang , Wenhu Chen

This paper presents a practical investigation into fine-tuning model parameters for mathematical reasoning tasks through experimenting with various configurations including randomness control, reasoning depth, and sampling strategies,…

Machine Learning · Computer Science 2025-09-10 Pranav Pawar , Dhwaj Jain , Varun Gupta , Kaustav Dedhia , Dashrath Kale , Sudhir Dhekane