English
Related papers

Related papers: Scaling Relationship on Learning Mathematical Reas…

200 papers

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by…

Machine Learning · Computer Science 2024-06-21 Amrith Setlur , Saurabh Garg , Xinyang Geng , Naman Garg , Virginia Smith , Aviral Kumar

Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on…

We introduce compression laws for language language models (LLMs). While recent scaling laws have sought to understand how LLMs scale with respect to model size, pre-training data, and computational resources, we focus on understanding how…

Computation and Language · Computer Science 2025-04-08 Ayan Sengupta , Siddhant Chaudhary , Tanmoy Chakraborty

Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning, significantly improving mathematical and logical problem solving. However, this explicit reasoning process also introduces…

Computation and Language · Computer Science 2025-12-02 Jinghan Jia , Nathalie Baracaldo , Sijia Liu

Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal…

Machine Learning · Computer Science 2025-10-13 Lixuan He , Jie Feng , Yong Li

Pretraining large language models (LLMs) on vast and heterogeneous datasets is crucial for achieving state-of-the-art performance across diverse downstream tasks. However, current training paradigms treat all samples equally, overlooking…

Machine Learning · Computer Science 2025-02-11 Daouda Sow , Herbert Woisetschläger , Saikiran Bulusu , Shiqiang Wang , Hans-Arno Jacobsen , Yingbin Liang

In recent years, language models (LMs) have made remarkable progress in advancing the field of natural language processing (NLP). However, the impact of data augmentation (DA) techniques on the fine-tuning (FT) performance of these LMs has…

Computation and Language · Computer Science 2023-06-14 Zhengxiang Shi , Aldo Lipani

Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems they previously answered correctly during training. We term…

Artificial Intelligence · Computer Science 2025-05-27 Yuetai Li , Zhangchen Xu , Fengqing Jiang , Bhaskar Ramasubramanian , Luyao Niu , Bill Yuchen Lin , Xiang Yue , Radha Poovendran

Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be…

Computation and Language · Computer Science 2025-11-13 Yibai Liu , Shihang Wang , Zeming Liu , Zheming Song , Junzhe Wang , Jingjing Liu , Qingjie Liu , Yunhong Wang

While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samples, leading to data inefficiency. To address this, we…

Machine Learning · Computer Science 2026-04-24 Zehua Liu , Shuqi Liu , Tao Zhong , Mingxuan Yuan

Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning and standard LLMs on…

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But…

Computation and Language · Computer Science 2024-06-11 Ming Li , Yong Zhang , Shwai He , Zhitao Li , Hongyu Zhao , Jianzong Wang , Ning Cheng , Tianyi Zhou

Large language models (LLMs) have demonstrated strong capabilities in programming and mathematical reasoning tasks, but are constrained by limited high-quality training data. Synthetic data can be leveraged to enhance fine-tuning outcomes,…

Machine Learning · Computer Science 2025-04-28 Caia Costello , Simon Guo , Anna Goldie , Azalia Mirhoseini

Long chain-of-thought (CoT) supervision has become a common strategy to enhance reasoning in language models. While effective for large models, we identify a phenomenon we call Long CoT Degradation, in which small language models (SLMs;…

Computation and Language · Computer Science 2025-10-02 Renjie Luo , Jiaxi Li , Chen Huang , Wei Lu

Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While…

Artificial Intelligence · Computer Science 2026-04-21 Justin Bauer , Thomas Walshe , Derek Pham , Harit Vishwakarma , Armin Parchami , Frederic Sala , Paroma Varma

High-quality supervised fine-tuning (SFT) data are crucial for eliciting strong capabilities from pretrained large language models (LLMs). Typically, instructions are paired with multiple responses sampled from other LLMs, which are often…

Computation and Language · Computer Science 2026-01-13 Dylan Zhang , Qirun Dai , Hao Peng

Mathematical reasoning has long represented one of the most fundamental and challenging frontiers in artificial intelligence research. In recent years, large language models (LLMs) have achieved significant advances in this area. This…

Artificial Intelligence · Computer Science 2025-06-11 Peng-Yuan Wang , Tian-Shuo Liu , Chenyang Wang , Yi-Di Wang , Shu Yan , Cheng-Xing Jia , Xu-Hui Liu , Xin-Wei Chen , Jia-Cheng Xu , Ziniu Li , Yang Yu

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…

Computation and Language · Computer Science 2024-07-12 Changyu Chen , Xiting Wang , Ting-En Lin , Ang Lv , Yuchuan Wu , Xin Gao , Ji-Rong Wen , Rui Yan , Yongbin Li

The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. However, unlike the well-established performance improvements…

Artificial Intelligence · Computer Science 2026-04-23 Zihan Chen , Song Wang , Zhen Tan , Xingbo Fu , Zhenyu Lei , Peng Wang , Huan Liu , Cong Shen , Jundong Li

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Machine Learning · Computer Science 2026-03-24 Yuanfu Wang , Zhixuan Liu , Xiangtian Li , Chaochao Lu , Chao Yang