English
Related papers

Related papers: First SFT, Second RL, Third UPT: Continual Improvi…

200 papers

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance…

Computation and Language · Computer Science 2024-09-26 Wenwen Zhuang , Xin Huang , Xiantao Zhang , Jin Zeng

Large Language Models (LLMs) are increasingly adopted as evaluators, offering a scalable alternative to human annotation. However, existing supervised fine-tuning (SFT) approaches often fall short in domains that demand complex reasoning.…

Computation and Language · Computer Science 2025-11-04 Nuo Chen , Zhiyuan Hu , Qingyun Zou , Jiaying Wu , Qian Wang , Bryan Hooi , Bingsheng He

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the…

Artificial Intelligence · Computer Science 2026-03-17 Zhijie Wang

Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the…

Computation and Language · Computer Science 2025-03-05 Ke Ji , Jiahao Xu , Tian Liang , Qiuzhi Liu , Zhiwei He , Xingyu Chen , Xiaoyuan Liu , Zhijie Wang , Junying Chen , Benyou Wang , Zhaopeng Tu , Haitao Mi , Dong Yu

Training large language models (LLMs) from scratch is increasingly impractical, making post-training methods such as supervised fine-tuning (SFT) and reinforcement-learning fine-tuning (RL-FT, e.g., PPO) central to modern practice. Using an…

Machine Learning · Computer Science 2025-08-25 Hangzhan Jin , Sicheng Lv , Sifan Wu , Mohammad Hamdaqa

Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications. Pretraining on vast web-scale data has laid the foundation for these models, yet the research community is now…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Computation and Language · Computer Science 2025-10-20 Liang Wang , Nan Yang , Shaohan Huang , Li Dong , Furu Wei

Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this…

Computation and Language · Computer Science 2024-02-20 Zhaorun Chen , Zhuokai Zhao , Zhihong Zhu , Ruiqi Zhang , Xiang Li , Bhiksha Raj , Huaxiu Yao

Recent advances in post-training techniques have endowed Large Language Models (LLMs) with enhanced capabilities for tackling complex, logic-intensive tasks through the generation of supplementary planning tokens. This development raises a…

Computation and Language · Computer Science 2026-04-29 Pratham Singla , Shivank Garg , Ayush Singh , Ishan Garg , Ketan Suhaas Saichandran

Recent progress in (multimodal) large language models ((M)LLMs) has shifted focus from pre-training to inference-time computation and post-training optimization, largely due to concerns over the availability of high-quality human data.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Xiaoying Zhang , Da Peng , Yipeng Zhang , Zonghao Guo , Chengyue Wu , Jen-Tse Huang , Chi Chen , Wei Ke , Helen Meng , Maosong Sun

Can language models improve their reasoning performance without external rewards, using only their own sampled responses for training? We show that they can. We propose Self-evolving Post-Training (SePT), a simple post-training method that…

Machine Learning · Computer Science 2026-05-18 Mengqi Li , Lei Zhao , Anthony Man-Cho So , Ruoyu Sun , Xiao Li

Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs). However, acquiring human-authored rationales or augmenting rationales from proprietary…

Computation and Language · Computer Science 2024-10-04 Hyeonbin Hwang , Doyoung Kim , Seungone Kim , Seonghyeon Ye , Minjoon Seo

Previous study suggest that powerful Large Language Models (LLMs) trained with Reinforcement Learning with Verifiable Rewards (RLVR) only refines reasoning path without improving the reasoning capacity in math tasks while…

Computation and Language · Computer Science 2025-05-29 Ran Li , Shimin Di , Yuchen Liu , Chen Jing , Yu Qiu , Lei Chen

Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which is a fundamental…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Qi Wang , Yanrui Yu , Ye Yuan , Rui Mao , Tianfei Zhou

Process Reward Models (PRMs) are a powerful mechanism for steering large language model reasoning by providing fine-grained, step-level supervision. However, this effectiveness comes at a significant cost: PRMs require expert annotations…

Machine Learning · Computer Science 2026-05-12 Artyom Gadetsky , Maxim Kodryan , Siba Smarak Panigrahi , Hang Guo , Maria Brbic

Large Language Models (LLMs) have achieved excellent performances in various tasks. However, fine-tuning an LLM requires extensive supervision. Human, on the other hand, may improve their reasoning abilities by self-thinking without…

Computation and Language · Computer Science 2022-10-26 Jiaxin Huang , Shixiang Shane Gu , Le Hou , Yuexin Wu , Xuezhi Wang , Hongkun Yu , Jiawei Han

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for…

Computation and Language · Computer Science 2026-02-04 Yufan Zhuang , Chandan Singh , Liyuan Liu , Yelong Shen , Dinghuai Zhang , Jingbo Shang , Jianfeng Gao , Weizhu Chen

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

Computation and Language · Computer Science 2025-09-30 Yijun Tian , Shaoyu Chen , Zhichao Xu , Yawei Wang , Jinhe Bi , Peng Han , Wei Wang

Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can then be fine-tuned for the question-answering (QA) task. However, effective strategies for fine-tuning LLMs for the QA task…

Computation and Language · Computer Science 2025-01-22 Junjie Ye , Yuming Yang , Qi Zhang , Tao Gui , Xuanjing Huang , Peng Wang , Zhongchao Shi , Jianping Fan

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Machine Learning · Computer Science 2025-12-22 Mingyu Su , Jian Guan , Yuxian Gu , Minlie Huang , Hongning Wang