中文
相关论文

相关论文: TMS: Trajectory-Mixed Supervision for Reward-Free,…

200 篇论文

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…

机器学习 · 计算机科学 2025-10-13 Lixuan He , Jie Feng , Yong Li

Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substantially improve reasoning, they struggle to expand reasoning…

计算与语言 · 计算机科学 2025-10-07 Xiangchi Yuan , Xiang Chen , Tong Yu , Dachuan Shi , Can Jin , Wenke Lee , Saayan Mitra

Test-time scaling (TTS) for large language models (LLMs) has thus far fallen into two largely separate paradigms: (1) reinforcement learning (RL) methods that optimize sparse outcome-based rewards, yet suffer from instability and low sample…

Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT)…

人工智能 · 计算机科学 2026-03-17 Haitao Jiang , Wenbo Zhang , Jiarui Yao , Hengrui Cai , Sheng Wang , Rui Song

Large reasoning models (LRMs) are commonly trained with reinforcement learning (RL) to explore long chain-of-thought reasoning, achieving strong performance at high computational cost. Recent methods add multi-reward objectives to jointly…

人工智能 · 计算机科学 2026-02-17 Anhao Zhao , Ziyang Chen , Junlong Tong , Yingqi Fan , Fanghua Ye , Shuhao Li , Yunpu Ma , Wenjie Li , Xiaoyu Shen

Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this…

机器学习 · 计算机科学 2025-12-04 Howard Chen , Noam Razin , Karthik Narasimhan , Danqi Chen

Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through comprehensive analysis…

计算与语言 · 计算机科学 2025-06-25 Yuqian Fu , Tinghong Chen , Jiajun Chai , Xihuai Wang , Songjun Tu , Guojun Yin , Wei Lin , Qichao Zhang , Yuanheng Zhu , Dongbin Zhao

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

机器学习 · 计算机科学 2026-03-02 Yongliang Wu , Yizhou Zhou , Zhou Ziheng , Yingzhe Peng , Xinyu Ye , Xinting Hu , Wenbo Zhu , Lu Qi , Ming-Hsuan Yang , Xu Yang

Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away from the supervised fine-tuning (SFT) paradigm. Many studies…

Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity…

计算与语言 · 计算机科学 2026-02-03 Rui Ming , Haoyuan Wu , Shoubo Hu , Zhuolun He , Bei Yu

Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits…

人工智能 · 计算机科学 2026-03-04 Siwei Wang , Yifei Shen , Haoran Sun , Shi Feng , Shang-Hua Teng , Li Dong , Yaru Hao , Wei Chen

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

计算与语言 · 计算机科学 2025-10-29 ChangSu Choi , Hoyun Song , Dongyeon Kim , WooHyeon Jung , Minkyung Cho , Sunjin Park , NohHyeob Bae , Seona Yu , KyungTae Lim

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Reward models are central to both reinforcement learning (RL) with language models and inference-time verification. However, existing reward models often lack temporal consistency, leading to ineffective policy updates and unstable RL…

机器学习 · 计算机科学 2025-09-30 Dan Zhang , Min Cai , Jonathan Light , Ziniu Hu , Yisong Yue , Jie Tang

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…

机器学习 · 计算机科学 2025-12-22 Mingyu Su , Jian Guan , Yuxian Gu , Minlie Huang , Hongning Wang

Extending large language models (LLMs) to low-resource languages often incurs an "alignment tax": improvements in the target language come at the cost of catastrophic forgetting in general capabilities. We argue that this trade-off arises…

计算与语言 · 计算机科学 2026-05-15 Zeli Su , Ziyin Zhang , Zhou Liu , Xuexian Song , Zhankai Xu , Longfei Zheng , Xiaolu Zhang , Rong Fu , Guixian Xu , Wentao Zhang

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL's use of on-policy data. We propose a framework to bridge this…

机器学习 · 计算机科学 2026-03-17 Miaosen Zhang , Yishan Liu , Shuxia Lin , Xu Yang , Qi Dai , Chong Luo , Weihao Jiang , Peng Hou , Anxiang Zeng , Xin Geng , Baining Guo

Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs) and adapting them to specialized domains. However, SFT often leads to a degradation of the model's general…

计算与语言 · 计算机科学 2025-07-01 Fei Ding , Baiqiao Wang

Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimizes the cross-entropy loss between model outputs and expert…

机器学习 · 计算机科学 2026-05-07 Xueyan Niu , Bo Bai , Wei Han , Weixi Zhang
‹ 上一页 1 2 3 10 下一页 ›