English
Related papers

Related papers: Debunk the Myth of SFT Generalization

200 papers

In post-training for reasoning Large Language Models (LLMs), the current state of practice trains LLMs in two independent stages: Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR, shortened as ``RL''…

Machine Learning · Computer Science 2025-10-03 Feiyang Kang , Michael Kuchnik , Karthik Padthe , Marin Vlastelica , Ruoxi Jia , Carole-Jean Wu , Newsha Ardalani

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…

Artificial Intelligence · Computer Science 2026-02-17 Anhao Zhao , Ziyang Chen , Junlong Tong , Yingqi Fan , Fanghua Ye , Shuhao Li , Yunpu Ma , Wenjie Li , Xiaoyu Shen

Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…

Artificial Intelligence · Computer Science 2026-05-05 Wangjie Gan , Miao Pan , Linbo Xi , Wenqi Zhang , Jintao Chen , Jianwei Yin , Xuhong Zhang

Training large language models (LLMs) for reasoning via maths and code datasets has become a major new focus in LLM post-training. Two particularly popular approaches are reinforcement learning (RL) and supervised fine-tuning (SFT), but…

Machine Learning · Computer Science 2025-07-28 Neel Rajani , Aryo Pradipta Gema , Seraphina Goldfarb-Tarrant , Ivan Titov

Fine-tuning large language models (LLMs) frequently induces catastrophic forgetting of prior capabilities. Recent work has shown that reinforcement learning (RL) retains prior capabilities more effectively than supervised fine-tuning (SFT),…

Enhancing the complex reasoning capabilities of Large Language Models (LLMs) attracts widespread attention. While reinforcement learning (RL) has shown superior performance for improving complex reasoning, its impact on cross-lingual…

Computation and Language · Computer Science 2025-09-30 Shulin Huang , Yiran Ding , Junshu Pan , Yue Zhang

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Recent advances in large language model (LLM) reasoning have shown that sophisticated behaviors such as planning and self-reflection can emerge through reinforcement learning (RL). However, despite these successes, RL in its current form…

Artificial Intelligence · Computer Science 2026-03-12 Lu Ma , Hao Liang , Meiyi Qiang , Lexiang Tang , Xiaochen Ma , Zhen Hao Wong , Junbo Niu , Chengyu Shen , Runming He , Yanhao Li , Bin Cui , Wentao Zhang

Reinforcement learning (RL) is often credited with improving language model reasoning and generalization at the expense of degrading memorized knowledge. We challenge this narrative by observing that RL-enhanced models consistently…

Computation and Language · Computer Science 2025-11-11 Renfei Zhang , Manasa Kaniselvan , Niloofar Mireshghallah

Reinforcement Learning (RL) has played a central role in the recent surge of LLMs' math abilities by enabling self-improvement through binary verifier signals. In contrast, Supervised Learning (SL) is rarely considered for such…

Machine Learning · Computer Science 2026-03-03 Huayu Chen , Kaiwen Zheng , Qinsheng Zhang , Ganqu Cui , Lifan Yuan , Yin Cui , Haotian Ye , Tsung-Yi Lin , Ming-Yu Liu , Jun Zhu , Haoxiang Wang

Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Among post-training paradigms, supervised fine-tuning (SFT) is widely used: it leverages…

Computation and Language · Computer Science 2026-05-27 Lisong Sun , Li Wang , Chen Zhang , Jinyang Wu , Kui Zhang , Tianhao Peng , Wenjun Wu

One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability,…

Computation and Language · Computer Science 2024-12-16 Trung Quoc Luong , Xinbo Zhang , Zhanming Jie , Peng Sun , Xiaoran Jin , Hang Li

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…

Computation and Language · Computer Science 2025-06-25 Yuqian Fu , Tinghong Chen , Jiajun Chai , Xihuai Wang , Songjun Tu , Guojun Yin , Wei Lin , Qichao Zhang , Yuanheng Zhu , Dongbin Zhao

Large vision-language models (VLMs) increasingly adopt post-training techniques such as long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL) to elicit sophisticated reasoning. While these methods exhibit…

Computation and Language · Computer Science 2025-07-11 Jierun Chen , Tiezheng Yu , Haoli Bai , Lewei Yao , Jiannan Wu , Kaican Li , Fei Mi , Chaofan Tao , Lei Zhu , Manyi Zhang , Xiaohui Li , Lu Hou , Lifeng Shang , Qun Liu

Large Vision-Language Action (VLA) models have shown significant potential for embodied AI. However, their predominant training via supervised fine-tuning (SFT) limits generalization due to susceptibility to compounding errors under…

Machine Learning · Computer Science 2026-01-15 Jijia Liu , Feng Gao , Bingwen Wei , Xinlei Chen , Qingmin Liao , Yi Wu , Chao Yu , Yu Wang

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Computation and Language · Computer Science 2025-02-21 Sonam Gupta , Yatin Nandwani , Asaf Yehudai , Dinesh Khandelwal , Dinesh Raghu , Sachindra Joshi

Supervised and preference-based fine-tuning techniques have become popular for aligning large language models (LLMs) with user intent and correctness criteria. However, real-world training data often exhibits spurious correlations --…

Computation and Language · Computer Science 2025-05-12 Julia Shuieh , Prasann Singhal , Apaar Shanker , John Heyer , George Pu , Samuel Denton

This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing…

Computation and Language · Computer Science 2025-04-17 Hardy Chen , Haoqin Tu , Fali Wang , Hui Liu , Xianfeng Tang , Xinya Du , Yuyin Zhou , Cihang Xie

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…

Computation and Language · Computer Science 2025-07-01 Fei Ding , Baiqiao Wang

Conventionally, supervised fine-tuning (SFT) is treated as a simple imitation learning process that only trains a policy to imitate expert behavior on demonstration datasets. In this work, we challenge this view by establishing a…

Machine Learning · Computer Science 2025-10-06 Jiangnan Li , Thuy-Trang Vu , Ehsan Abbasnejad , Gholamreza Haffari