English
Related papers

Related papers: Mitigating Forgetting Between Supervised and Reinf…

200 papers

Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective…

Computation and Language · Computer Science 2025-06-03 Fangyu Lei , Jinxiang Meng , Yiming Huang , Tinghong Chen , Yun Zhang , Shizhu He , Jun Zhao , Kang Liu

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Machine Learning · Computer Science 2025-09-22 Shiwan Zhao , Xuyang Zhao , Jiaming Zhou , Aobo Kong , Qicheng Li , Yong Qin

Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…

Machine Learning · Computer Science 2026-04-13 Taojie Zhu , Dongyang Xu , Ding Zou , Sen Zhao , Qiaobo Hao , Zhiguo Yang , Yonghong He

Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However, their capacity for visual semantic arithmetic, inferring relationships from images,…

Artificial Intelligence · Computer Science 2026-04-22 Chuou Xu , Liya Ji , Qifeng Chen

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

Artificial Intelligence · Computer Science 2024-10-07 Ju-Seung Byun , Jiyun Chun , Jihyung Kil , Andrew Perrault

Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetuning with the same optimizer as in pretraining achieves a…

Machine Learning · Computer Science 2026-05-08 Yuxing Liu , Jianyu Wang , Tong Zhang

Large language models (LLMs) have made rapid progress, yet adapting them to downstream scenarios still commonly relies on supervised fine-tuning (SFT). When downstream data exhibit a substantial distribution shift from the model's prior…

Machine Learning · Computer Science 2026-02-13 Jiacheng Wang , Ping Jian , Zhen Yang , Zirong Chen , Keren Liao , Zhongbin Guo

Although many efforts have been made, it is still a challenge to balance the training budget, downstream performance, and the general capabilities of the LLMs in many applications. Training the whole model for downstream tasks is expensive,…

Machine Learning · Computer Science 2025-01-29 Jiayi Han , Liang Du , Hongwei Du , Xiangguo Zhou , Yiwen Wu , Weibo Zheng , Donghong Han

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

Computation and Language · Computer Science 2024-10-08 Yiming Ju , Ziyi Ni , Xingrun Xing , Zhixiong Zeng , hanyu Zhao , Siqi Fan , Zheng Zhang

Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples. Specifically,…

Machine Learning · Computer Science 2025-05-22 Rohan Deb , Kiran Thekumparampil , Kousha Kalantari , Gaurush Hiranandani , Shoham Sabach , Branislav Kveton

Parameter-Efficient Fine-Tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), are indispensable for efficiently customizing Large Language Models (LLMs). However, vanilla LoRA suffers from slow convergence speed and knowledge…

Machine Learning · Computer Science 2025-11-03 Minrui Luo , Fuhang Kuang , Yu Wang , Zirui Liu , Tianxing He

In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…

Information Retrieval · Computer Science 2025-09-22 Haowei Liu , Xuyang Wu , Guohao Sun , Zhiqiang Tao , Yi Fang

Large Language Models (LLMs) demand significant computational resources, making it essential to enhance their capabilities without retraining from scratch. A key challenge in this domain is \textit{catastrophic forgetting} (CF), which…

Machine Learning · Computer Science 2025-01-31 Haichao Wei , Yunxiang Ren , Zhoutong Fu , Aman Lunia , Yi-Lin Chen , Alice Leung , Ya Xu

Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from receiving meaningful positive feedback. At the same time,…

Machine Learning · Computer Science 2026-03-06 Yangzhen Wu , Shanda Li , Zixin Wen , Xin Zhou , Ameet Talwalkar , Yiming Yang , Wenhao Huang , Tianle Cai

Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential…

Machine Learning · Computer Science 2026-01-21 Quy-Anh Dang , Chris Ngo

Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improves accuracy, it can degrade reasoning. We propose a two-stage approach: SFT on disease…

Artificial Intelligence · Computer Science 2026-04-22 Yishu Wei , Yi Lin , Adam Flanders , George Shih , Yifan Peng

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

Computation and Language · Computer Science 2025-05-26 Xiang Liu , Zhaoxiang Liu , Peng Wang , Kohou Wang , Huan Hu , Kai Wang , Shiguo Lian

Pretrained on large-scale and diverse datasets, VLA models demonstrate strong generalization and adaptability as general-purpose robotic policies. However, Supervised Fine-Tuning (SFT), which serves as the primary mechanism for adapting…

Robotics · Computer Science 2026-05-19 Yuan Liu , Haoran Li , Shuai Tian , Yuxing Qin , Yuhui Chen , Yupeng Zheng , Yongzhen Huang , Dongbin Zhao

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

Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement learning (RL) with verifiable signals or supervised…

Computation and Language · Computer Science 2026-03-17 Yige Yuan , Teng Xiao , Shuchang Tao , Xue Wang , Jinyang Gao , Bolin Ding , Bingbing Xu