English
Related papers

Related papers: The Magic Correlations: Understanding Knowledge Tr…

200 papers

This paper explores a scientific question in supervised fine-tuning (SFT): why SFT is broadly effective for small-scale deep neural networks, yet can produce inconsistent or even detrimental effects when applied to large language models…

Artificial Intelligence · Computer Science 2026-05-19 Junpeng Zhang , Lei Cheng , Guoxi Zhang , Hua Cai , Qing Xu , Quanshi Zhang

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the…

Computation and Language · Computer Science 2026-05-05 Zhiwen Ruan , Yichao Du , Jianjie Zheng , Longyue Wang , Yun Chen , Peng Li , Jinsong Su , Yang Liu , Guanhua Chen

Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting.…

Computation and Language · Computer Science 2026-04-29 Dan Shi , Zhuowen Han , Simon Ostermann , Renren Jin , Josef van Genabith , Deyi Xiong

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

As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an effective analysis method for gauging the reliability of…

Computation and Language · Computer Science 2023-11-23 Chiwei Zhu , Benfeng Xu , Quan Wang , Yongdong Zhang , Zhendong Mao

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) are increasingly used in decision-making contexts, but when they present answers without signaling low confidence, users may unknowingly act on erroneous outputs. Prior work shows that LLMs maintain internal…

Computation and Language · Computer Science 2025-10-23 Mark Steyvers , Catarina Belem , Padhraic Smyth

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

Supervised Fine-Tuning (SFT) is a standard approach for injecting domain knowledge into Large Language Models (LLMs). However, relying on validation perplexity to monitor training is often insufficient, as it confounds stylistic mimicry…

Computation and Language · Computer Science 2026-01-08 Soheil Zibakhsh Shabgahi , Pedram Aghazadeh , Farinaz Koushanfar

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Computation and Language · Computer Science 2026-05-12 Guowei Xu , Wenxin Xu , Jiawang Zhao , Kaisheng Ma

Large Language Models (LLMs) face the "knowledge cutoff" challenge, where their frozen parametric memory prevents direct internalization of new information. While Supervised Fine-Tuning (SFT) is commonly used to update model knowledge, it…

Machine Learning · Computer Science 2026-05-12 Pingzhi Tang , Yiding Wang , Muhan Zhang

Large language models have transformed natural language processing, yet supervised fine-tuning (SFT) remains computationally intensive. This paper formally proves that capabilities acquired through SFT can be approximated by a base…

Machine Learning · Computer Science 2025-06-11 Asankhaya Sharma

Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is not memorization itself, but its target: vanilla SFT drives…

Machine Learning · Computer Science 2026-05-26 Ruiying Peng , Mengyu Yang , Jing Lei , Xiaohui Li , Xueyu Wu , Xinlei Chen

Although supervised finetuning (SFT) has emerged as an essential technique to align large language models with humans, it is considered superficial, with style learning being its nature. At the same time, recent works indicate the…

Computation and Language · Computer Science 2024-02-12 Ming Shen

Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for…

Machine Learning · Computer Science 2024-01-05 Shashank Subramanian , Peter Harrington , Kurt Keutzer , Wahid Bhimji , Dmitriy Morozov , Michael Mahoney , Amir Gholami

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

Ensuring that deep learning models are well-calibrated in terms of their predictive uncertainty is essential in maintaining their trustworthiness and reliability, yet despite increasing advances in foundation model research, the…

Computation and Language · Computer Science 2026-01-06 Jerry Huang , Peng Lu , Qiuhao Zeng , Yusuke Iwasawa , Yutaka Matsuo , Sarath Chandar , Edison Marrese-Taylor , Irene Li

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…

Computation and Language · Computer Science 2024-12-18 Yuchen Fan , Yuzhong Hong , Qiushi Wang , Junwei Bao , Hongfei Jiang , Yang Song

The rapid proliferation of generative AI, especially large language models, has led to their integration into a variety of applications. A key phenomenon known as weak-to-strong generalization - where a strong model trained on a weak…

Machine Learning · Computer Science 2025-01-03 Martin Pawelczyk , Lillian Sun , Zhenting Qi , Aounon Kumar , Himabindu Lakkaraju

Supervised fine-tuning (SFT) is the standard approach for post-training large language models (LLMs), yet it often shows limited generalization. We trace this limitation to its default training objective: negative log likelihood (NLL).…

Computation and Language · Computer Science 2026-05-25 Gaotang Li , Ruizhong Qiu , Xiusi Chen , Heng Ji , Hanghang Tong