English
Related papers

Related papers: Learning to Adapt SFT Data for Better Reasoning Ge…

200 papers

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches…

Computation and Language · Computer Science 2025-01-28 Leonardo Ranaldi , Andrè Freitas

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

Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Bac Nguyen , Stefan Uhlich , Fabien Cardinaux , Lukas Mauch , Marzieh Edraki , Aaron Courville

Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-based approaches appear limited in alleviating this bias. We…

General Finance · Quantitative Finance 2026-05-05 Zhenyu Gao , Wenxi Jiang , Yutong Yan

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 language models (LLMs) tuned for safety often avoid acknowledging demographic differences, even when such acknowledgment is factually correct (e.g., ancestry-based disease incidence) or contextually justified (e.g., religious hiring…

Computation and Language · Computer Science 2026-04-21 Ziwen Pan , Zihan Liang , Jad Kabbara , Ali Emami

Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-scale multimodal reasoning data or reinforcement learning,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Chao Huang , Zeliang Zhang , Jiang Liu , Ximeng Sun , Jialian Wu , Xiaodong Yu , Ze Wang , Chenliang Xu , Emad Barsoum , Zicheng Liu

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Machine Learning · Computer Science 2026-02-10 Zahra Rahimi Afzal , Tara Esmaeilbeig , Mojtaba Soltanalian , Mesrob I. Ohannessian

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Machine Learning · Computer Science 2026-01-22 Song Lai , Haohan Zhao , Rong Feng , Changyi Ma , Wenzhuo Liu , Hongbo Zhao , Xi Lin , Dong Yi , Qingfu Zhang , Hongbin Liu , Gaofeng Meng , Fei Zhu

Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), optimize the…

Machine Learning · Computer Science 2026-05-21 Adam Ousherovitch , Ambuj Tewari

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 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 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

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…

Computation and Language · Computer Science 2025-10-07 Xiangchi Yuan , Xiang Chen , Tong Yu , Dachuan Shi , Can Jin , Wenke Lee , Saayan Mitra

Length generalization, the ability to solve problems longer than those seen during training, remains a critical challenge for large language models (LLMs). Previous work modifies positional encodings (PEs) and data formats to improve length…

Computation and Language · Computer Science 2025-05-20 Yi Hu , Shijia Kang , Haotong Yang , Haotian Xu , Muhan Zhang

Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a…

Computation and Language · Computer Science 2026-03-24 Hongyu Cao , Kunpeng Liu , Dongjie Wang , Yanjie Fu

Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious…

Computation and Language · Computer Science 2024-10-08 Joykirat Singh , Subhabrata Dutta , Tanmoy Chakraborty

We consider the problem of OOD generalization, where the goal is to train a model that performs well on test distributions that are different from the training distribution. Deep learning models are known to be fragile to such shifts and…

Machine Learning · Computer Science 2022-08-22 Anshul Nasery , Sravanti Addepalli , Praneeth Netrapalli , Prateek Jain

High-quality supervised fine-tuning (SFT) data are crucial for eliciting strong capabilities from pretrained large language models (LLMs). Typically, instructions are paired with multiple responses sampled from other LLMs, which are often…

Computation and Language · Computer Science 2026-01-13 Dylan Zhang , Qirun Dai , Hao Peng

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Machine Learning · Computer Science 2025-10-14 Jinyang Zhang , Yue Fang , Hongxin Ding , Weibin Liao , Muyang Ye , Xu Chu , Junfeng Zhao , Yasha Wang