English
Related papers

Related papers: Instruction Tuning Changes How Upstream State Cond…

200 papers

Large language models (LLMs) are increasingly used for automated tutoring, but their reliability in structured symbolic domains remains unclear. We study step-level feedback for propositional logic proofs, which require precise symbolic…

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva

Existing research has shown that a multilingual pre-trained language model fine-tuned with one (source) language also performs well on downstream tasks for non-source languages, even though no fine-tuning is done on these languages.…

Computation and Language · Computer Science 2023-05-22 Yiduo Guo , Yaobo Liang , Dongyan Zhao , Bing Liu , Duan Nan

Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large…

Software Engineering · Computer Science 2023-04-12 Ensheng Shi , Yanlin Wang , Hongyu Zhang , Lun Du , Shi Han , Dongmei Zhang , Hongbin Sun

State-of-the-art cross-encoders can be fine-tuned to be highly effective in passage re-ranking. The typical fine-tuning process of cross-encoders as re-rankers requires large amounts of manually labelled data, a contrastive learning…

Information Retrieval · Computer Science 2025-03-31 Francesca Pezzuti , Sean MacAvaney , Nicola Tonellotto

For long-tailed classification, most works often pretrain a big model on a large-scale dataset, and then fine-tune the whole model for adapting to long-tailed data. Though promising, fine-tuning the whole pretrained model tends to suffer…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Bowen Dong , Pan Zhou , Shuicheng Yan , Wangmeng Zuo

In this work, we introduce Reinforcement Pre-Training (RPT) as a new scaling paradigm for large language models and reinforcement learning (RL). Specifically, we reframe next-token prediction as a reasoning task trained using RL, where it…

Computation and Language · Computer Science 2025-06-10 Qingxiu Dong , Li Dong , Yao Tang , Tianzhu Ye , Yutao Sun , Zhifang Sui , Furu Wei

The two-stage fine-tuning (FT) method, linear probing (LP) then fine-tuning (LP-FT), outperforms linear probing and FT alone. This holds true for both in-distribution (ID) and out-of-distribution (OOD) data. One key reason for its success…

Machine Learning · Computer Science 2024-10-23 Akiyoshi Tomihari , Issei Sato

Debates about large language model post-training often treat supervised fine-tuning (SFT) as imitation and reinforcement learning (RL) as discovery. But this distinction is too coarse. What matters is whether a training procedure increases…

Artificial Intelligence · Computer Science 2026-05-12 Yuhao Li , Shengchao Liu

Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is,…

Computation and Language · Computer Science 2020-10-07 Marius Mosbach , Anna Khokhlova , Michael A. Hedderich , Dietrich Klakow

Model diffing is the study of how fine-tuning changes a model's representations and internal algorithms. Many behaviors of interest are introduced during fine-tuning, and model diffing offers a promising lens to interpret such behaviors.…

Machine Learning · Computer Science 2026-02-23 Julian Minder , Clément Dumas , Caden Juang , Bilal Chugtai , Neel Nanda

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

Computation and Language · Computer Science 2026-04-28 Erfan Baghaei Potraghloo , Seyedarmin Azizi , Souvik Kundu , Massoud Pedram

Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world. Yet, the key factors driving the model's capability to understand and follow…

Computation and Language · Computer Science 2024-06-03 Dylan Zhang , Justin Wang , Francois Charton

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…

Machine Learning · Computer Science 2018-06-07 Xuhong Li , Yves Grandvalet , Franck Davoine

We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task. Deep learning models trained on increasing amounts of data are known to encode societal biases.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Jaspreet Ranjit , Tianlu Wang , Baishakhi Ray , Vicente Ordonez

Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Yuhang Zang , Wei Li , Kaiyang Zhou , Chen Huang , Chen Change Loy

Fine-tuning on task-specific question-answer pairs is a predominant method for enhancing the performance of instruction-tuned large language models (LLMs) on downstream tasks. However, in certain specialized domains, such as healthcare or…

Computation and Language · Computer Science 2024-10-18 Shuyang Jiang , Yusheng Liao , Ya Zhang , Yanfeng Wang , Yu Wang

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…

Computation and Language · Computer Science 2022-07-01 Jingping Liu , Yuqiu Song , Kui Xue , Hongli Sun , Chao Wang , Lihan Chen , Haiyun Jiang , Jiaqing Liang , Tong Ruan

Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding…

Machine Learning · Computer Science 2023-12-29 Aditi Jha , Sam Havens , Jeremy Dohmann , Alex Trott , Jacob Portes

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current…

Machine Learning · Computer Science 2024-06-21 Myeongseob Ko , Feiyang Kang , Weiyan Shi , Ming Jin , Zhou Yu , Ruoxi Jia