English
Related papers

Related papers: Instruction Following without Instruction Tuning

200 papers

Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks. Previously, for zero-shot cross-lingual evaluation,…

Computation and Language · Computer Science 2022-12-14 Lifu Tu , Caiming Xiong , Yingbo Zhou

Recently, pretrained language models (PLMs) have had exceptional success in language generation. To leverage the rich knowledge encoded by PLMs, a simple yet powerful paradigm is to use prompts in the form of either discrete tokens or…

Computation and Language · Computer Science 2022-10-04 Tianyi Tang , Junyi Li , Wayne Xin Zhao , Ji-Rong Wen

This paper describes an alignment-based model for interpreting natural language instructions in context. We approach instruction following as a search over plans, scoring sequences of actions conditioned on structured observations of text…

Computation and Language · Computer Science 2017-04-14 Jacob Andreas , Dan Klein

In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct high-quality instruction datasets, many instruction processing…

Computation and Language · Computer Science 2024-06-25 Yixin Ou , Ningyu Zhang , Honghao Gui , Ziwen Xu , Shuofei Qiao , Yida Xue , Runnan Fang , Kangwei Liu , Lei Li , Zhen Bi , Guozhou Zheng , Huajun Chen

Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks. However, most existing instruction datasets include only single…

Computation and Language · Computer Science 2025-01-07 Shirley Anugrah Hayati , Taehee Jung , Tristan Bodding-Long , Sudipta Kar , Abhinav Sethy , Joo-Kyung Kim , Dongyeop Kang

Instruction fine-tuning (IFT) elicits instruction following capabilities and steers the behavior of large language models (LLMs) via supervised learning. However, existing models trained on open-source IFT datasets only have the ability to…

Computation and Language · Computer Science 2024-09-24 Kuan Wang , Alexander Bukharin , Haoming Jiang , Qingyu Yin , Zhengyang Wang , Tuo Zhao , Jingbo Shang , Chao Zhang , Bing Yin , Xian Li , Jianshu Chen , Shiyang Li

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

Machine Learning · Computer Science 2026-03-03 Vivswan Shah , Randy Cogill , Hanwei Yue , Gopinath Chennupati , Rinat Khaziev

Multi-task learning (MTL), instruction tuning, and prompting have recently been shown to improve the generalizability of large language models to new tasks. However, the benefits of such methods are less well-documented in smaller language…

Computation and Language · Computer Science 2022-10-11 Alon Albalak , Akshat Shrivastava , Chinnadhurai Sankar , Adithya Sagar , Mike Ross

We propose structured prompt tuning, a simple and effective method to improve prompt tuning. Instead of prepending a sequence of tunable embeddings to the input, we generate the soft prompt embeddings through a hypernetwork. Our approach…

Computation and Language · Computer Science 2022-05-26 Chi-Liang Liu , Hung-yi Lee , Wen-tau Yih

In many real-world applications, users rely on natural language instructions to guide large language models (LLMs) across a wide range of tasks. These instructions are often complex, diverse, and subject to frequent change. However, LLMs do…

Machine Learning · Computer Science 2026-01-27 Praveen Venkateswaran , Danish Contractor

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…

Computation and Language · Computer Science 2021-09-09 Ruiqi Zhong , Kristy Lee , Zheng Zhang , Dan Klein

Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model into strong language model without preference data. However, the theoretical foundations for…

Machine Learning · Computer Science 2026-02-03 Shangzhe Li , Xuchao Zhang , Chetan Bansal , Weitong Zhang

Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to…

Machine Learning · Computer Science 2023-05-02 Korawat Tanwisuth , Shujian Zhang , Huangjie Zheng , Pengcheng He , Mingyuan Zhou

Automatic evaluation of natural language generation has long been an elusive goal in NLP.A recent paradigm fine-tunes pre-trained language models to emulate human judgements for a particular task and evaluation criterion. Inspired by the…

Computation and Language · Computer Science 2023-11-01 Shuhaib Mehri , Vered Shwartz

We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, starts with a language…

Computation and Language · Computer Science 2024-03-13 Xian Li , Ping Yu , Chunting Zhou , Timo Schick , Omer Levy , Luke Zettlemoyer , Jason Weston , Mike Lewis

Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable zero-shot capabilities on new tasks, and no human-written instructions are…

Computation and Language · Computer Science 2023-04-07 Baolin Peng , Chunyuan Li , Pengcheng He , Michel Galley , Jianfeng Gao

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…

Machine Learning · Computer Science 2026-05-21 Lukas Twist , Helen Yannakoudakis , Jie M. Zhang

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…

Computation and Language · Computer Science 2023-10-09 Zhengxiang Shi , Aldo Lipani

Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…

Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning. Using a large pre-trained language model (PLM), prefix-tuning can obtain strong performance by training…

Computation and Language · Computer Science 2022-10-27 Yifan Chen , Devamanyu Hazarika , Mahdi Namazifar , Yang Liu , Di Jin , Dilek Hakkani-Tur