Improving Cross-Task Generalization with Step-by-Step Instructions
Instruction tuning has been shown to be able to improve cross-task generalization of language models. However, it is still challenging for language models to complete the target tasks following the instructions, as the instructions are general and lack intermediate steps. To address this problem, we propose to incorporate the step-by-step instructions to help language models to decompose the tasks, which can provide the detailed and specific procedures for completing the target tasks. The step-by-step instructions are obtained automatically by prompting ChatGPT, which are further combined with the original instructions to tune language models. The extensive experiments on SUP-NATINST show that the high-quality step-by-step instructions can improve cross-task generalization across different model sizes. Moreover, the further analysis indicates the importance of the order of steps of the step-by-step instruction for the improvement. To facilitate future research, we release the step-by-step instructions and their human quality evaluation results.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models
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 …
Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
As a step towards developing zero-shot task generalization capabilities in reinforcement learning (RL), we introduce a new RL problem where the agent should learn to execute sequences of instructions after learning usefu…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Reinforcement Learning of Implicit and Explicit Control Flow in Instructions
Learning to flexibly follow task instructions in dynamic environments poses interesting challenges for reinforcement learning agents. We focus here on the problem of learning control flow that deviates from a strict step…
Minecraftreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2Language-Guided Long Horizon Manipulation with LLM-based Planning and Visual Perception
Language-guided long-horizon manipulation of deformable objects presents significant challenges due to high degrees of freedom, complex dynamics, and the need for accurate vision-language grounding. In this work, we focu…
Visual GroundingStep-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
Recent advances in large language models (LLMs) have enabled impressive performance in various tasks. However, standard prompting often struggles to produce structurally valid and accurate outputs, especially in dependen…
Dependency ParsingHallucinationPart-Of-Speech Taggingvalid