Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning
Preprint
Abstract
Large language models (LLMs) have shown impressive performance in following natural language instructions to solve unseen tasks. However, it remains unclear whether models truly understand task definitions and whether the human-written definitions are optimal. In this paper, we systematically study the role of task definitions in instruction learning. We first conduct an ablation analysis informed by human annotations to understand which parts of a task definition are most important, and find that model performance only drops substantially when removing contents describing the task output, in particular label information. Next, we propose an automatic algorithm to compress task definitions to a minimal supporting set of tokens, and find that 60\% of tokens can be removed while maintaining or even improving model performance. Based on these results, we propose two strategies to help models better leverage task instructions: (1) providing only key information for tasks in a common structured format, and (2) adding a meta-tuning stage to help the model better understand the definitions. With these two strategies, we achieve a 4.2 Rouge-L improvement over 119 unseen test tasks.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models2023
- Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning2023
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2023
- Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor2023
- RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning2022
- Do Prompt-Based Models Really Understand the Meaning of Their Prompts?2022
- Reframing Instructional Prompts to GPTk’s Language2022
- Cross-Task Generalization via Natural Language Crowdsourcing Instructions2022