Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Improving Cross-Task Generalization with Step-by-Step Instructions (2305.04429v1)

Published 8 May 2023 in cs.CL

Abstract: Instruction tuning has been shown to be able to improve cross-task generalization of LLMs. However, it is still challenging for LLMs 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 LLMs 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 LLMs. 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.

Citations (9)

Summary

We haven't generated a summary for this paper yet.