https://scholars.lib.ntu.edu.tw/handle/123456789/640564
標題: | SELF-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations | 作者: | Chen, Wei Lin Wu, Cheng Kuang YUN-NUNG CHEN HSIN-HSI CHEN |
公開日期: | 1-一月-2023 | 來源出版物: | EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings | 摘要: | Large language models (LLMs) have exhibited striking in-context learning (ICL) ability to adapt to target tasks with a few input-output demonstrations. For better ICL, different methods are proposed to select representative demonstrations from existing training corpora. However, such settings are not aligned with real-world practices, as end-users usually query LMs without access to demonstration pools. In this work, we introduce SELF-ICL-a simple framework which bootstraps LMs' intrinsic capabilities to perform zero-shot ICL. Given a test input, SELF-ICL first prompts the model to generate pseudo-inputs. Next, the model predicts pseudo-labels for the pseudo-inputs via zero-shot prompting. Finally, we perform ICL for the test input with the pseudo-input-label pairs as demonstrations. Evaluation on 23 BIG-Bench Hard tasks shows SELF-ICL outperforms zero-shot baselines on both average accuracy and head-to-head comparison. Moreover, with zero-shot chain-of-thought, SELF-ICL achieves results comparable to using real demonstrations. Additionally, we conduct a range of analyses to validate SELF-ICL's effectiveness and provide insights for its behaviors under different settings. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/640564 | ISBN: | 9798891760608 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。