Saved in:
Bibliographic Details
Main Authors: Qian, Kun, Sang, Yisi, Bayat, Farima Fatahi, Belyi, Anton, Chu, Xianqi, Govind, Yash, Khorshidi, Samira, Khot, Rahul, Luna, Katherine, Nikfarjam, Azadeh, Qi, Xiaoguang, Wu, Fei, Zhang, Xianhan, Li, Yunyao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.04637
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913462931685376
author Qian, Kun
Sang, Yisi
Bayat, Farima Fatahi
Belyi, Anton
Chu, Xianqi
Govind, Yash
Khorshidi, Samira
Khot, Rahul
Luna, Katherine
Nikfarjam, Azadeh
Qi, Xiaoguang
Wu, Fei
Zhang, Xianhan
Li, Yunyao
author_facet Qian, Kun
Sang, Yisi
Bayat, Farima Fatahi
Belyi, Anton
Chu, Xianqi
Govind, Yash
Khorshidi, Samira
Khot, Rahul
Luna, Katherine
Nikfarjam, Azadeh
Qi, Xiaoguang
Wu, Fei
Zhang, Xianhan
Li, Yunyao
contents Prompt engineering is an iterative procedure often requiring extensive manual effort to formulate suitable instructions for effectively directing large language models (LLMs) in specific tasks. Incorporating few-shot examples is a vital and effective approach to providing LLMs with precise instructions, leading to improved LLM performance. Nonetheless, identifying the most informative demonstrations for LLMs is labor-intensive, frequently entailing sifting through an extensive search space. In this demonstration, we showcase a human-in-the-loop tool called APE (Active Prompt Engineering) designed for refining prompts through active learning. Drawing inspiration from active learning, APE iteratively selects the most ambiguous examples for human feedback, which will be transformed into few-shot examples within the prompt. The demo recording can be found with the submission or be viewed at https://youtu.be/OwQ6MQx53-Y.
format Preprint
id arxiv_https___arxiv_org_abs_2408_04637
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle APE: Active Learning-based Tooling for Finding Informative Few-shot Examples for LLM-based Entity Matching
Qian, Kun
Sang, Yisi
Bayat, Farima Fatahi
Belyi, Anton
Chu, Xianqi
Govind, Yash
Khorshidi, Samira
Khot, Rahul
Luna, Katherine
Nikfarjam, Azadeh
Qi, Xiaoguang
Wu, Fei
Zhang, Xianhan
Li, Yunyao
Computation and Language
Prompt engineering is an iterative procedure often requiring extensive manual effort to formulate suitable instructions for effectively directing large language models (LLMs) in specific tasks. Incorporating few-shot examples is a vital and effective approach to providing LLMs with precise instructions, leading to improved LLM performance. Nonetheless, identifying the most informative demonstrations for LLMs is labor-intensive, frequently entailing sifting through an extensive search space. In this demonstration, we showcase a human-in-the-loop tool called APE (Active Prompt Engineering) designed for refining prompts through active learning. Drawing inspiration from active learning, APE iteratively selects the most ambiguous examples for human feedback, which will be transformed into few-shot examples within the prompt. The demo recording can be found with the submission or be viewed at https://youtu.be/OwQ6MQx53-Y.
title APE: Active Learning-based Tooling for Finding Informative Few-shot Examples for LLM-based Entity Matching
topic Computation and Language
url https://arxiv.org/abs/2408.04637