Guideline Learning for In-context Information Extraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pang, Chaoxu, Cao, Yixuan, Ding, Qiang, Luo, Ping
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918088394407936
author Pang, Chaoxu
Cao, Yixuan
Ding, Qiang
Luo, Ping
author_facet Pang, Chaoxu
Cao, Yixuan
Ding, Qiang
Luo, Ping
contents Large language models (LLMs) can perform a new task by merely conditioning on task instructions and a few input-output examples, without optimizing any parameters. This is called In-Context Learning (ICL). In-context Information Extraction (IE) has recently garnered attention in the research community. However, the performance of In-context IE generally lags behind the state-of-the-art supervised expert models. We highlight a key reason for this shortfall: underspecified task description. The limited-length context struggles to thoroughly express the intricate IE task instructions and various edge cases, leading to misalignment in task comprehension with humans. In this paper, we propose a Guideline Learning (GL) framework for In-context IE which reflectively learns and follows guidelines. During the learning phrase, GL automatically synthesizes a set of guidelines based on a few error cases, and during inference, GL retrieves helpful guidelines for better ICL. Moreover, we propose a self-consistency-based active learning method to enhance the efficiency of GL. Experiments on event extraction and relation extraction show that GL can significantly improve the performance of in-context IE.
format Preprint
id arxiv_https___arxiv_org_abs_2310_05066
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Guideline Learning for In-context Information Extraction
Pang, Chaoxu
Cao, Yixuan
Ding, Qiang
Luo, Ping
Computation and Language
Machine Learning
Large language models (LLMs) can perform a new task by merely conditioning on task instructions and a few input-output examples, without optimizing any parameters. This is called In-Context Learning (ICL). In-context Information Extraction (IE) has recently garnered attention in the research community. However, the performance of In-context IE generally lags behind the state-of-the-art supervised expert models. We highlight a key reason for this shortfall: underspecified task description. The limited-length context struggles to thoroughly express the intricate IE task instructions and various edge cases, leading to misalignment in task comprehension with humans. In this paper, we propose a Guideline Learning (GL) framework for In-context IE which reflectively learns and follows guidelines. During the learning phrase, GL automatically synthesizes a set of guidelines based on a few error cases, and during inference, GL retrieves helpful guidelines for better ICL. Moreover, we propose a self-consistency-based active learning method to enhance the efficiency of GL. Experiments on event extraction and relation extraction show that GL can significantly improve the performance of in-context IE.
title Guideline Learning for In-context Information Extraction
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2310.05066