EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs

TL;DR

EAVIT is a framework that combines local models and online LLMs to efficiently and accurately identify human values from text, reducing computational costs and improving performance over traditional methods.

Contribution

The paper introduces EAVIT, a novel approach that integrates local value detectors with online LLMs, optimizing prompt construction and training for better value identification.

Findings

Reduces input tokens by up to 1/6 compared to direct LLM queries.

Outperforms traditional NLP and other LLM-based methods in accuracy.

Enhances efficiency and accuracy in human value identification from text.

Abstract

The rapid evolution of large language models (LLMs) has revolutionized various fields, including the identification and discovery of human values within text data. While traditional NLP models, such as BERT, have been employed for this task, their ability to represent textual data is significantly outperformed by emerging LLMs like GPTs. However, the performance of online LLMs often degrades when handling long contexts required for value identification, which also incurs substantial computational costs. To address these challenges, we propose EAVIT, an efficient and accurate framework for human value identification that combines the strengths of both locally fine-tunable and online black-box LLMs. Our framework employs a value detector - a small, local language model - to generate initial value estimations. These estimations are then used to construct concise input prompts for online LLMs, enabling accurate final value identification. To train the value detector, we introduce explanation-based training and data generation techniques specifically tailored for value identification, alongside sampling strategies to optimize the brevity of LLM input prompts. Our approach effectively reduces the number of input tokens by up to 1/6 compared to directly querying online LLMs, while consistently outperforming traditional NLP methods and other LLM-based strategies.