From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models
This work addresses the high cost of large-scale surveys for predicting opinions in domains like politics and marketing, offering a novel computational approach, though it is incremental in applying value injection to LLMs.
The paper tackles the problem of predicting human opinions and behaviors by proposing value-injected large language models (LLMs) using the Value Injection Method (VIM), which includes argument generation and question answering techniques, and finds that these models substantially outperform baselines in experiments across four tasks.
Being able to predict people's opinions on issues and behaviors in realistic scenarios can be helpful in various domains, such as politics and marketing. However, conducting large-scale surveys like the European Social Survey to solicit people's opinions on individual issues can incur prohibitive costs. Leveraging prior research showing influence of core human values on individual decisions and actions, we propose to use value-injected large language models (LLM) to predict opinions and behaviors. To this end, we present Value Injection Method (VIM), a collection of two methods -- argument generation and question answering -- designed to inject targeted value distributions into LLMs via fine-tuning. We then conduct a series of experiments on four tasks to test the effectiveness of VIM and the possibility of using value-injected LLMs to predict opinions and behaviors of people. We find that LLMs value-injected with variations of VIM substantially outperform the baselines. Also, the results suggest that opinions and behaviors can be better predicted using value-injected LLMs than the baseline approaches.