PrimeX: A Dataset of Worldview, Opinion, and Explanation

2025-09-30

AI Summary

Prior work on personalized alignment of language models overlooks individuals’ deep-seated belief systems. Method: We construct the first multimodal dataset (N=858, U.S. residents) integrating the Primal World Belief Scale—a validated psychological instrument—with open-ended textual explanations of personal views. Combining public opinion surveys, structured questionnaires, and natural language analysis, we develop a computationally tractable, multidimensional belief representation framework. Results: Incorporating worldview dimensions significantly improves model accuracy in understanding and predicting individual viewpoints (p<0.01). This work establishes a reproducible data foundation, a novel modeling paradigm, and empirical validation for psychological-trait-driven personalized NLP, thereby advancing interdisciplinary integration between NLP and cognitive/personality psychology.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Reasoning with Beliefs

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

As the adoption of language models advances, so does the need to better represent individual users to the model. Are there aspects of an individual's belief system that a language model can utilize for improved alignment? Following prior research, we investigate this question in the domain of opinion prediction by developing PrimeX, a dataset of public opinion survey data from 858 US residents with two additional sources of belief information: written explanations from the respondents for why they hold specific opinions, and the Primal World Belief survey for assessing respondent worldview. We provide an extensive initial analysis of our data and show the value of belief explanations and worldview for personalizing language models. Our results demonstrate how the additional belief information in PrimeX can benefit both the NLP and psychological research communities, opening up avenues for further study.

Problem

• Developing PrimeX dataset to capture worldview and opinion data
• Investigating belief systems for improved language model alignment
• Analyzing how explanations and worldview personalize language models

Innovation

• Dataset includes written explanations from respondents
• Incorporates Primal World Belief survey for worldview assessment
• Combines opinion data with belief information for personalization