Future You: Designing and Evaluating Multimodal AI-generated Digital Twins for Strengthening Future Self-Continuity

2025-12-05

AI Summary

This study investigates how multimodal AI-generated digital twins of one’s future self—comprising text, synthetic speech, and photorealistic avatars—affect psychological connectedness to the future self, emotional well-being, and intertemporal decision-making. We constructed personalized digital twins using voice cloning, age-progression facial rendering, autobiographical narrative generation, and large language models (with Claude 4 as the core). A controlled experimental design compared the effects of three modalities. Results show that all modalities significantly enhance future self-continuity, positive affect, and behavioral motivation; no significant overall difference emerged across modalities, but interaction quality—particularly perceived realism and persuasive efficacy—served as a critical mediating factor. Crucially, Claude 4 outperformed baseline LLMs in amplifying these psychological effects. This work provides the first systematic empirical validation of multimodal digital twins for temporal self-intervention and reveals that interaction quality, rather than modality per se, is the primary driver of efficacy.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

What if users could meet their future selves today? AI-generated future selves simulate meaningful encounters with a digital twin decades in the future. As AI systems advance, combining cloned voices, age-progressed facial rendering, and autobiographical narratives, a central question emerges: Does the modality of these future selves alter their psychological and affective impact? How might a text-based chatbot, a voice-only system, or a photorealistic avatar shape present-day decisions and our feeling of connection to the future? We report a randomized controlled study (N=92) evaluating three modalities of AI-generated future selves (text, voice, avatar) against a neutral control condition. We also report a systematic model evaluation between Claude 4 and three other Large Language Models (LLMs), assessing Claude 4 across psychological and interaction dimensions and establishing conversational AI quality as a critical determinant of intervention effectiveness. All personalized modalities strengthened Future Self-Continuity (FSC), emotional well-being, and motivation compared to control, with avatar producing the largest vividness gains, yet with no significant differences between formats. Interaction quality metrics, particularly persuasiveness, realism, and user engagement, emerged as robust predictors of psychological and affective outcomes, indicating that how compelling the interaction feels matters more than the form it takes. Content analysis found thematic patterns: text emphasized career planning, while voice and avatar facilitated personal reflection. Claude 4 outperformed ChatGPT 3.5, Llama 4, and Qwen 3 in enhancing psychological, affective, and FSC outcomes.

Problem

• Evaluates how different AI modalities affect psychological impact of future self digital twins
• Assesses interaction quality as key predictor of intervention effectiveness across modalities
• Compares performance of Claude 4 against other LLMs in enhancing future self-continuity

Innovation

• AI-generated digital twins with multimodal interactions
• Randomized controlled study comparing text, voice, avatar modalities
• Claude 4 outperforms other LLMs in psychological outcomes