Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling

2026-02-24

AI Summary

Large language models often exhibit convergent outputs due to shared pretraining priors, limiting creative exploration and scientific discovery. To address this, this work proposes the Epistemic Evolution paradigm and introduces PRISM—a model-agnostic system that dynamically constructs personalized cognitive trajectories (Nurture) and context-aware epistemic graphs during inference, enabling diverse reasoning beyond model consensus. The approach achieves state-of-the-art novelty and significantly enhances output diversity across three creativity benchmarks. In rare disease diagnosis, it successfully identifies long-tail correct diagnoses missed by standard LLMs. This study presents the first framework for structuring individualized cognitive pathways at inference time, advancing AI toward a pluralistic cognitive ecosystem.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: AI & Epistemology

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Large Language Models (LLMs) are converging towards a singular Artificial Hivemind, where shared Nature (pre-training priors) result in a profound collapse of distributional diversity, limiting the distinct perspectives necessary for creative exploration and scientific discovery. To address this, we propose to equip models with inference-time Nurture (individualized epistemic trajectories) using Epistemic Evolution paradigm, progressing through explore, internalize, and express. We instantiate this via PRISM (Pluralistic Reasoning via In-context Structure Modeling), a model-agnostic system that augments LLM with dynamic On-the-fly Epistemic Graphs. On three creativity benchmarks, PRISM achieves state-of-the-art novelty and significantly expands distributional diversity. Moreover, we evaluate the real-world utility via a challenging rare-disease diagnosis benchmark. Results demonstrate that PRISM successfully uncovers correct long-tail diagnoses that standard LLM miss, confirming that its divergence stems from meaningful exploration rather than incoherent noise. Overall, this work establishes a new paradigm for Pluralistic AI, moving beyond monolithic consensus toward a diverse ecosystem of unique cognitive individuals capable of collective, multi-perspective discovery.

Problem

• Artificial Hivemind
• Distributional Diversity
• Pluralistic Reasoning
• Large Language Models
• Epistemic Diversity

Innovation

• Pluralistic AI
• Epistemic Evolution
• In-context Structure Modeling
• On-the-fly Epistemic Graphs
• Distributional Diversity