让大模型学会多样思考，突破单一思维局限
Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling
- 通过动态构建认知图谱，在推理时引入个性化知识路径
- 在三个创意任务上实现最佳新颖性，显著提升多样性
- 适合需要多角度探索的科研与罕见病诊断场景
大型语言模型正趋向于单一的人工蜂群心智，其共享的预训练先验导致分布多样性严重坍缩，限制了创造性探索与科学发现所需的多元视角。为此，我们提出在推理阶段引入个体化的认知轨迹（Nurture），基于认知演进范式，经历探索、内化与表达三阶段。我们以PRISM（基于上下文结构建模的多元推理）为例，实现一种与模型无关的系统，通过动态生成即时认知图谱增强大模型。在三个创意基准测试中，PRISM达到当前最优的新颖性表现，并显著扩大分布多样性。此外，我们在具有挑战性的罕见病诊断任务中评估其实用价值，结果表明PRISM成功识别出标准大模型遗漏的正确长尾诊断，证实其分化源于有意义的探索而非无序噪声。本工作确立了多元智能的新范式，推动从单一共识走向具备独特认知个体的多样化协同发现生态系统。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。