利用Graph-PReFLexOR進行現場圖推理和知識擴展

In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR

January 14, 2025

作者: Markus J. Buehler

cs.AI

摘要

追求自動化科學發現的目標推動了從符號邏輯到現代人工智慧的進步，開拓了推理和模式識別的新領域。變壓器作為潛在系統，每種可能的關係都保持潛在性，直到任務施加約束，類似於測量。然而，要改進它們的取樣不僅需要概率選擇：解決方案必須符合特定結構或規則，確保一致性和通用原則的應用。我們提出了Graph-PReFLexOR（基於圖形的基於偏好的遞歸語言建模的探索性優化推理）框架，將圖形推理與符號抽象結合起來，動態擴展領域知識。受強化學習啟發，Graph-PReFLexOR將推理定義為結構映射，其中任務產生知識圖形、抽象模式，最終得出最終答案。受范畴論啟發，它將概念編碼為節點，將它們之間的關係編碼為邊，支持階層推理和通過同構表示實現的適應性學習。示範包括假設生成、材料設計和創造性推理，例如發現神話概念如“薄弱之處”與材料科學之間的關係。我們提出了一種“知識花園成長”策略，整合跨領域的見解，促進跨學科的聯繫。使用30億參數的Graph-PReFLexOR模型的結果顯示出優越的推理深度和適應性，突顯了透明、多學科的人工智慧驅動發現的潛力。它為通用自主推理解決方案奠定了基礎。

English

The pursuit of automated scientific discovery has fueled progress from symbolic logic to modern AI, forging new frontiers in reasoning and pattern recognition. Transformers function as potential systems, where every possible relationship remains latent potentiality until tasks impose constraints, akin to measurement. Yet, refining their sampling requires more than probabilistic selection: solutions must conform to specific structures or rules, ensuring consistency and the invocation of general principles. We present Graph-PReFLexOR (Graph-based Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning), a framework that combines graph reasoning with symbolic abstraction to dynamically expand domain knowledge. Inspired by reinforcement learning, Graph-PReFLexOR defines reasoning as a structured mapping, where tasks yield knowledge graphs, abstract patterns, and ultimately, final answers. Inspired by category theory, it encodes concepts as nodes and their relationships as edges, supporting hierarchical inference and adaptive learning through isomorphic representations. Demonstrations include hypothesis generation, materials design, and creative reasoning, such as discovering relationships between mythological concepts like 'thin places' with materials science. We propose a 'knowledge garden growth' strategy that integrates insights across domains, promoting interdisciplinary connections. Results with a 3-billion-parameter Graph-PReFLexOR model show superior reasoning depth and adaptability, underscoring the potential for transparent, multidisciplinary AI-driven discovery. It lays the groundwork for general autonomous reasoning solutions.