超越範例：透過MCTS在上下文學習中的高層次自動推理範式

Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS

November 27, 2024

作者: Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zengqi Wen, Jianhua Tao

cs.AI

摘要

在上下文學習（ICL）中，大型語言模型（LLMs）通過複雜的提示和高質量的示範來應對下游任務。然而，傳統的ICL範式在面對複雜的數學推理任務時存在局限性，主要是由於其對示例質量的重度依賴以及在具有挑戰性情境下需要人類干預。為了應對這些限制，本文提出了HiAR-ICL，一種高級自動推理範式在ICL中，將焦點從具體示例轉移到抽象思維模式，擴展了ICL中的傳統上下文概念。HiAR-ICL引入了五種原子推理行為作為構建鏈狀模式的基本組件。通過蒙特卡洛樹搜索，我們探索推理路徑並構建思維卡，以引導後續推理。然後，我們開發了一個動態匹配問題與適當思維卡的認知複雜性框架。實驗結果表明HiAR-ICL的有效性，在MATH基準測試中以Qwen2.5-7B-Instruct實現了最先進的準確性（79.6%），超越了GPT-4o（76.6%）和Claude 3.5（71.1%）。

English

In-context Learning (ICL) enables large language models (LLMs) to tackle downstream tasks through sophisticated prompting and high-quality demonstrations. However, this traditional ICL paradigm shows limitations when facing complex mathematical reasoning tasks, primarily due to its heavy dependence on example quality and the necessity for human intervention in challenging scenarios. To address these limitations, this paper presents HiAR-ICL, a High-level Automated Reasoning paradigm in ICL that shifts focus from specific examples to abstract thinking patterns, extending the conventional concept of context in ICL. HiAR-ICL introduces five atomic reasoning actions as fundamental components for constructing chain-structured patterns. Using Monte Carlo Tree Search, we explore reasoning paths and construct thought cards to guide subsequent inference. We then develop a cognitive complexity framework that dynamically matches problems with appropriate thought cards. Experimental results demonstrate HiAR-ICL's effectiveness, achieving state-of-the-art accuracy (79.6%) on the MATH benchmark with Qwen2.5-7B-Instruct, surpassing GPT-4o (76.6%) and Claude 3.5 (71.1%).