Scholarlink

<p>Multi-hop question answering (MHQA) requires aggregating information across multiple heterogeneous evidence passages, simulating human step-by-step reasoning and clue tracing to construct a complete logical path toward the answer. However, existing approaches face key limitations: chain-of-thought paradigms are prone to error accumulation across reasoning steps, while tree-structured paradigms often struggle with efficiency due to the vast discrete search space and slow convergence. To address these challenges, we propose the PMA framework, which integrates a prior estimate of the number of reasoning steps with structurally constrained search to achieve efficient and stable reasoning using minimal yet sufficient paths. Specifically, PMA consists of three core components: (1) a fine-tuned BERT-based hop predictor to estimate the required number of reasoning steps, guiding the scope of tree expansion; (2) a structurally constrained Monte Carlo Tree Search (MCTS) that regulates search depth and dynamically selects expansion nodes using coherence and adaptability scores; and (3) a multi-path answer aggregation module that consolidates candidate answers via majority voting, with ties resolved by selecting the path with the highest average score. Experimental results demonstrate that PMA achieves competitive accuracy while significantly reducing token consumption, highlighting its advantages in both efficiency and robustness.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Less is more: a PMA framework for zero-shot multi-hop question answering

  • 期刊论文

  • 发表日期：

    2026年7月24日

查看全文
  • Rongsheng Dong,
  • Xiaolong Wang,
  • Sen Li,
  • Fengying Li

摘要

Multi-hop question answering (MHQA) requires aggregating information across multiple heterogeneous evidence passages, simulating human step-by-step reasoning and clue tracing to construct a complete logical path toward the answer. However, existing approaches face key limitations: chain-of-thought paradigms are prone to error accumulation across reasoning steps, while tree-structured paradigms often struggle with efficiency due to the vast discrete search space and slow convergence. To address these challenges, we propose the PMA framework, which integrates a prior estimate of the number of reasoning steps with structurally constrained search to achieve efficient and stable reasoning using minimal yet sufficient paths. Specifically, PMA consists of three core components: (1) a fine-tuned BERT-based hop predictor to estimate the required number of reasoning steps, guiding the scope of tree expansion; (2) a structurally constrained Monte Carlo Tree Search (MCTS) that regulates search depth and dynamically selects expansion nodes using coherence and adaptability scores; and (3) a multi-path answer aggregation module that consolidates candidate answers via majority voting, with ties resolved by selecting the path with the highest average score. Experimental results demonstrate that PMA achieves competitive accuracy while significantly reducing token consumption, highlighting its advantages in both efficiency and robustness.