LLM Reasoning 相关度: 9/10

AILS-NTUA at SemEval-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoning

Nikolas Karafyllis, Maria Lymperaiou, Giorgos Filandrianos, Athanasios Voulodimos, Giorgos Stamou
arXiv: 2603.04319v1 发布: 2026-03-04 更新: 2026-03-04
下载 PDF arXiv 页面

AI 摘要

该论文提出了一种用于推理的图检索和反思提示的三阶段系统，并在SemEval-2026任务中取得了第一名。

主要贡献

  • 图检索方法
  • 反思提示进化优化的LLM推理
  • 后置一致性增强

方法论

结合图检索，LLM反思提示优化，以及后置一致性加强，实现事件推理。

原文摘要

We present a winning three-stage system for SemEval 2026 Task~12: Abductive Event Reasoning that combines graph-based retrieval, LLM-driven abductive reasoning with prompt design optimized through reflective prompt evolution, and post-hoc consistency enforcement; our system ranks first on the evaluation-phase leaderboard with an accuracy score of 0.95. Cross-model error analysis across 14 models (7~families) reveals three shared inductive biases: causal chain incompleteness, proximate cause preference, and salience bias, whose cross-family convergence (51\% cause-count reduction) indicates systematic rather than model-specific failure modes in multi-label causal reasoning.

标签

事件推理 图检索 LLM 反思提示 SemEval

arXiv 分类

cs.CL