通过投票一致性动态调度计算，提升叙事相似度判断精度
CascadeMind at SemEval-2026 Task 4: A Hybrid Neuro-Symbolic Cascade for Narrative Similarity
- 根据大模型投票一致性分级路由，硬样本自动触发额外采样
- 在开发集上准确率随投票分歧度单调下降：超多数85%、分歧67%、平局61%
- 核心优势在于智能分配算力，适合需要高效推理的场景
在大模型自一致性采样中，投票一致性与实例难度呈正相关：在SemEval-2026任务4（叙事相似度）中，超多数情况（≥7/8票）准确率达85%，分歧票达67%，完全平局为61%，该单调关系贯穿开发集。CascadeMind系统基于此设计，对八次Gemini 2.5 Flash投票按共识分流，分歧样本进入额外采样轮次，仅在完全平局（占5%）时启用符号化集成的理论驱动叙事信号。该系统在Track A测试中达到72.75%准确率，位列44支队伍第10名。消融实验表明，符号组件端到端贡献微乎其微，几乎所有提升均来自置信度感知的路由策略。关键启示是：对于叙事相似度任务，精准判断何时投入更多计算比添加辅助表征更为重要。
原文摘要 · Abstract (English)
Across self-consistency samples from an LLM, vote agreement tracks instance difficulty: on SemEval-2026 Task 4 (Narrative Story Similarity), supermajority cases (>= 7/8 votes) resolve at 85 percent accuracy, split votes at 67 percent, and perfect ties at 61 percent, a monotone gradient that holds across the development set. We exploit this in CascadeMind, which routes eight Gemini 2.5 Flash votes by consensus, escalates split votes to additional sampling rounds, and falls through to a symbolic ensemble of theory-inspired narrative signals only on perfect ties (5 percent of cases). The system reached 72.75 percent on Track A test, placing 10th of 44 teams. Ablations show that the symbolic component contributes negligibly end-to-end and that nearly all gains come from confidence-aware routing. The takeaway is methodological: for narrative similarity, calibrating when to spend more compute on a hard instance matters more than adding auxiliary representations to reason about it.
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。