# 多数投票在因果推理中失效，CALVER 用符号验证提升最佳K选择

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-04 08:00
- AIHOT 分数：50
- AIHOT 链接：https://aihot.virxact.com/items/cmsge0m2w02yqro5qlzgp3en5
- 原文链接：https://arxiv.org/abs/2608.03506

## AI 摘要

自一致性投票在因果推理中会因重复混杂错误和票数分散而失效，研究提出免训练的符号验证器 CALVER，依据 Pearl 因果准则对推理轨迹打分选优。在 CLEAR 查询上 CALVER 达 42.1%，而多数投票、奖励模型等方法均接近 30%，且无需参考答案，CPU 上毫秒级评分。

## 正文

Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confounding error, and votes fragment across multiple valid answers, letting an invalid answer win despite a valid minority trace. We introduce CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal criteria, including -separation, backdoor adjustment, and intervention, and selects the highest-scoring candidate without consulting a reference answer. On CLEAR find-one-valid queries that admit multiple graph-valid answers, CALVER reaches 42.1% where plurality, a reward model, an LLM judge, and model confidence remain near 30% on identical frozen pools. Scaling the judge to 72B does not close the gap. In an audited clean-core subset, 11 of 21 graph-valid CALVER selections differ from the benchmark's listed answer while still satisfying the requested predicate. The advantage widens with the sampling budget and reproduces across ten published Bayesian networks, a second model family, and settings where the model must build the graph from text. CALVER also improves thresholded average-treatment-effect decisions against exact ground truth, generalizes to logic under a truth-table checker, and scores each candidate in milliseconds on CPU. CALVER needs only a causal structure, supplied outright or built from the text; wherever that holds, selection can aggregate via causal validity.