When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs

• 类型：arxiv
• 标识：2608.03506
• 链接：https://arxiv.org/abs/2608.03506
• 主分类：engineering
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：This work introduces 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.
• 待LLM分类：否
• 标题中文：当多个答案均有效时，投票失效：面向 LLM Best-of-K 因果推理的符号验证
• TLDR中文：提出 CALVER (Causal Axiom-Level VERification)，一种无需训练的对称验证器，根据 Pearl 的因果准则（包括 d-分离、backdoor 调整与干预）对结构化 trace 评分，并在不参考标准答案的情况下选择得分最高的候选。
• 来源文件：
• /inbox/tom/_candidates/2026-08-06-agent-rag-longcontext-candidates.json
• [S2 enrich]