解决大模型多查询推理中的自相矛盾问题，提升整体一致性。
Quantifying Cross-Query Contradictions in Multi-Query LLM Reasoning
- 通过提取承诺、验证全局一致性和修复矛盾，实现跨查询逻辑自洽。
- 在四个领域中将跨查询一致性从0.56提升至0.94，同时保持单个查询准确率。
- 适用于需要多步推理和逻辑一致性的智能系统设计者。
大型语言模型在处理多个相关查询时，常产生相互矛盾的答案。本文研究案例文件逻辑一致性：在相互依赖的查询间维持全局可满足的信念状态。我们构建了一个包含390个多查询推理实例的基准数据集，标注了蕴含/矛盾/未知关系，并提出集合级度量指标，包括案例可满足率（SetCons）、矛盾密度和修订成本。所提出的增强求解器方法能提取承诺、验证全局可满足性并进行反例引导修复。在四个推理领域中，该方法显著降低跨查询矛盾（SetCons由0.56提升至0.94），同时保持单个查询的准确性，证明全局一致性对鲁棒多查询推理至关重要。
原文摘要 · Abstract (English)
Large language models frequently produce mutually inconsistent answers when reasoning over multiple related queries. We study case-file logical consistency: maintaining a globally satisfiable belief state across interdependent queries. We introduce a benchmark of 390 multi-query reasoning instances with entailment/contradiction/unknown labels and propose set-level metrics including Case Satisfiability Rate, Contradiction Density and Revision Cost. Our solver-augmented approach extracts commitments, verifies global satisfiability and performs counterexample-guided repair. Across four reasoning domains, our method substantially reduces cross-query contradictions (SetCons: 0.56 to 0.94) while preserving per-query accuracy, demonstrating that global coherence is critical for robust multi-query reasoning.
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。