Quantifying Cross-Query Contradictions in Multi-Query LLM Reasoning
arXiv:2604.14525
Abstract
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.
Accepted at the ICLR 2026 Workshop on Logical Reasoning of Large Language Models. 9 pages, 6 tables, code and data at https://huggingface.co/datasets/rohitspider/cross_query_benchmark