# Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts Source: [Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts]() Collection index: [llms.txt]() Data updated: 2026-07-02T05:00:13.059Z Authors: Xianda Zheng, Zijian Huang, Meng-Fen Chiang, Jiamou Liu, Yuan Fang, Michael Witbrock, Kaiqi Zhao Published: 2025-08-02T09:09:50.000Z ## Abstract Explicit knowledge conflicts, occurring when retrieved contexts contain contradictory information, pose a fundamental challenge for Large Language Models (LLMs) as they integrate increasingly diverse data sources. The core difficulty lies in the complexity of entangled narratives and heterogeneous conflict patterns, which frequently exceeds the reasoning capacity of standard backbone architectures. We propose \\textbf{\\textsc{Kcr}} (Knowledge Conflict Reasoning), a framework that adjudicates contradictions by systematically structuring their underlying logic. \\textsc{Kcr} disentangles conflicting contexts into discrete sets of reasoning traces, utilizing a hybrid representation of text and graphs to facilitate systematic comprehension. It then employs a Reinforcement Learning with Verifiable Rewards (RLVR) paradigm to instill a reasoning policy that maximizes logical consistency while suppressing spurious paths derived from contradictory evidence. Extensive evaluations demonstrate that \\textsc{Kcr} yields substantial performance gains. Notably, a 7B model enhanced by \\textsc{Kcr} achieves adjudication capabilities that significantly outperform leading proprietary models, including GPT-4o and GPT-5.1, on complex tasks. Code is available at https://github.com/zhengxianda/KCR. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Inter-Context Knowledge Conflict on PopQA](): Inter-Context Knowledge Conflict; PopQA; ACCL: 90.28. - [Inter-Context Knowledge Conflict on StrategyQA](): Inter-Context Knowledge Conflict; StrategyQA; ACCL: 83.2. ## Original sources and implementation [Original paper]() [PDF]()