# Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method

arXiv: https://arxiv.org/abs/2604.11209 · HTML: https://mlsanity.com/paper/2604.11209/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 7 of its 42 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 7 of 7)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization](https://mlsanity.com/paper/2502.20364/) (2025)
- [RAG-based Question Answering over Heterogeneous Data and Text](https://mlsanity.com/paper/2412.07420/) (2024)

## Built on by (most cited first, 6 of 6)

- [Selective QA over Conflicting Multi-Source Personal Memory: A Diagnostic Testbed and Method Comparison](https://mlsanity.com/paper/2605.30087/) (2026)
- [When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict](https://mlsanity.com/paper/2608.13921/) (2026)
- [Quantifying Prior Dominance in RAG Systems](https://mlsanity.com/paper/2606.23695/) (2026)
- [EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning](https://mlsanity.com/paper/2607.10491/) (2026)
- [Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities](https://mlsanity.com/paper/2610.00606/) (2026)
- [Learning When to Trust Medical Knowledge: Regression-Safe Routing for Clinical Reasoning](https://mlsanity.com/paper/2610.19663/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have achieved remarkable success across a wide range of applications especially when augmented by external knowledge through retrieval-augmented generation (RAG). Despite their widespread adoption, recent studies have shown that LLMs often struggle to perform faithful reasoning when conflicting knowledge is retrieved. However, existing work primarily focuses on conflicts between external knowledge and the parametric knowledge of LLMs, leaving conflicts across external knowledge largely unexplored. Meanwhile, modern RAG systems increasingly emphasize the integration of unstructured text and (semi-)structured data like knowledge graphs (KGs) to improve knowledge completeness and reasoning faithfulness. To address this gap, we introduce ConflictQA, a novel benchmark that systematically instantiates conflicts between textual evidence and KG evidence. Extensive evaluations across representative LLMs reveal that, facing such cross-source conflicts, LLMs often fail to identify reliable evidence for correct reasoning. Instead, LLMs become more sensitive to prompting choices and tend to rely exclusively on either KG or textual evidence, resulting in incorrect responses. Based on these findings, we further propose XoT, a two-stage explanation-based thinking framework tailored for reasoning over heterogeneous conflicting evidence, and verify its effectiveness with extensive experiments.