# Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents

arXiv: https://arxiv.org/abs/2404.16032 · HTML: https://mlsanity.com/paper/2404.16032/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 24 Apr 2024.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 30 of 31)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [NewsQA: A Machine Comprehension Dataset](https://mlsanity.com/paper/1611.09830/) (2016)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://mlsanity.com/paper/1704.05179/) (2017)
- [MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension](https://mlsanity.com/paper/1910.09753/) (2019)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models](https://mlsanity.com/paper/2212.08037/) (2022)
- [Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation](https://mlsanity.com/paper/2202.07654/) (2022)
- [LexDrafter: Terminology Drafting for Legislative Documents using Retrieval Augmented Generation](https://mlsanity.com/paper/2403.16295/) (2024)

## Built on by (most cited first, 27 of 27)

- [Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs](https://mlsanity.com/paper/2510.17771/) (2025)
- [Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals](https://mlsanity.com/paper/2502.16101/) (2025)
- [DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs](https://mlsanity.com/paper/2506.08500/) (2025)
- [Retrieval-Augmented Generation with Estimation of Source Reliability](https://mlsanity.com/paper/2410.22954/) (2024)
- [Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict](https://mlsanity.com/paper/2506.06485/) (2025)
- [Do RAG Systems Really Suffer From Positional Bias?](https://mlsanity.com/paper/2505.15561/) (2025)
- [ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.15543/) (2025)
- [The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation](https://mlsanity.com/paper/2505.15807/) (2025)
- [A Reality Check on Context Utilisation for Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.17031/) (2024)
- ["Lost-in-the-Later": Framework for Quantifying Contextual Grounding in Large Language Models](https://mlsanity.com/paper/2507.05424/) (2025)
- [Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models](https://mlsanity.com/paper/2508.19720/) (2025)
- [How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models](https://mlsanity.com/paper/2510.02370/) (2025)
- [KScope: A Framework for Characterizing the Knowledge Status of Language Models](https://mlsanity.com/paper/2506.07458/) (2025)
- [When Facts Change: Probing LLMs on Evolving Knowledge with evolveQA](https://mlsanity.com/paper/2510.19172/) (2025)
- [When Should Models Change Their Minds? Contextual Belief Management in Large Language Models](https://mlsanity.com/paper/2605.30219/) (2026)
- [Evaluating Evidence Grounding Under User Pressure in Instruction-Tuned Language Models](https://mlsanity.com/paper/2603.20162/) (2026)
- [Information Discernment in Large Language Models](https://mlsanity.com/paper/2607.19355/) (2026)
- [Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts](https://mlsanity.com/paper/2609.00293/) (2026)
- [CCSK:Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Models](https://mlsanity.com/paper/2504.10498/) (2025)
- [CALRK-Bench: Evaluating Context-Aware Legal Reasoning in Korean Law](https://mlsanity.com/paper/2603.26332/) (2026)
- [The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.05594/) (2026)
- [Persistent Priors, Preserved Targets: A Stroop-Style Paradigm for Lexical Override](https://mlsanity.com/paper/2606.07555/) (2026)
- [When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Models](https://mlsanity.com/paper/2608.19208/) (2026)
- [Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution](https://mlsanity.com/paper/2608.24460/) (2026)
- [Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs](https://mlsanity.com/paper/2609.25602/) (2026)
- [Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers](https://mlsanity.com/paper/2609.31342/) (2026)
- [What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use](https://mlsanity.com/paper/2609.32991/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) mitigates many problems of fully parametric language models, such as temporal degradation, hallucinations, and lack of grounding. In RAG, the model's knowledge can be updated from documents provided in context. This leads to cases of conflict between the model's parametric knowledge and the contextual information, where the model may not always update its knowledge. Previous work studied context-memory knowledge conflicts by creating synthetic documents that contradict the model's correct parametric answers. We present a framework for studying such knowledge conflicts in a realistic setup. We update incorrect parametric knowledge using real conflicting documents. This reflects how knowledge conflicts arise in practice. In this realistic scenario, we find that knowledge updates fail less often than previously reported. In cases where the models still fail to update their answers, we find a parametric bias: the incorrect parametric answer appearing in context makes the knowledge update likelier to fail. These results suggest that the factual parametric knowledge of LLMs can negatively influence their reading abilities and behaviors. Our code is available at https://github.com/kortukov/realistic_knowledge_conflicts/ .