# "Merge Conflicts!" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs

arXiv: https://arxiv.org/abs/2309.08594 · HTML: https://mlsanity.com/paper/2309.08594/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 15 Sep 2023.

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

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [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)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters](https://mlsanity.com/paper/2002.01808/) (2020)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Counterfactual Memorization in Neural Language Models](https://mlsanity.com/paper/2112.12938/) (2021)
- [Training Language Models with Memory Augmentation](https://mlsanity.com/paper/2205.12674/) (2022)
- [DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering](https://mlsanity.com/paper/2211.05655/) (2022)
- [Language Models are Open Knowledge Graphs](https://mlsanity.com/paper/2010.11967/) (2020)
- [Context-faithful Prompting for Large Language Models](https://mlsanity.com/paper/2303.11315/) (2023)
- [Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge](https://mlsanity.com/paper/2305.01651/) (2023)
- [Kformer: Knowledge Injection in Transformer Feed-Forward Layers](https://mlsanity.com/paper/2201.05742/) (2022)
- [Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy](https://mlsanity.com/paper/2305.18582/) (2023)

## Built on by (most cited first, 11 of 11)

- [Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2402.14409/) (2024)
- [SMART: Self-Aware Agent for Tool Overuse Mitigation](https://mlsanity.com/paper/2502.11435/) (2025)
- [Resolving Knowledge Conflicts in Large Language Models](https://mlsanity.com/paper/2310.00935/) (2023)
- [Taming Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2503.10996/) (2025)
- [Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework](https://mlsanity.com/paper/2409.16146/) (2024)
- [Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models](https://mlsanity.com/paper/2310.01290/) (2023)
- [GTool: Graph Enhanced Tool Planning with Large Language Model](https://mlsanity.com/paper/2508.12725/) (2025)
- [ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models](https://mlsanity.com/paper/2403.05266/) (2024)
- [DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2406.07080/) (2024)
- [Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes](https://mlsanity.com/paper/2601.04716/) (2026)
- [REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control](https://mlsanity.com/paper/2511.20233/) (2025)

## Abstract (arXiv)

Large language models (LLMs) acquire extensive knowledge during pre-training, known as their parametric knowledge. However, in order to remain up-to-date and align with human instructions, LLMs inevitably require external knowledge during their interactions with users. This raises a crucial question: How will LLMs respond when external knowledge interferes with their parametric knowledge? To investigate this question, we propose a framework that systematically elicits LLM parametric knowledge and introduces external knowledge. Specifically, we uncover the impacts by constructing a parametric knowledge graph to reveal the different knowledge structures of LLMs, and introduce external knowledge through distractors of varying degrees, methods, positions, and formats. Our experiments on both black-box and open-source models demonstrate that LLMs tend to produce responses that deviate from their parametric knowledge, particularly when they encounter direct conflicts or confounding changes of information within detailed contexts. We also find that while LLMs are sensitive to the veracity of external knowledge, they can still be distracted by unrelated information. These findings highlight the risk of hallucination when integrating external knowledge, even indirectly, during interactions with current LLMs. All the data and results are publicly available.