# In Praise of Stubbornness: An Empirical Case for Cognitive-Dissonance Aware Continual Update of Knowledge in LLMs

arXiv: https://arxiv.org/abs/2502.04390 · HTML: https://mlsanity.com/paper/2502.04390/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Builds on (most cited first, 30 of 32)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Continual Learning of Context-dependent Processing in Neural Networks](https://mlsanity.com/paper/1810.01256/) (2018)
- [EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models](https://mlsanity.com/paper/2308.07269/) (2023)
- [Massive Editing for Large Language Models via Meta Learning](https://mlsanity.com/paper/2311.04661/) (2023)
- [Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning](https://mlsanity.com/paper/2404.00781/) (2024)
- [Unveiling the Pitfalls of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2310.02129/) (2023)
- [Scalable Language Model with Generalized Continual Learning](https://mlsanity.com/paper/2404.07470/) (2024)
- [CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models](https://mlsanity.com/paper/2403.19137/) (2024)
- [A Unified and General Framework for Continual Learning](https://mlsanity.com/paper/2403.13249/) (2024)
- [Disentangling and Mitigating the Impact of Task Similarity for Continual Learning](https://mlsanity.com/paper/2405.20236/) (2024)
- [Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation](https://mlsanity.com/paper/2410.22658/) (2024)
- [SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models](https://mlsanity.com/paper/2411.02175/) (2024)
- [Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2406.18868/) (2024)
- [Vector Quantization Prompting for Continual Learning](https://mlsanity.com/paper/2410.20444/) (2024)
- [Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2408.07413/) (2024)
- [Reasons and Solutions for the Decline in Model Performance after Editing](https://mlsanity.com/paper/2410.23843/) (2024)

## Built on by (most cited first, 2 of 2)

- [ScienceMeter: Tracking Scientific Knowledge Updates in Language Models](https://mlsanity.com/paper/2505.24302/) (2025)
- [The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations](https://mlsanity.com/paper/2609.18560/) (2026)

## Abstract (arXiv)

Through systematic empirical investigation, we uncover a fundamental and concerning property of Large Language Models: while they can safely learn facts that don't contradict their knowledge, attempting to update facts with contradictory information triggers catastrophic corruption of unrelated knowledge. Unlike humans, who naturally resist contradictory information, these models indiscriminately accept contradictions, leading to devastating interference, destroying up to 80% of unrelated knowledge even when learning as few as 10-100 contradicting facts. To understand whether this interference could be mitigated through selective plasticity, we experiment with targeted network updates, distinguishing between previously used (stubborn) and rarely used (plastic) neurons. We uncover another asymmetry: while sparing frequently-used neurons significantly improves retention of existing knowledge for non-contradictory updates (98% vs 93% with standard updates), contradictory updates trigger catastrophic interference regardless of targeting strategy. This effect which persists across tested model scales (GPT-2 to GPT-J-6B), suggests a fundamental limitation in how neural networks handle contradictions. Finally, we demonstrate that contradictory information can be reliably detected (95%+ accuracy) using simple model features, offering a potential protective mechanism. These findings motivate new architectures that can, like humans, naturally resist contradictions rather than allowing destructive overwrites.