# Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms

arXiv: https://arxiv.org/abs/2509.08778 · HTML: https://mlsanity.com/paper/2509.08778/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [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)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Movement Pruning: Adaptive Sparsity by Fine-Tuning](https://mlsanity.com/paper/2005.07683/) (2020)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks](https://mlsanity.com/paper/1608.04207/) (2016)
- [PMET: Precise Model Editing in a Transformer](https://mlsanity.com/paper/2308.08742/) (2023)
- [What do Neural Machine Translation Models Learn about Morphology?](https://mlsanity.com/paper/1704.03471/) (2017)

## Built on by (most cited first, 3 of 3)

- [Facts in Stats: Impacts of Pretraining Diversity on Language Model Generalization](https://mlsanity.com/paper/2510.16096/) (2025)
- [The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations](https://mlsanity.com/paper/2605.09195/) (2026)
- [Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution](https://mlsanity.com/paper/2605.15138/) (2026)

## Abstract (arXiv)

Understanding how Transformer-based language models store and retrieve factual associations is critical for improving interpretability and enabling targeted model editing. Prior work, primarily on GPT-style models, has identified MLP modules in early layers as key contributors to factual recall. However, it remains unclear whether these findings generalize across different autoregressive architectures. To address this, we conduct a comprehensive evaluation of factual recall across several models -- including GPT, LLaMA, Qwen, and DeepSeek -- analyzing where and how factual information is encoded and accessed. Consequently, we find that Qwen-based models behave differently from previous patterns: attention modules in the earliest layers contribute more to factual recall than MLP modules. Our findings suggest that even within the autoregressive Transformer family, architectural variations can lead to fundamentally different mechanisms of factual recall.