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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choe, Minyeong, Cho, Haehyun, Seo, Changho, Kim, Hyunil
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916945097392128
author Choe, Minyeong
Cho, Haehyun
Seo, Changho
Kim, Hyunil
author_facet Choe, Minyeong
Cho, Haehyun
Seo, Changho
Kim, Hyunil
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08778
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms
Choe, Minyeong
Cho, Haehyun
Seo, Changho
Kim, Hyunil
Computation and Language
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.
title Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms
topic Computation and Language
url https://arxiv.org/abs/2509.08778