Cover Image

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:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
by: Choe, Minyeong, et al.
Published: (2024)

How Do Multilingual Language Models Remember Facts?
by: Fierro, Constanza, et al.
Published: (2024)

Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
by: Chughtai, Bilal, et al.
Published: (2024)

How Do Humans Write Code? Large Models Do It the Same Way Too
by: Li, Long, et al.
Published: (2024)

Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling
by: Lee, Hyunji, et al.
Published: (2025)

Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion
by: Saynova, Denitsa, et al.
Published: (2024)

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
by: Sun, Jingwei, et al.
Published: (2026)

On the Way to LLM Personalization: Learning to Remember User Conversations
by: Magister, Lucie Charlotte, et al.
Published: (2024)

Geometric Factual Recall in Transformers
by: Ravfogel, Shauli, et al.
Published: (2026)

What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models
by: Zhao, Xin, et al.
Published: (2024)

Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models?
by: Modica, Luca, et al.
Published: (2026)

Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time
by: Herel, David, et al.
Published: (2024)

The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models
by: Pradeep, Ronak, et al.
Published: (2025)

Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models
by: Hanna, Michael, et al.
Published: (2024)

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
by: Lv, Ang, et al.
Published: (2024)

Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?
by: Rawat, Shivam, et al.
Published: (2026)

Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP
by: Khurana, Urja, et al.
Published: (2026)

ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models
by: Kim, Minchan, et al.
Published: (2024)

Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge
by: Zhang, Ying, et al.
Published: (2025)

Language Models Change Facts Based on the Way You Talk
by: Kearney, Matthew, et al.
Published: (2025)

Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning
by: Han, Janghoon, et al.
Published: (2024)

Probability Distributions Computed by Autoregressive Transformers
by: Yang, Andy, et al.
Published: (2025)

MoFE: Mixture of Frozen Experts Architecture
by: Seo, Jean, et al.
Published: (2025)

Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea
by: Cho, Eunjung, et al.
Published: (2025)

Do LLMs and Humans Find the Same Questions Difficult? A Case Study on Japanese Quiz Answering
by: Sugiura, Naoya, et al.
Published: (2025)

Understanding Factual Recall in Transformers via Associative Memories
by: Nichani, Eshaan, et al.
Published: (2024)

Facts are Harder Than Opinions -- A Multilingual, Comparative Analysis of LLM-Based Fact-Checking Reliability
by: Saju, Lorraine, et al.
Published: (2025)

Do We Need Language-Specific Fact-Checking Models? The Case of Chinese
by: Zhang, Caiqi, et al.
Published: (2024)

Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models
by: Kim, Jiyeon, et al.
Published: (2026)

One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking
by: Larsson, Malin Astrid, et al.
Published: (2026)

Zero-Shot Learning and Key Points Are All You Need for Automated Fact-Checking
by: Mohammadkhani, Mohammad Ghiasvand, et al.
Published: (2024)

OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature
by: Srivastava, Alisha, et al.
Published: (2025)

Same Company, Same Signal: The Role of Identity in Earnings Call Transcripts
by: Yu, Ding, et al.
Published: (2024)

Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment
by: Kim, Laerdon, et al.
Published: (2026)

Do Music Preferences Reflect Cultural Values? A Cross-National Analysis Using Music Embedding and World Values Survey
by: Kim, Yongjae, et al.
Published: (2025)

Diverse Word Choices, Same Reference: Annotating Lexically-Rich Cross-Document Coreference
by: Zhukova, Anastasia, et al.
Published: (2026)

Transformers Remember First, Forget Last: Dual-Process Interference in LLMs
by: Chattaraj, Sourav, et al.
Published: (2026)

Transfer Learning and Transformer Architecture for Financial Sentiment Analysis
by: Rehman, Tohida, et al.
Published: (2024)

Entity-aware Cross-lingual Claim Detection for Automated Fact-checking
by: Panchendrarajan, Rrubaa, et al.
Published: (2025)

Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
by: Liu, Xiyu, et al.
Published: (2024)