Cover Image

From Memorization to Reasoning in the Spectrum of Loss Curvature

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Merullo, Jack, Vatsavaya, Srihita, Bushnaq, Lucius, Lewis, Owen
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
by: Boppana, Siddharth, et al.
Published: (2026)

Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition
by: Chrisman, Brianna, et al.
Published: (2025)

Circuit Component Reuse Across Tasks in Transformer Language Models
by: Merullo, Jack, et al.
Published: (2023)

Language Models Implement Simple Word2Vec-style Vector Arithmetic
by: Merullo, Jack, et al.
Published: (2023)

I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2
by: McLaughlin, Oliver, et al.
Published: (2025)

Localizing Paragraph Memorization in Language Models
by: Stoehr, Niklas, et al.
Published: (2024)

Transferring Linear Features Across Language Models With Model Stitching
by: Chen, Alan, et al.
Published: (2025)

Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
by: Anand, Suraj, et al.
Published: (2024)

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
by: Bigelow, Eric, et al.
Published: (2026)

Reason to Rote: Rethinking Memorization in Reasoning
by: Du, Yupei, et al.
Published: (2025)

Stochastic Parameter Decomposition
by: Bushnaq, Lucius, et al.
Published: (2025)

$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
by: Khandelwal, Apoorv, et al.
Published: (2024)

Memorization vs. Reasoning: Updating LLMs with New Knowledge
by: Li, Aochong Oliver, et al.
Published: (2025)

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
by: Braun, Dan, et al.
Published: (2025)

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
by: Wu, Mingqi, et al.
Published: (2025)

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
by: Bushnaq, Lucius, et al.
Published: (2024)

Language Models as Causal Effect Generators
by: Bynum, Lucius E. J., et al.
Published: (2024)

Demystifying Verbatim Memorization in Large Language Models
by: Huang, Jing, et al.
Published: (2024)

Representational Curvature Modulates Behavioral Uncertainty in Large Language Models
by: King, Jack, et al.
Published: (2026)

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
by: Lou, Siyu, et al.
Published: (2024)

A Lightweight Method to Disrupt Memorized Sequences in LLM
by: Prashant, Parjanya Prajakta, et al.
Published: (2025)

Rethinking LLM Memorization through the Lens of Adversarial Compression
by: Schwarzschild, Avi, et al.
Published: (2024)

Memorization in In-Context Learning
by: Golchin, Shahriar, et al.
Published: (2024)

FictionalQA: A Dataset for Studying Memorization and Knowledge Acquisition
by: Kirchenbauer, John, et al.
Published: (2025)

Hubble: a Model Suite to Advance the Study of LLM Memorization
by: Wei, Johnny Tian-Zheng, et al.
Published: (2025)

Mitigating Memorization In Language Models
by: Sakarvadia, Mansi, et al.
Published: (2024)

Elephants Never Forget: Testing Language Models for Memorization of Tabular Data
by: Bordt, Sebastian, et al.
Published: (2024)

Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning
by: Bi, Jiaxi, et al.
Published: (2026)

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
by: Ye, Jiayuan, et al.
Published: (2026)

Memorization: A Close Look at Books
by: Ma, Iris, et al.
Published: (2025)

Titans: Learning to Memorize at Test Time
by: Behrouz, Ali, et al.
Published: (2024)

Memorization Dynamics of Fill-in-the-Middle Pretraining
by: von Arx, Tobias, et al.
Published: (2026)

Detecting Memorization in Large Language Models
by: Slonski, Eduardo
Published: (2024)

Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
by: Udsa, Tinnakit, et al.
Published: (2025)

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
by: Yan, Lecheng, et al.
Published: (2026)

Evaluating the Robustness of Analogical Reasoning in Large Language Models
by: Lewis, Martha, et al.
Published: (2024)

Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
by: Hellwig, Philipp, et al.
Published: (2026)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
by: Xiong, Alexander, et al.
Published: (2025)

Exploring Memorization in Fine-tuned Language Models
by: Zeng, Shenglai, et al.
Published: (2023)

Skewed Memorization in Large Language Models: Quantification and Decomposition
by: Li, Hao, et al.
Published: (2025)